Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge the training–inference gap and lack the capacity for fine-grained token selection across multiple dimensions—such as queries, key-values (KV), and heads—leading to suboptimal performance and acceleration gains. In this paper, we introduce OmniSparse, a training-aware fine-grained sparse attention of long-video MLLMs, which is applied in both training and inference with dynamic token budget allocation. Specifically, OmniSparse contains three adaptive and complementary mechanisms: (1) query selection as lazy-active classification, aiming to retain active queries that capture broader semantic similarity, while discarding most of lazy ones that focus on limited local context and exhibit high functional redundancy with their neighbors, (2) KV selection with head-level dynamic budget allocation, where a shared budget is determined based on the flattest head and applied uniformly across all heads to ensure attention recall after selection, and (3) KV cache slimming to alleviate head-level redundancy, which selectively fetches visual KV cache according to the head-level decoding query pattern. Experimental results demonstrate that OmniSparse can achieve comparable performance with full attention, achieving 2.7x speedup during prefill and 2.4x memory reduction for decoding.

Zero-shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with varied visual manipulation intents across domains, scenes, objects, and attributes. A key challenge is that existing datasets contain limited intent-relevant annotations, making it hard for models to infer human intent from textual modifications. We introduce an intent-centric image–text dataset generated via reasoning by a Multimodal Large Language Model (MLLM) to better train ZS-CIR models for human manipulation intent understanding. Building on this dataset, we propose De-MINDS, a framework that distills the MLLM’s reasoning ability to capture manipulation intent and enhance models’ comprehension of modified text. A simple mapping network translates image information into language space and combines it with the manipulation text to form a query. De-MINDS then extracts intention-relevant information from this query and encodes it as pseudo-word tokens for accurate ZS-CIR. Across four ZS-CIR tasks, De-MINDS shows strong generalization and improves over existing methods by 2.15% to 4.05%, establishing new state-of-the-art results with comparable inference time.

Vision-and-language pretraining (VLP) in medicine leverages contrastive learning on image-text pairs, often enhanced with masked modeling.However, existing methods face two challenges: difficulty reconstructing key pathological features due to limited data, and reliance on either paired or image-only datasets without combining both.To address this, we propose MMCLIP (Masked Medical Contrastive Language-Image Pre-training), which introduces two modules: AttMIM, masking image features highly correlated with text to improve reconstruction of fine medical details, and EntMLM, masking key medical entities in text and reconstructing them using visual cues.Furthermore, MMCLIP incorporates unpaired data through disease-kind prompts, achieving state-of-the-art performance in zero-shot and fine-tuning across five benchmarks.Code

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a wide range of vision-language tasks. However, their performance as embodied agents, which requires multi-round interaction with spatial reasoning and sequential action prediction, needs further exploration. Our work investigates this potential in the context of Vision-and-Language Navigation (VLN) by introducing a unified and extensible simulation-free evaluation framework to probe MLLMs as zero-shot agents, named VLN-MME. Simplifying the evaluation with a highly modular and accessible design streamlines experiments, enabling structured comparisons and component-level ablations across diverse MLLM architectures, agent designs, and navigation tasks. Crucially, enabled by VLN-MME, we observe that enhancing prevalent agents with Chain-of-Thought (CoT) reasoning and self-reflection leads to an unexpected performance decrease. This suggests MLLMs exhibit poor context awareness in embodied navigation tasks; although they can follow instructions and structure their output, their 3D spatial reasoning fidelity is low. Furthermore, we demonstrate that agent performance could be largely improved with simple failure cases in context learning. VLN-MME lays the groundwork for systematic evaluation of general-purpose MLLMs in embodied navigation settings and reveals limitations in their sequential decision-making capabilities. We believe these findings offer crucial guidance for MLLM post-training as embodied agents.

The Vision-and-Language Navigation (VLN) task involves an agent navigating within 3D indoor environments based on provided instructions. Achieving cross-modal alignment presents one of the most critical challenges in VLN, as the predicted trajectory needs to precisely align with the given instruction. This paper focuses on addressing cross-modal alignment in VLN from a fine-grained perspective. Firstly, to address the issue of weak cross-modal alignment supervision arising from coarse-grained data, we introduce a human-annotated fine-grained VLN dataset called Landmark-RxR. This dataset aims to offer precise, fine-grained supervision for VLN. Secondly, in order to comprehensively demonstrate the potential and advantage of the fine-grained data from Landmark-RxR, we explore the core components of the training process that depend on the characteristics of the training data. These components include data augmentation, training paradigm, reward shaping, and navigation loss design. Leveraging our fine-grained data, we carefully design methods for handling them and introduce a novel evaluation mechanism. The experimental results demonstrate that the fine-grained data can effectively improve the agent's cross-modal alignment ability.

VQA explanation task aims to explain the decision-making process of VQA models in a way that is easily understandable to humans. Existing methods mostly use visual location or natural language explanation approaches to generate corresponding rationales. Although significant progress has been made, these frameworks are bottlenecked by the following challenges: 1) Uni-modal paradigm inevitably leads to semantic ambiguity of explanations. 2) The reasoning process cannot be faithfully responded to and suffers from logical inconsistency. 3) Human-annotated explanations are expensive and time-consuming to collect. In this paper, we introduce a new Semi-supervised VQA Multi-modal Explanation (SME) method via self-critical learning, which addresses the above challenges by leveraging both visual and textual explanations to comprehensively reveal the inference process of the model. Meanwhile, in order to improve the logical consistency between answers and rationales, we design a novel self-critical strategy to evaluate candidate explanations based on answer reward scores. More importantly, our method can benefit from a tremendous amount of samples without human-annotated explanations with semi-supervised learning. Extensive automatic measures and human evaluations all show the effectiveness of our method. Finally, the framework achieves a new state-of-the-art performance on the three VQA explanation datasets.

Distributed Machine Learning (DML) enables parallel training but creates conflicts regarding model ownership determination, as verifying the specific contributions of individual clients during weight updates remains a challenge. To resolve ownership disputes and prevent malicious clients from forging data, verifying the integrity and effectiveness of each client's unique training history can fairly establish their partial ownership of the final DML model. In this paper, for the first time we propose a novel Matrix Commitment-based DML Ownership Verification (MAMMON) scheme that adopts a concise proof to ensure computational integrity and correctness within a limited computing cost. In contrast to computationally intensive SNARK-based approaches, MAMMON constructs a multi-linear tree structure to reduce proof update costs and avoids complex arithmetic circuit computations by standardizing the training process. Additionally, we watermark the weight proofs using client identity private keys to safeguard the commitments against tampering or unauthorized acquisition. Extensive experiments demonstrate MAMMON's superior performance in preserving computational integrity of DML training, covering both theoretical analysis and comparisons with other existing baselines.

• In REVERIE, the agent needs fine-grained instructions to act more efficiently. • Large Language Models (LLMs) show great potential for the navigation task. • Generating goal plans and single-step instructions improves the agent’s performance. • Parameter-efficient fine-tuning the LLMs results in more accurate navigation plans. • Designing precise prompts alongside fine-tuning mitigates hallucination generation. The remote embodied referring expression (REVERIE) task requires an agent to navigate through complex indoor environments and localize a remote object specified by high-level instructions, such as “ bring me a spoon ”, without pre-exploration. Hence, an efficient navigation plan is essential for the final success. This paper proposes a novel parameter-efficient action planner using large language models (PEAP-LLM) to generate a single-step instruction at each location. The proposed model consists of two modules, LLM goal planner (LGP) and LoRA action planner (LAP). Initially, LGP extracts the goal-oriented plan from REVERIE instructions, including the target object and room. Then, LAP generates a single-step instruction with the goal-oriented plan, high-level instruction, and current visual observation as input. PEAP-LLM enables the embodied agent to interact with LAP as the path planner on the fly. A simple direct application of LLMs hardly achieves good performance. Moreover, existing hard-prompt-based methods are prone to errors in complex scenarios and require human intervention. To address these issues and prevent the LLM from generating hallucinations and biased information, we propose a novel two-stage method for fine-tuning the LLM, consisting of supervised fine-tuning (SFT) and direct preference optimization (DPO). SFT improves the quality of the generated instructions, while DPO incorporates environmental feedback into fine-tuning. Experimental results demonstrate a noticeable enhancement over the baseline model on the REVERIE benchmark.

Referring Video Object Segmentation (RVOS) aims to segment the target objects specified in human instructions. Previous approaches typically rely on explicit human instructions that contain target categories or salient appearance descriptions. These approaches tend to fail when the instructions require temporal video understanding and complex relational reasoning. In this work, we present RViSeg, a reasoning-centric video object segmentation model that leverages the reasoning capability of Multi-modal Large Language Models (MLLM) to handle complex queries. The primary challenge lies in enabling MLLM to perform efficient pixel-level video perception. To tackle this challenge, we introduce a novel Spatial Token Merge (STM) module that consolidates lengthy video tokens into compact region-level clusters, while preserving essential spatial details. This structured representation enables MLLM to infer user intention by interleaving spatial and temporal visual information. Furthermore, we propose a Query-based Target Retrieval (QTR) module that utilizes learnable tokens as the target identity for mask prediction. By propagating these instance-specific tokens both intra-clip and inter-clip, our RViSeg effectively encodes object motion, ensuring spatio-temporal consistency in segmentation results. To facilitate training and evaluation, we construct InstructVideo, a single- and multiple-object reasoning video segmentation benchmark. Comprehensive experiments demonstrate the effectiveness of the proposed components.

Referring Expression Comprehension (REC) aims to achieve fine-grained cross-modal content alignment. The traditional two-stage approaches, by decomposing REC into localization (region proposal) and comprehension (expression-based ranking), lead to the isolation of continuous image information and heavily rely on the quality of the proposals. In this article, we propose a point-based two-stage framework for REC to quickly achieve localization by inserting a language-modulated auto-focus module into the locked vision model. Specifically, we redefine REC as two processes: point-based cross-modal comprehension and point-based instance localization. For the comprehension stage, we reconstruct the raw annotations into soft masks at the feature point level as a metric of cross-modal correlation. With this indirect metric, REC can be approximated as a binary classification problem, which fundamentally avoids the impact of isolated regions. Remarkably, soft masks are shape-independent, which means our method is extremely general. By switching different vision models, different types of predictions (e.g., localization and segmentation) can be obtained. Experiments on multiple benchmarks demonstrate the feasibility and potential of our point-based paradigm. Our code will be public at https://github.com/VILAN-Lab/PBREC-AF .

Multi-modal Federated Learning (MFL) is a distributed machine learning paradigm that enables multiple participants with multi-modal data to collaboratively train a global model for multi-modal tasks without sharing their local data. MFL typically deploys the trained global model as an Embedding-as-a-Service (EaaS), allowing participants to obtain embeddings for downstream tasks. However, it increases the risk of unauthorized copying and leakage of the model. Protecting the ownership of the MFL model while maintaining model performance is challenging. In this paper, we propose the first general model ownership protection framework for MFL, named MFL-Owner. MFL-Owner decouples the watermarking process from the model training process and addresses both ownership verification and traceability, effectively safeguarding the interests of the MFL collective. MFL-Owner leverages the concept of orthogonal transformations by incorporating a linear transformation matrix with orthogonal constraints into the model, achieving high-quality ownership verification and traceability with minimal impact on model performance. To enhance the practicality of the watermark and prevent conflicts among multiple clients during tracing, we propose a trigger dataset selection method based on out-of-distribution data combined with Gaussian noise perturbation. Our experiments on multiple datasets demonstrate that MFL-Owner is effective for model ownership verification and traceability for MFL.

Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent across domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to modify a reference image according to manipulation text to accurately retrieve a target image, especially when the reference image is missing essential target content. In this paper, we propose a novel prediction-based mapping network, named PrediCIR, to adaptively predict the missing target visual content in reference images in the latent space before mapping for accurate ZS-CIR. Specifically, a world view generation module first constructs a source view by omitting certain visual content of a target view, coupled with an action that includes the manipulation intent derived from existing image-caption pairs. Then, a target content prediction module trains a world model as a predictor to adaptively predict the missing visual information guided by user intention in manipulating text at the latent space. The two modules map an image with the predicted relevant information to a pseudo-word token without extra supervision. Our model shows strong generalization ability on six ZS-CIR tasks. It obtains consistent and significant performance boosts ranging from 1.73% to 4.45% over the best methods and achieves new state-of-the-art results on ZS-CIR. Our code is available at https://github.com/Pter61/predicir.

Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user intent more accurately. Existing training-free zero-shot CIR (ZS-CIR) methods often employ a two-stage process: they first generate a caption for the reference image and then use Large Language Models for reasoning a target description. However, these methods suffer from missing critical visual details and limited reasoning capabilities, leading to suboptimal retrieval performance. To address these challenges, we propose a novel, training-free one-stage method, One-Stage Reflective Chain-of-Thought Reasoning (OSrCIR) for ZS-CIR, which employs Multimodal Large Language Models to retain essential visual information in a single-stage reasoning process, eliminating the information loss in two-stage methods. Our Reflective Chain-of-Thought framework further improves interpretative accuracy by aligning manipulation intent with contextual cues from reference images. OSrCIR achieves performance gains of 1.80% to 6.44% over existing training-free methods across multiple tasks, setting new state-of-the-art results in ZS-CIR and enhancing its utility in vision-language applications. Our code is available at https://github.com/microsoft/ACV/tree/main/OSrCIR.

Vision-and-Language Navigation (VLN) tasks have gained prominence within artificial intelligence research due to their potential application in fields like home assistants. Many contemporary VLN approaches, while based on transformer architectures, have increasingly incorporated additional components such as external knowledge bases or map information to enhance performance. These additions, while boosting performance, also lead to larger models and increased computational costs. In this paper, to achieve both high performance and low computational costs, we propose a novel architecture with the COmbination of Selective MemOrization (COSMO). Specifically, COSMO integrates state-space modules and transformer modules, and incorporates two VLN-customized selective state space modules: the Round Selective Scan (RSS) and the Cross-modal Selective State Space Module (CS3). RSS facilitates comprehensive inter-modal interactions within a single scan, while the CS3 module adapts the selective state space module into a dual-stream architecture, thereby enhancing the acquisition of cross-modal interactions. Experimental validations on three mainstream VLN benchmarks, REVERIE, R2R, and R2R-CE, not only demonstrate competitive navigation performance of our model but also show a significant reduction in computational costs.

The academic field of learning instruction-guided visual navigation can be generally categorized into high-level category-specific search and low-level language-guided navigation, depending on the granularity of language instruction, in which the former emphasizes the exploration process, while the latter concentrates on following detailed textual commands. Despite the differing focuses of these tasks, the underlying requirements of interpreting instructions, comprehending the surroundings, and inferring action decisions remain consistent. This paper consolidates diverse navigation tasks into a unified and generic framework -- we investigate the core difficulties of sharing general knowledge and exploiting task-specific capabilities in learning navigation and propose a novel State-Adaptive Mixture of Experts (SAME) model that effectively enables an agent to infer decisions based on different-granularity language and dynamic observations. Powered by SAME, we present a versatile agent capable of addressing seven navigation tasks simultaneously that outperforms or achieves highly comparable performance to task-specific agents.

Large Vision Language Models (LVLMs) have demonstrated remarkable abilities in understanding and reasoning about both visual and textual information. However, existing evaluation methods for LVLMs, primarily based on benchmarks like Visual Question Answering and image captioning, often fail to capture the full scope of LVLMs' capabilities. These benchmarks are limited by issues such as inadequate assessment of detailed visual perception, data contamination, and a lack of focus on multi-turn reasoning. To address these challenges, we propose LVLM-Playground, a game-based evaluation framework designed to provide a comprehensive assessment of LVLMs' cognitive and reasoning skills in structured environments. LVLM-Playground uses a set of games to evaluate LVLMs on four core tasks: Perceiving, Question Answering, Rule Following, and End-to-End Playing, with each target task designed to assess specific abilities, including visual perception, reasoning, decision-making, etc. Based on this framework, we conduct extensive experiments that explore the limitations of current LVLMs, such as handling long structured outputs and perceiving detailed and dense elements. Code and data are publicly available at https://github.com/xinke-wang/LVLM-Playground.

Vision-and-Language Navigation (VLN) tasks mainly evaluate agents based on one-time execution of individual instructions across multiple environments, aiming to develop agents capable of functioning in any environment in a zero-shot manner. However, real-world navigation robots often operate in persistent environments with relatively consistent physical layouts, visual observations, and language styles from instructors. Such a gap in the task setting presents an opportunity to improve VLN agents by incorporating continuous adaptation to specific environments. To better reflect these real-world conditions, we introduce GSA-VLN (General Scene Adaptation for VLN), a novel task requiring agents to execute navigation instructions within a specific scene and simultaneously adapt to it for improved performance over time. To evaluate the proposed task, one has to address two challenges in existing VLN datasets: the lack of out-of-distribution (OOD) data, and the limited number and style diversity of instructions for each scene. Therefore, we propose a new dataset, GSA-R2R, which significantly expands the diversity and quantity of environments and instructions for the Room-to-Room (R2R) dataset to evaluate agent adaptability in both ID and OOD contexts. Furthermore, we design a three-stage instruction orchestration pipeline that leverages large language models (LLMs) to refine speaker-generated instructions and apply role-playing techniques to rephrase instructions into different speaking styles. This is motivated by the observation that each individual user often has consistent signatures or preferences in their instructions, taking the use case of home robotic assistants as an example. We conducted extensive experiments on GSA-R2R to thoroughly evaluate our dataset and benchmark various methods, revealing key factors enabling agents to adapt to specific environments. Based on our findings, we propose a novel method, Graph-Retained DUET (GR-DUET), which incorporates memory-based navigation graphs with an environment-specific training strategy, achieving state-of-the-art results on all GSA-R2R splits.

Vision-and-Language Navigation (VLN) empowers agents to associate time-sequenced visual observations with corresponding instructions to make sequential decisions. However, dealing with visually diverse scenes or transitioning from simulated environments to real-world deployment is still challenging. In this paper, we address the mismatch between human-centric instructions and quadruped robots with a lowheight field of view, proposing a Ground-level Viewpoint Navigation (GVNav) approach to mitigate this issue. This work represents the first attempt to highlight the generalization gap in VLN across varying heights of visual observation in realistic robot deployments. Our approach leverages weighted historical observations as enriched spatiotemporal contexts for instruction following, effectively managing feature collisions within cells by assigning appropriate weights to identical features across different viewpoints. This enables low-height robots to overcome challenges such as visual obstructions and perceptual mismatches. Additionally, we transfer the connectivity graph from the HM3D and Gibson datasets as an extra resource to enhance spatial priors and a more comprehensive representation of real-world scenarios, leading to improved performance and generalizability of the waypoint predictor in real-world environments. Extensive experiments demonstrate that our Groundlevel Viewpoint Navigation (GVnav) approach significantly improves performance in both simulated environments and real-world deployments with quadruped robots.

Vision-and-Language Navigation (VLN) tasks require an agent to follow textual instructions to navigate through 3D environments. Traditional approaches use supervised learning methods, relying heavily on domain-specific datasets to train VLN models. Recent methods try to utilize closedsource large language models (LLMs) like GPT-4 to solve VLN tasks in zero-shot manners, but face challenges related to expensive token costs and potential data breaches in realworld applications. In this work, we introduce Open-Nav, a novel study that explores open-source LLMs for zero-shot VLN in the continuous environment. Open-Nav employs a spatial-temporal chain-of-thought (CoT) reasoning approach to break down tasks into instruction comprehension, progress estimation, and decision-making. It enhances scene perceptions with fine-grained object and spatial knowledge to improve LLM's reasoning in navigation. Our extensive experiments in both simulated and real-world environments demonstrate that Open-Nav achieves competitive performance compared to using closed-source LLMs.

In recent years, Embodied Artificial Intelligence (Embodied AI) has advanced rapidly, yet the increasing size of models conflicts with the limited computational capabilities of Embodied AI platforms. To address this challenge, we aim to achieve both high model performance and practical deployability. Specifically, we focus on Vision-and-Language Navigation (VLN), a core task in Embodied AI. This paper introduces a two-stage knowledge distillation framework, producing a student model, MiniVLN, and showcasing the significant potential of distillation techniques in developing lightweight models. The proposed method aims to capture fine-grained knowledge during the pretraining phase and navigation-specific knowledge during the fine-tuning phase. Our findings indicate that the two-stage distillation approach is more effective in narrowing the performance gap between the teacher model and the student model compared to single-stage distillation. On the public R2R and REVERIE benchmarks, MiniVLN achieves performance on par with the teacher model while having only about 12 % of the teacher model's parameter count.

Latent diffusion models have exhibited considerable potential in generative tasks. Watermarking is considered to be an alternative to safeguard the copyright of generative models and prevent their misuse. However, in the context of model distribution scenarios, the accessibility of models to large scale of model users brings new challenges to the security, efficiency and robustness of existing watermark solutions. To address these issues, we propose a secure and efficient watermarking solution. A new security mechanism is designed to prevent watermark leakage and watermark escape, which considers watermark randomness and watermark-model association as two constraints for mandatory watermark injection. To reduce the time cost of training the security module, watermark injection and the security mechanism are decoupled, ensuring that fine-tuning VAE only accomplishes the security mechanism without the burden of learning watermark patterns. A watermark distribution-based verification strategy is proposed to enhance the robustness against diverse attacks in the model distribution scenarios. Experimental results prove that our watermarking consistently outperforms existing six baselines on effectiveness and robustness against ten image processing attacks and adversarial attacks, while enhancing security in the distribution scenarios. The code is available at https://anonymous.4open.science/r/DistriMark-F11F/.

Vision-and-Language Navigation (VLN) in continuous environments requires agents to interpret natural language instructions while navigating unconstrained 3D spaces. Existing VLN-CE frameworks rely on a two-stage approach: a waypoint predictor to generate waypoints and a navigator to execute movements. However, current waypoint predictors struggle with spatial awareness, while navigators lack historical reasoning and backtracking capabilities, limiting adaptability. We propose a zero-shot VLN-CE framework integrating an enhanced waypoint predictor with a Multi-modal Large Language Model (MLLM)-based navigator. Our predictor employs a stronger vision encoder, masked cross-attention fusion, and an occupancy-aware loss for better waypoint quality. The navigator incorporates history-aware reasoning and adaptive path planning with backtracking, improving robustness. Experiments on R2R-CE and MP3D benchmarks show our method achieves state-of-the-art (SOTA) performance in zero-shot settings, demonstrating competitive results compared to fully supervised methods. Real-world validation on Turtlebot 4 further highlights its adaptability.

Commanding robots to do chores using natural language instructions has been a dream of us for a long time. The navigation capability, as one of the key foundational abilities to achieve this goal, has garnered significant attention in this regard. When human users instruct intelligent agent, the instructions they given sometimes exhibit slight discrepancies from navigable ones, as user's understanding of scene may not be up-to-date due to instant change of environments. This paper investigates 3 common scenarios where instructions and navigation scenes are imperfectly aligned: change of navigability, incorrect landmark references, and incorrect direction descriptions. We then propose an ImperfectVLN task and dataset for evaluating an agent's navigation performance under instruction and environment imperfectly matched conditions. Evaluation results indicate significant performance fluctuations in existing state-of-the-art models under modification scenarios including referred landmark removal and original path blockages. We also provide a series of result analyses and further insights. We aim for this new dataset to become a valuable benchmark, enhancing practical VLN tasks. We further design a reflection module based on our insights, allowing an agent to review its history and identify potential errors. Experiments show that this module improves the performance on ImperfectVLN by 4.4%.

Multimodal Large Language Models (MLLMs) have demonstrated strong generalization in vision-language tasks, yet their ability to understand and act within embodied environments remains underexplored. We present NavBench, a benchmark to evaluate the embodied navigation capabilities of MLLMs under zero-shot settings. NavBench consists of two components: (1) navigation comprehension, assessed through three cognitively grounded tasks including global instruction alignment, temporal progress estimation, and local observation-action reasoning, covering 3,200 question-answer pairs; and (2) step-by-step execution in 432 episodes across 72 indoor scenes, stratified by spatial, cognitive, and execution complexity. To support real-world deployment, we introduce a pipeline that converts MLLMs' outputs into robotic actions. We evaluate both proprietary and open-source models, finding that GPT-4o performs well across tasks, while lighter open-source models succeed in simpler cases. Results also show that models with higher comprehension scores tend to achieve better execution performance. Providing map-based context improves decision accuracy, especially in medium-difficulty scenarios. However, most models struggle with temporal understanding, particularly in estimating progress during navigation, which may pose a key challenge.

Goal-Oriented Vision-and-Language Navigation (VLN) aims to enable agents to navigate to specified locations and identify designated target objects following natural language instruction. This approach has gained popularity due to its close alignment with real-world scenarios. However, existing studies have predominantly focused on enhancing navigation performance, neglecting the ability to locate objects at the navigation endpoint. This oversight has resulted in a significant discrepancy between the success rates of navigation and object grounding. The challenge is compounded by the complex reasoning required by the instructions and the necessity to synthesize multiperspective images of objects, which overwhelms traditional object grounding methods. We leverage the Multi-Modal Large Language Model (MLLM) to bridge this gap, allowing agents to seek assistance from these models when struggling to locate the target object. The agent conducts a multi-stage evaluation to discern the cause of its confusion and promptly extracts and updates the most relevant information for MLLM to assess. Our method is plug-and-play and model-agnostic, facilitating integration with numerous existing VLN strategies without the need for retraining. Implementing our approach across four distinct methods has improved performance on the REVERIE and SOON datasets, demonstrating the effectiveness and generalizability of our technique.

Storyboards comprising key illustrations and images help filmmakers to outline ideas, key moments, and story events when filming movies. Inspired by this, we introduce the first contextual benchmark dataset Script-to-Storyboard (Sc2St) composed of storyboards to explicitly express story structures in the movie domain, and propose the contextual retrieval task to facilitate movie story understanding. The Sc2St dataset contains fine-grained and diverse texts, annotated semantic keyframes, and coherent storylines in storyboards, unlike existing movie datasets. The contextual retrieval task takes as input a multi-sentence movie script summary with keyframe history and aims to retrieve a future keyframe described by a corresponding sentence to form the storyboard. Compared to classic text-based visual retrieval tasks, this requires capturing the context from the description (script) and keyframe history. We benchmark existing text-based visual retrieval methods on the new dataset and propose a recurrent-based framework with three variants for effective context encoding. Comprehensive experiments demonstrate that our methods compare favourably to existing methods; ablation studies validate the effectiveness of the proposed context encoding approaches.

Given a piece of text, a video clip, and reference audio, the movie dubbing (also known as Visual Voice Cloning, V2C) task aims to generate speeches that clone reference voice and align well with the video in both emotion and lip movement, which is more challenging than conventional text-to-speech synthesis tasks. To align the generated speech with the inherent lip motion of the given silent video, most existing works utilize each video frame to query textual phonemes. However, such an attention operation usually leads to mumble speech because different phonemes are fused for video frames corresponding to one phoneme (video frames are finer-grained than phonemes). To address this issue, we propose a diffusion-based movie dubbing architecture, which improves pronunciation by Hierarchical Phoneme Modeling (HPM) and generates better mel-spectrogram through Acoustic Diffusion Denoising (ADD). We term our model as HD-Dubber. Specifically, our HPM bridges the visual information and corresponding speech prosody from three aspects: (1) aligning lip movement with the speech duration based on each phoneme unit by contrastive learning; (2) conveying facial expression to phoneme-level energy and pitch; and (3) injecting global emotions captured from video scenes into prosody. On the other hand, ADD exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via a parameterized Markov chain conditioned on textual phonemes and reference audio. ADD has two novel denoisers, the Style-adaptive Residual Denoiser (SRD) and the Phoneme-enhanced U-net Denoiser (PUD), to enhance speaker similarity and improve pronunciation quality. Extensive experimental results on the three benchmark datasets demonstrate the state-of-the-art performance of the proposed method. The source code and trained models will be made available to the public.

Visual Question Answering (VQA) is a prevalent task that can facilitate the perception of the real world by the visually impaired. However, many VQA models tend to rely on superficial correlations in datasets for predictions rather than genuine reasoning, limiting their real-world applicability. While existing methods address this issue by incorporating debiasing strategies during training, they typically assume prior knowledge of out-of-distribution (OOD) test sets and then tailor debiasing strategies and select optimal models on the basis of the OOD samples. This reliance on OOD test data, however, is unrealistic in practical applications. To address this, some works introduce test-time adaptation techniques to mitigate dataset shifts during model deployment. Despite their potential, these methods risk catastrophic forgetting as they update models at test time without access to the ground-truth answers or the source data. An emerging solution involves leveraging the extensive knowledge embedded in Large Language Models (LLMs) to support reasoning tasks, yet their language-only input restricts flexibility in multimodal tasks. To bridge this gap, we propose leveraging the zero-shot capability of Multimodal Large Language Models (MLLMs). To optimise computational efficiency, we introduce a novel VQA Collaborative Inference framework (VQA-CI) that integrates MLLMs (e.g.BLIP-2 Flan T5) with VQA specialists (e.g.UpDn). This framework initially processes samples through VQA specialists and subsequently determines the necessity for re-evaluation with MLLMs based on predefined bias and reliability indicators. Experiments on the GQA-OOD and VQA-CP v2 datasets show that our VQA-CI achieves significant performance gains, with accuracy improvements of around 6% over state-of-the-art methods, underscoring the effectiveness of our VQA-CI.

Vision-and-Language Navigation (VLN) task aims to enable AI agents to accurately understand and follow natural language instructions to navigate through real-world environments, ultimately reaching specific target locations. We recognise a promising opportunity to extend VLN to a comparable navigation task that holds substantial significance in our daily lives, albeit within the virtual realm: navigating websites on the Internet. This paper proposes a new task named Vision-and-Language Navigation on Websites (WebVLN), where we use question-based instructions to train an agent, emulating how users naturally browse websites. Unlike the existing VLN task that only pays attention to vision and instruction (language), the WebVLN agent further considers underlying web-specific content like HTML, which could not be seen on the rendered web pages yet contain rich visual and textual information. Toward this goal, we contribute a dataset, WebVLN-v1, and introduce a novel approach called Website-aware VLN Network (WebVLN-Net), which is built upon the foundation of state-of-the-art VLN techniques. Experimental results show that WebVLN-Net outperforms current VLN and web-related navigation methods. We believe that the introduction of the newWebVLN task and its dataset will establish a new dimension within the VLN domain and contribute to the broader vision-and-language research community. Code is available at: https://github.com/WebVLN/WebVLN.

The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object features to represent navigable viewpoints. However, these representations are insufficient for proper action prediction, especially for the REVERIE task, which uses concise high-level instructions, such as “Bring me the blue cushion in the master bedroom”. To address enhancing representation, we propose an augmented commonsense knowledge model (ACK) to leverage commonsense information as a spatio-temporal knowledge graph for improving agent navigation. Specifically, the proposed approach involves constructing a knowledge base by retrieving commonsense information from ConceptNet, followed by a refinement module to remove noisy and irrelevant knowledge. We further present ACK which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information. Moreover, we add a new pipeline for the commonsense-based decision-making process which leads to more accurate local action prediction. Experimental results demonstrate our proposed model noticeably outperforms the baseline and archives the state-of-the-art on the REVERIE benchmark. The source code is available at https://github.com/Bahram-Mohammadi/ACK.

Different from the Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to learn a more accurate image representation that has adaptive attention to the reference image for various manipulation descriptions. In this paper, we propose a novel context-dependent mapping network, named Context-I2W, for adaptively converting description-relevant Image information into a pseudo-word token composed of the description for accurate ZS-CIR. Specifically, an Intent View Selector first dynamically learns a rotation rule to map the identical image to a task-specific manipulation view. Then a Visual Target Extractor further captures local information covering the main targets in ZS-CIR tasks under the guidance of multiple learnable queries. The two complementary modules work together to map an image to a context-dependent pseudo-word token without extra supervision. Our model shows strong generalization ability on four ZS-CIR tasks, including domain conversion, object composition, object manipulation, and attribute manipulation. It obtains consistent and significant performance boosts ranging from 1.88% to 3.60% over the best methods and achieves new state-of-the-art results on ZS-CIR. Our code is available at https://anonymous.4open.science/r/Context-I2W-4224/.

Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling. Such a trend underscored the potential of training LLMs with unlimited language data, advancing the development of a universal embodied agent. In this work, we introduce the NavGPT, a purely LLM-based instruction-following navigation agent, to reveal the reasoning capability of GPT models in complex embodied scenes by performing zero-shot sequential action prediction for vision-and-language navigation (VLN). At each step, NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status, and makes the decision to approach the target. Through comprehensive experiments, we demonstrate NavGPT can explicitly perform high-level planning for navigation, including decomposing instruction into sub-goals, integrating commonsense knowledge relevant to navigation task resolution, identifying landmarks from observed scenes, tracking navigation progress, and adapting to exceptions with plan adjustment. Furthermore, we show that LLMs is capable of generating high-quality navigational instructions from observations and actions along a path, as well as drawing accurate top-down metric trajectory given the agent's navigation history. Despite the performance of using NavGPT to zero-shot R2R tasks still falling short of trained models, we suggest adapting multi-modality inputs for LLMs to use as visual navigation agents and applying the explicit reasoning of LLMs to benefit learning-based models. Code is available at: https://github.com/GengzeZhou/NavGPT.

Novel view synthesis aims to generate new view images of a given view image collection. Recent attempts address this problem relying on 3D geometry priors (e.g., shapes, sizes, and positions) learned from multi-view images. However, such methods encounter the following limitations: 1) they require a set of multi-view images as training data for a specific scene (e.g., face, car or chair), which is often un-available in many real-world scenarios; 2) they fail to ex-tract the geometry priors from single-view images due to the lack of multi-view supervision. In this paper, we pro-pose a Geometry-enhanced NeRF (G-NeRF), which seeks to enhance the geometry priors by a geometry-guided multi-view synthesis approach, followed by a depth-aware training. In the synthesis process, inspired that existing 3D GAN models can unconditionally synthesize high-fidelity multi-view images, we seek to adopt off-the-shelf 3D GAN models, such as EG3D, as a free source to provide geometry priors through synthesizing multi-view data. Simultaneously, to further improve the geometry quality of the synthetic data, we introduce a truncation method to effectively sample la-tent codes within 3D GAN models. To tackle the absence of multi-view supervision for single-view images, we design the depth-aware training approach, incorporating a depth-aware discriminator to guide geometry priors through depth maps. Experiments demonstrate the effectiveness of our method in terms of both qualitative and quantitative results.

Medical vision language pre-training (VLP) has emerged as a frontier of research, enabling zero-shot pathological recognition by comparing the query image with the textual descriptions for each disease. Due to the complex semantics of biomedical texts, current methods struggle to align medical images with key pathological findings in un-structured reports. This leads to the misalignment with the target disease's textual representation. In this paper, we introduce a novel VLP framework designed to dissect disease descriptions into their fundamental aspects, leveraging prior knowledge about the visual manifestations of pathologies. This is achieved by consulting a large language model and medical experts. Integrating a Transformer module, our approach aligns an input image with the diverse elements of a disease, generating aspect-centric image representations. By consolidating the matches from each aspect, we improve the compatibility between an image and its associated disease. Additionally, capitalizing on the aspect-oriented representations, we present a dual-head Transformer tailored to process known and unknown diseases, optimizing the comprehensive detection efficacy. Conducting experiments on seven downstream datasets, ours improves the accuracy of recent methods by up to 8.56% and 17.26% for seen and unseen categories, respectively. Our code is released at https://github.com/HieuPhan33/MAVL.

Humans possess the capability to comprehend diverse modalities and seamlessly transfer information between them. In this work, we introduce ModaVerse, a Multi-modal Large Language Model (MLLM) capable of comprehending and transforming content across various modalities in-cluding images, videos, and audio. Predominant MLLM frameworks have largely relied on aligning latent spaces of textual and non-textual features. This alignment process, which synchronizes a language model trained on tex-tual data with encoders and decoders trained on multimodal data, often necessitates extensive training of several projection layers in multiple stages. Inspired by LLM-as-agent methodologies, we propose a novel Input/Output (I/O) alignment mechanism that operates directly at the level of natural language. It aligns the LLM's output with the input of generative models, avoiding the complexities associated with latent feature alignments, and simplifying the multiple training stages of existing MLLMs into a single, efficient process. By conducting experiments on several benchmarks, we demonstrate that our approach at-tains comparable performance with the state of the art while achieving considerable efficiencies in data usage. The code is available at https://github.com/xinke-wang/ModaVerse.

Current vision-language pre-training (VLP) methodologies predominantly depend on paired image-text datasets, a resource that is challenging to acquire in radiology due to privacy considerations and labelling complexities. Data augmentation provides a practical solution to overcome the issue of data scarcity, however, most augmentation methods exhibit a limited focus, prioritising either image or text augmentation exclusively. Acknowledging this limitation, our objective is to devise a framework capable of concurrently augmenting medical image and text data. We design a Pairwise Augmentation (PairAug) approach that contains an Inter-patient Augmentation (InterAug) branch and an Intra-patient Augmentation (IntraAug) branch. Specifically, the InterAug branch of our approach generates radiology images using synthesised yet plausible reports derived from a Large Language Model (LLM). The generated pairs can be considered a collection of new patient cases since they are artificially created and may not exist in the original dataset. In contrast, the IntraAug branch uses newly generated reports to manipulate images. This process allows us to create new paired data for each individual with diverse medical conditions. Our extensive experiments on various downstream tasks covering medical image classification zero-shot and fine-tuning analysis demonstrate that our PairAug, concurrently expanding both image and text data, substantially outperforms image-/text-only expansion baselines and advanced medical VLP baselines. Our code is released at https://github.com/YtongXie/PairAug.

Self-supervised learning (SSL) is an efficient pre-training method for medical image analysis. However, current research is mostly confined to certain modalities, consuming considerable time and resources without achieving universality across different modalities. A straightforward solution is combining all modality data for joint SSL, which poses practical challenges. Firstly, our experiments reveal conflicts in representation learning as the number of modalities increases. Secondly, multi-modal data collected in advance cannot cover all real-world scenarios. In this paper, we reconsider versatile SSL from the perspective of continual learning and propose MedCoSS, a continuous SSL approach for multi-modal medical data. Different from joint representation learning, MedCoSS assigns varying data modalities to separate training stages, creating a multi-stage pre-training process. We propose a rehearsal- based continual learning approach to manage modal conflicts and prevent catastrophic forgetting. Specifically, we use the k-means sampling to retain and rehearse previous modality data during new modality learning. Moreover, we apply feature distillation and intra-modal mixup on buffer data for knowledge retention, bypassing pretext tasks. We conduct experiments on a large-scale multi-modal unlabeled dataset, including clinical reports, X-rays, CT, MRI, and pathological images. Experimental results demonstrate MedCoSS's exceptional generalization ability across 9 downstream datasets and its significant scalability in inte- grating new modality data. The code and pre-trained model are available at https://github.com/yeerwen/MedCoSS.

In numerous medical scenarios, segmenting clinical targets is highly subjective, influenced by the doctors' expertise and preferences, which results in significant multi-rater variability. This inherent annotation ambiguity poses a challenge for the practical deployment of data-driven techniques and raises concerns about the reliability of automatic predictions by medical artificial intelligence (AI) systems. To address this issue, we host a grand challenge (MMIS-2024) at ACM MM '24 to explore the problem of multi-rater medical image segmentation. First, we have released two datasets publicly, one on nasopharyngeal carcinoma (NPC) and the other on glioblastoma (GBM). For NPC, one challenge track encourages participants to develop models that utilize the four expert-provided labels per sample. The second GBM track explores the one-sample-one-label setting in the context of multi-rater segmentation. Here, different experts annotated different GBM samples for training. Finally, to assess the submissions, we employ two distinct sets of metrics, designed to evaluate prediction diversity and personalization, respectively. By exploring the two tasks with different metrics, the MMIS-2024 challenge aims to establish a global benchmark for multi-rater medical image segmentation, facilitating clinical AI deployments.

Real-world navigation often involves dealing with unexpected obstructions such as closed doors, moved objects, and unpredictable entities. However, mainstream Vision-and-Language Navigation (VLN) tasks typically assume instructions perfectly align with the fixed and predefined navigation graphs without any obstructions. This assumption overlooks potential discrepancies in actual navigation graphs and given instructions, which can cause major failures for both indoor and outdoor agents. To address this issue, we integrate diverse obstructions into the R2R dataset by modifying both the navigation graphs and visual observations, introducing an innovative dataset and task, R2R with UNexpected Obstructions (R2R-UNO). R2R-UNO contains various types and numbers of path obstructions to generate instruction-reality mismatches for VLN research. Experiments on R2R-UNO reveal that state-of-the-art VLN methods inevitably encounter significant challenges when facing such mismatches, indicating that they rigidly follow instructions rather than navigate adaptively. Therefore, we propose a novel method called ObVLN (Obstructed VLN), which includes a curriculum training strategy and virtual graph construction to help agents effectively adapt to obstructed environments. Empirical results show that ObVLN not only maintains robust performance in unobstructed scenarios but also achieves a substantial performance advantage with unexpected obstructions. The source code is available at https://github.com/honghd16/ObstructedVLN.

Current text-video retrieval methods mainly rely on cross-modal matching between queries and videos to calculate their similarity scores, which are then sorted to obtain retrieval results. This method considers the matching between each candidate video and the query, but it incurs a significant time cost and will increase notably with the increase of candidates. Generative models are common in natural language processing and computer vision, and have been successfully applied in document retrieval, but their application in multimodal retrieval remains unexplored. To enhance retrieval efficiency, in this paper, we introduce a model-based video indexer named T2VIndexer, which is a sequence-to-sequence generative model directly generating video identifiers and retrieving candidate videos with constant time complexity. T2VIndexer aims to reduce retrieval time while maintaining high accuracy. To achieve this goal, we propose video identifier encoding and query-identifier augmentation approaches to represent videos as short sequences while preserving their semantic information. Our method consistently enhances the retrieval efficiency of current state-of-the-art models on four standard datasets. It enables baselines with only 30%-50% of the original retrieval time to achieve better retrieval performance on MSR-VTT (+1.0%), MSVD (+1.8%), ActivityNet (+1.5%), and DiDeMo (+0.2%). The code is available at https://github.com/Lilidamowang/T2VIndexer-generativeSearch.

Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with corresponding images to transfer knowledge. However, they disregard that semantic information is not equivalent between them, resulting in a suboptimal alignment. In this work, we propose a novel network to extract multi-view semantic concepts from documents and images and align the matching rather than entire concepts. Specifically, we propose a semantic decomposition module to generate multi-view semantic embeddings from visual and textual sides, providing the basic concepts for partial alignment. To alleviate the issue of information redundancy among embeddings, we propose the local-to-semantic variance loss to capture distinct local details and multiple semantic diversity loss to enforce orthogonality among embeddings. Subsequently, two losses are introduced to partially align visual-semantic embedding pairs according to their semantic relevance at the view and word-to-patch levels. Consequently, we consistently outperform state-of-the-art methods under two document sources in three standard benchmarks for document-based zero-shot learning. Qualitatively, we show that our model learns the interpretable partial association. Code is available at https://github.com/MorningStarOvO/EmDepart.

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore environments following natural language. The VLN agent, closely integrated into daily lives, poses a substantial threat to the security of privacy and property upon the occurrence of malicious behavior. However, this serious issue has long been overlooked. In this paper, we pioneer the exploration of an object-aware backdoored VLN, achieved by implanting object-aware backdoors during the training phase. Tailored to the unique VLN nature of cross-modality and continuous decision-making, we propose a novel backdoored VLN paradigm: IPR Backdoor. This enables the agent to act in abnormal behavior once encountering the object triggers during language-guided navigation in unseen environments, thereby executing an attack on the target scene. Experiments demonstrate the effectiveness of our method in both physical and digital spaces across different VLN agents, as well as its robustness to various visual and textual variations. Additionally, our method also well ensures navigation performance in normal scenarios with remarkable stealthiness.

Masked Image Modelling (MIM), a form of self-supervised learning, has garnered significant success in computer vision by improving image representations using unannotated data. Traditional MIMs typically employ a strategy of random sampling across the image. However, this random masking technique may not be ideally suited for medical imaging, which possesses distinct characteristics divergent from natural images. In medical imaging, particularly in pathology, disease-related features are often exceedingly sparse and localized, while the remaining regions appear normal and undifferentiated. Additionally, medical images frequently accompany reports, directly pinpointing pathological changes' location. Inspired by this, we propose Masked medical Image Modelling (MedIM), a novel approach, to our knowledge, the first research that employs radiological reports to guide the masking and restore the informative areas of images, encouraging the network to explore the stronger semantic representations from medical images. We introduce two mutual comprehensive masking strategies, knowledge-driven masking (KDM), and sentence-driven masking (SDM). KDM uses Medical Subject Headings (MeSH) words unique to radiology reports to identify symptom clues mapped to MeSH words (e.g., cardiac, edema, vascular, pulmonary) and guide the mask generation. Recognizing that radiological reports often comprise several sentences detailing varied findings, SDM integrates sentence-level information to identify key regions for masking. MedIM reconstructs images informed by this masking from the KDM and SDM modules, promoting a comprehensive and enriched medical image representation. Our extensive experiments on seven downstream tasks covering multi-label/class image classification, pneumothorax segmentation, and medical image-report analysis, demonstrate that MedIM with report-guided masking achieves competitive performance. Our method substantially outperforms ImageNet pre-training, MIM-based pre-training, and medical image-report pre-training counterparts. Codes are available at https://github.com/YtongXie/MedIM.

Image captioning is one of the fundamental problems of computer vision and has drawn great attention over the years. However, most existing methods in image captioning focus on improving the quality of the image captions, while ignoring the ability of controlling the caption style. In this work, we aim to improve the controllability of image captioning methods, especially, by choosing to describe the image either roughly or in detail. We find this can be achieved by adding a simple length level embedding into existing models, which enables them to generate length-controllable captions describing the image at a specified level of detail, and further improve the diversity. On top of it, we propose to learn a length-level reranking transformer that captures the correlation between the semantic complexities of the image and text modalities, which can be used to select the most suitable length level for each image to make the captions informative while not being redundant. Moreover, when the length of the generated captions grows, existing methods usually suffer from a linearly increased computational complexity due to their autoregressive (AR) nature. To aid this, we devise a non-autoregressive (NAR) approach that generates captions in a length-irrelevant complexity. Besides, we propose a refinement-enhanced sequence training scheme and also adopt a sequence-level knowledge distillation technique for the training of our NAR model to bridge its performance gap with the AR models. In the experiments, our length-controllable models not only achieve SOTA performance in terms of caption quality on the MS COCO dataset but more importantly, generate controllable and diverse image captions. Specifically, our NAR model outperforms the AR baselines in terms of controllability and diversity, and also significantly improves the decoding efficiency for longer captions. By further applying the sequence-level training schemes, the caption quality of our NAR model improves clearly and is competitive with the state-of-the-art AR baselines.

Given a high-level instruction, the task of Embodied Referring Expression (REVERIE) requires an embodied agent to localise a remote referred object via navigating in the unseen environment. Previous vision-language navigation methods utilise the provided fine-grained instruction as step-by-step navigation guidance to conduct strict instruction-following, while REVERIE aims to achieve efficient goal-oriented exploration according to the high-level command. In this work, we propose a Cross-modal Knowledge Reasoning (abbreviated as CKR+) framework, which incorporates the prior knowledge as decision guidance to learn the navigation scheme comprehensively. Specifically, we design a Room-Object Aware (ROA) mechanism to explicitly decouple the room- and object-related clues from instruction and visual observations. Moreover, we propose a Knowledge-enabled Entity Relation Reasoning (KERR+) module to leverage the structured knowledge from the knowledge graph explicitly and unstructured knowledge from pre-trained model implicitly, to learn the internal-external correlations among room- and object-entities for the agent to make proper decisions. We devise an Entity Prompter (EP) that embeds in the KERR+ module, which utilises the navigation history and visual entities as prompts to transfer knowledge from the pre-trained CLIP model. In addition, we develop a Reinforced End Decider (RED) to learn the stopping scheme specifically, which is achieved by a customised reinforcement learning strategy and knowledge enhanced matching. Two techniques are also introduced to improve navigation efficiency further. Extensive experiments conducted on the REVERIE benchmark demonstrate the effectiveness and superiority of our proposed methods, which boosts the key metrics, i.e., SPL and REVERIE-success rate, to 14.46% and 13.81% respectively.

Self-supervised learning (SSL) opens up huge opportunities for medical image analysis that is well known for its lack of annotations. However, aggregating massive (unlabeled) 3D medical images like computerized tomography (CT) remains challenging due to its high imaging cost and privacy restrictions. In our pilot study, we advocated bringing a wealth of 2D images like X-rays as compensation for the lack of 3D data, aiming to build a universal medical self-supervised representation learning framework, called UniMiSS. Especially, we designed a pyramid U-like medical Transformer (MiT) as the backbone to make UniMiSS possible to perform SSL with both 2D and 3D images. UniMiSS surpasses current 3D-specific SSL in effectiveness and versatility, excelling in various downstream tasks and overcoming the limitations of dimensionality. However, the initial version did not fully explore the anatomical correlations between 2D and 3D images due to the absence of paired multi-modal patient data. In this extension, we introduce UniMiSS+, which leverages digitally reconstructed radiographs (DRR) technology to simulate X-rays from CT volumes, providing access to paired data. Benefiting from the paired group, we introduce an extra pair-wise constraint to boost the cross modality correlation learning, which also can be adopted as a cross dimension regularization to further improve the representations. We conduct expensive experiments on multiple 3D/2D medical image analysis tasks, including segmentation and classification. The results show that our UniMiSS+ achieves promising performance on various downstream tasks, not only outperforming ImageNet pre-training and other advanced SSL counterparts but also improving the predecessor UniMiSS pre-training.

Visual question answering (VQA) is a prevalent task in real-world, and plays an essential role in helping the blind understand the physical world. However, due to the real-world complexity, VQA test samples may come from a different distribution from the training data, resulting in unavoidable performance degradation. This similar issue also exists in the image recognition field, in which one most recent effective solutions is a test-time adaptation (TTA). TTA adapts a trained model at test time using only test samples, which provides a new idea to alleviate the analogous issue in VQA. However, naively introducing existing TTA methods (e.g.,test-time entropy minimisation) into VQA is imperfect and achieves only marginal performance gain. The reason is that prior methods do not consider the special nature of the VQA problem and ignore that 1) the biased samples in the dataset may have negative effects on test-time model adaptation, and 2) the model may have captured the biases in the dataset. In this paper, we propose Test-time Debiased Self-supervised (TDS) learning objectives for VQA model adaptation. Specifically, we minimise the entropy for those unbiased test samples. To identify these samples, we construct a negative sample for each test sample, and regard the test samples as unbiased if the output answers are different when feeding the test sample and the counterpart negative sample into the VQA model. Meanwhile, we also remove those samples with high prediction entropy from adaptation, making the test-time gradients more reliable. To hinder the model from excessively fitting the superficial correlations of the biased sample, we adopt the biased samples and the counterpart negative samples to assist the adaptation. Extensive experiments on the VQA-CP v1 and VQA-CP v2 datasets demonstrate the effectiveness of our TDS.

Visual Relational Reasoning is the basis of many vision-and-language based tasks (e.g., visual question answering and referring expression comprehension). In this article, we regard the complex referring expression comprehension (c-REF) task as the reasoning basis, in which c-REF seeks to localise a target object in an image guided by a complex query. Such queries often contain complex logic and thus impose two critical challenges for reasoning: (i) Comprehending the complex queries is difficult since these queries usually refer to multiple objects and their relationships; (ii) Reasoning among multiple objects guided by the queries and then localising the target correctly are non-trivial. To address the above challenges, we propose a Transformer-based Relational Inference Network (Trans-RINet). Specifically, to comprehend the queries, we mimic the language-comprehending mechanism of humans, and devise a language decomposition module to decompose the queries into four types, i.e., basic attributes, absolute location, visual relationship and relative location. We further devise four modules to address the corresponding information. In each module, we consider the intra-(i.e., between the objects) and inter-modality relationships(i.e., between the queries and objects) to improve the reasoning ability. Moreover, we construct a relational graph to represent the objects and their relationships, and devise a multi-step reasoning method to progressively understand the complex logic. Since each type of the queries is closely related, we let each module interact with each other before making a decision. Extensive experiments on the CLEVR-Ref+, Ref-Reasoning, and CLEVR-CoGenT datasets demonstrate the superior reasoning performance of our Trans-RINet.

Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone, V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference. V2C is more challenging than conventional text-to-speech tasks as it additionally requires the generated speech to exactly match the varying emotions and speaking speed presented in the video. Unlike previous works, we propose a novel movie dubbing architecture to tackle these problems via hierarchical prosody modeling, which bridges the visual information to corresponding speech prosody from three aspects: lip, face, and scene. Specifically, we align lip movement to the speech duration, and convey facial expression to speech energy and pitch via attention mechanism based on valence and arousal representations inspired by the psychology findings. Moreover, we design an emotion booster to capture the atmosphere from global video scenes. All these embeddings are used together to generate mel-spectrogram, which is then converted into speech waves by an existing vocoder. Extensive experimental results on the V2C and Chem benchmark datasets demonstrate the favourable performance of the proposed method. The code and trained models will be made available at https://github.com/GalaxyCong/HPMDubbing

VQA Natural Language Explanation (VQA-NLE) task aims to explain the decision-making process of VQA models in natural language. Unlike traditional attention or gradient analysis, free-text rationales can be easier to understand and gain users' trust. Existing methods mostly use post-hoc or selfrationalization models to obtain a plausible explanation. However, these frameworks are bottle-necked by the following challenges: 1) the reasoning process cannot be faithfully responded to and suffer from the problem of logical inconsistency. 2) Human-annotated explanations are expensive and time-consuming to collect. In this paper, we propose a new Semi-Supervised VQA-NLE via Self-Critical Learning (S3C), which evaluates the candidate explanations by answering rewards to improve the logical consistency between answers and rationales. With a semi-supervised learning framework, the S3C can benefit from a tremendous amount of samples without human-annotated explanations. A large number of automatic measures and human evaluations all show the effectiveness of our method. Meanwhile, the framework achieves a new state-of-the-art performance on the two VQA-NLE datasets.

Cristian Rodriguez-Opazo, Edison Marrese-Taylor, Basura Fernando, Hiroya Takamura, Qi Wu. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame. Existing methods treat the temporal contexts obtained from different objects indiscriminately and ignore their different identities. While intuitively, aggregating local views of the same object in different frames may facilitate a better understanding of the object. Thus, in this paper, we aim to enable the model to focus on the identity-consistent temporal contexts of each object to obtain more comprehensive object representations and handle the rapid object appearance variations such as occlusion, motion blur, etc. However, realizing this goal on top of existing VID models faces low-efficiency problems due to their redundant region proposals and nonparallel frame-wise prediction manner. To aid this, we propose ClipVID, a VID model equipped with Identity-Consistent Aggregation (ICA) layers specifically designed for mining fine-grained and identity-consistent temporal contexts. It effectively reduces the redundancies through the set prediction strategy, making the ICA layers very efficient and further allowing us to design an architecture that makes parallel clip-wise predictions for the whole video clip. Extensive experimental results demonstrate the superiority of our method: a state-of-the-art (SOTA) performance (84.7% mAP) on the ImageNet VID dataset while running at a speed about 7× faster (39.3 fps) than previous SOTAs.

In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively capture the rich semantics inside the video using the image encoder of CLIP. To tackle this, state-of-the-art methods adopt complex cross-modal modeling techniques to fuse the text information into video frame representations, which, however, incurs severe efficiency issues in large-scale retrieval systems as the video representations must be recomputed online for every text query. In this paper, we discard this problematic cross-modal fusion process and aim to learn semantically-enhanced representations purely from the video, so that the video representations can be computed offline and reused for different texts. Concretely, we first introduce a spatial-temporal "Prompt Cube" into the CLIP image encoder and iteratively switch it within the encoder layers to efficiently incorporate the global video semantics into frame representations. We then propose to apply an auxiliary video captioning objective to train the frame representations, which facilitates the learning of detailed video semantics by providing fine-grained guidance in the semantic space. With a naive temporal fusion strategy (i.e., mean-pooling) on the enhanced frame representations, we obtain state-of-the-art performances on three benchmark datasets, i.e., MSR-VTT, MSVD, and LSMDC.

Recently emerged Vision-and-Language Navigation (VLN) tasks have drawn significant attention in both computer vision and natural language processing communities. Existing VLN tasks are built for agents that navigate on the ground, either indoors or outdoors. However, many tasks require intelligent agents to carry out in the sky, such as UAV-based goods delivery, traffic/security patrol, and scenery tour, to name a few. Navigating in the sky is more complicated than on the ground because agents need to consider the flying height and more complex spatial relationship reasoning. To fill this gap and facilitate research in this field, we propose a new task named AerialVLN, which is UAV-based and towards outdoor environments. We develop a 3D simulator rendered by near-realistic pictures of 25 city-level scenarios. Our simulator supports continuous navigation, environment extension and configuration. We also proposed an extended baseline model based on the widely-used cross-modal-alignment (CMA) navigation methods. We find that there is still a significant gap between the baseline model and human performance, which suggests AerialVLN is a new challenging task. Dataset and code is available at https://github.com/AirVLN/AirVLN.

Many Vision-and-Language Navigation (VLN) tasks have been proposed in recent years, from room-based to object-based and indoor to outdoor. The REVERIE (Remote Embodied Referring Expression) is interesting since it only provides high-level instructions to the agent, which are closer to human commands in practice. Nevertheless, this poses more challenges than other VLN tasks since it requires agents to infer a navigation plan only based on a short instruction. Large Language Models (LLMs) show great potential in robot action planning by providing proper prompts. Still, this strategy has not been explored under the REVERIE settings. There are several new challenges. For example, the LLM should be environment-aware so that the navigation plan can be adjusted based on the current visual observation. Moreover, the LLM planned actions should be adaptable to the much larger and more complex REVERIE environment. This paper proposes a March-in-Chat (MiC) model that can talk to the LLM on the fly and plan dynamically based on a newly proposed Room-and-Object Aware Scene Perceiver (ROASP). Our MiC model outperforms the previous state-of-the-art by large margins by SPL and RGSPL metrics on the REVERIE benchmark. The source code is available at https://github.com/YanyuanQiao/MiC

The performance of the Vision-and-Language Navigation (VLN) tasks has witnessed rapid progress recently thanks to the use of large pre-trained vision-and-language models. However, full fine-tuning the pre-trained model for every downstream VLN task is becoming costly due to the considerable model size. Recent research hotspot of Parameter-Efficient Transfer Learning (PETL) shows great potential in efficiently tuning large pre-trained models for the common CV and NLP tasks, which exploits the most of the representation knowledge implied in the pre-trained model while only tunes a minimal set of parameters. However, simply utilizing existing PETL methods for the more challenging VLN tasks may bring non-trivial degeneration to the performance. Therefore, we present the first study to explore PETL methods for VLN tasks and propose a VLN-specific PETL method named VLN-PETL. Specifically, we design two PETL modules: Historical Interaction Booster (HIB) and Cross-modal Interaction Booster (CIB). Then we combine these two modules with several existing PETL methods as the integrated VLN-PETL. Extensive experimental results on four mainstream VLN tasks (R2R, REVERIE, NDH, RxR) demonstrate the effectiveness of our proposed VLN-PETL, where VLN-PETL achieves comparable or even better performance to full fine-tuning and outperforms other PETL methods with promising margins. The source code is available at https://github.com/YanyuanQiao/VLN-PETL

We present ShapeScaffolder, a structure-based neural network for generating colored 3D shapes based on text input. The approach, similar to providing scaffolds as internal structural supports and adding more details to them, aims to capture finer text-shape connections and improve the quality of generated shapes. Traditional text-to-shape methods often generate 3D shapes as a whole. However, humans tend to understand both shape and text as being structure-based. For example, a table is interpreted as being composed of legs, a seat, and a back; similarly, texts possess inherent linguistic structures that can be analyzed as dependency graphs, depicting the relationships between entities within the text. We believe structure-aware shape generation can bring finer text-shape connections and improve shape generation quality. However, the lack of explicit shape structure and the high freedom of text structure make cross-modality learning challenging. To address these challenges, we first build the structured shape implicit fields in an unsupervised manner. We then propose the part-level attention mechanism between shape parts and textual graph nodes to align the two modalities at the structural level. Finally, we employ a shape refiner to add further detail to the predicted structure, yielding the final results. Extensive experimentation demonstrates that our approaches outperform state-of-the-art methods in terms of both shape fidelity and shape-text matching. Our methods also allow for part-level manipulation and improved part-level completeness.

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents. To tackle the common data scarcity issue in existing vision-and-language navigation datasets, we propose an effective paradigm for generating large-scale data for learning, which applies 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction-trajectory pairs using fully-accessible resources on the web. Importantly, we investigate the influence of each component in this paradigm on the agent’s performance and study how to adequately apply the augmented data to pre-train and fine-tune an agent. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning. The long-lasting generalization gap between navigating in seen and unseen environments is also reduced to less than 1% (versus 8% in the previous best method). Moreover, our paradigm also facilitates different models to achieve new state-of-the-art navigation results on CVDN, REVERIE, and R2R in continuous environments.

Vision-and-Language Navigation (VLN) aims to navigate to the target location by following a given instruction. Unlike existing methods focused on predicting a more accurate action at each step in navigation, in this paper, we make the first attempt to tackle a long-ignored problem in VLN: narrowing the gap between Success Rate (SR) and Oracle Success Rate (OSR). We observe a consistently large gap (up to 9%) on four state-of-the-art VLN methods across two benchmark datasets: R2R and REVERIE. The high OSR indicates the robot agent passes the target location, while the low SR suggests the agent actually fails to stop at the target location at last. Instead of predicting actions directly, we propose to mine the target location from a trajectory given by off-the-shelf VLN models. Specially, we design a multi-module transformer-based model for learning compact discriminative trajectory viewpoint representation, which is used to predict the confidence of being a target location as described in the instruction. The proposed method is evaluated on three widely-adopted datasets: R2R, REVERIE and NDH, and shows promising results, demonstrating the potential for more future research.

The capacity to reason logically is a hallmark of human cognition. Humans excel at integrating multimodal information for locigal reasoning, as exemplified by the Visual Question Answering (VQA) task, which is a challenging multimodal task. VQA tasks and large vision-and-language models aim to tackle reasoning problems, but the accuracy, consistency and fabrication of the generated answers is hard to evaluate in the absence of a VQA dataset that can offer formal, comprehensive and systematic complex logical reasoning questions. To address this gap, we present LoRA, a novel Logical Reasoning Augmented VQA dataset that requires formal and complex description logic reasoning based on a food-and-kitchen knowledge base. Our main objective in creating LoRA is to enhance the complex and formal logical reasoning capabilities of VQA models, which are not adequately measured by existing VQA datasets. We devise strong and flexible programs to automatically generate 200,000 diverse description logic reasoning questions based on the SROIQ Description Logic, along with realistic kitchen scenes and ground truth answers. We fine-tune the latest transformer VQA models and evaluate the zero-shot performance of the state-of-the-art large vision-and-language models on LoRA. The results reveal that LoRA presents a unique challenge in logical reasoning, setting a systematic and comprehensive evaluation standard.

Recent works attempt to employ pre-training in Vision-and-Language Navigation (VLN). However, these methods neglect the importance of historical contexts or ignore predicting future actions during pre-training, limiting the learning of visual-textual correspondence and the capability of decision-making. To address these problems, we present a history-enhanced and order-aware pre-training with the complementing fine-tuning paradigm (HOP+) for VLN. Specifically, besides the common Masked Language Modeling (MLM) and Trajectory-Instruction Matching (TIM) tasks, we design three novel VLN-specific proxy tasks: Action Prediction with History (APH) task, Trajectory Order Modeling (TOM) task and Group Order Modeling (GOM) task. APH task takes into account the visual perception trajectory to enhance the learning of historical knowledge as well as action prediction. The two temporal visual-textual alignment tasks, TOM and GOM further improve the agent's ability to order reasoning. Moreover, we design a memory network to address the representation inconsistency of history context between the pre-training and the fine-tuning stages. The memory network effectively selects and summarizes historical information for action prediction during fine-tuning, without costing huge extra computation consumption for downstream VLN tasks. HOP+ achieves new state-of-the-art performance on four downstream VLN tasks (R2R, REVERIE, RxR, and NDH), which demonstrates the effectiveness of our proposed method.

The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding. By embedding information into a noise-tolerant signal, such as audio, video, or images, digital watermarking and steganography techniques can be used to protect sensitive intellectual property (IP) and enable confidential communication, ensuring that the information embedded is only accessible to authorized parties. This survey provides an overview of recent developments in deep learning techniques deployed for data hiding, categorized systematically according to model architectures and noise injection methods. In addition, potential future research directions that unite digital watermarking and steganography on software engineering to enhance security and mitigate risks are suggested and deliberated. This contribution furthers the creation of a more trustworthy digital world and advances responsible artificial intelligence (AI).

Many real-world video-text tasks involve different levels of granularity to represent local and global information with distinct semantics, such as frames and words, clips and sentences, or videos and paragraphs. Most existing multimodal representation learning methods suffer from limitations: (i) Adopting expert systems or manual design to extract more fine-grained local information (such as objects and actions in a video frame) for supervision may lead to information asymmetry since there may no corresponding information among modalities; (ii) Neglecting the hierarchical nature of the data to aggregate different levels of information from different modalities will cause insufficient representations. To alleviate the above issues, in this paper, we propose a Multi-Granularity Aggregation Transformer (MGAT) for joint video-audio-text representation learning. Specifically, for intra-modality, we first design a multi-granularity transformer module to relieve information asymmetry by making full use of local and global information within a single modality from different perspectives. Then, for inter-modality, we develop an attention-guided aggregation module to fuse audio and video information hierarchically. Last, we align the aggregated information with text information at different hierarchical levels via intra- and inter-modality consistency loss and contrastive loss. With the help of more granularity of information, we are able to obtain a well-performed representation model for a variety of tasks, e.g., video-paragraph retrieval and video captioning. Extensive experiments on two challenging benchmarks, i.e., ActivityNet-captions and Youcook2, demonstrate the superiority of our proposed method.

Text-based Visual Question Answering (TextVQA) aims to produce correct answers for given questions about the images with multiple scene texts. In most cases, the texts naturally attach to the surface of the objects. Therefore, spatial reasoning between texts and objects is crucial in TextVQA. However, existing approaches are constrained within 2D spatial information learned from the input images and rely on transformer-based architectures to reason implicitly during the fusion process. Under this setting, these 2D spatial reasoning approaches cannot distinguish the fine-grained spatial relations between visual objects and scene texts on the same image plane, thereby impairing the interpretability and performance of TextVQA models. In this paper, we introduce 3D geometric information into the spatial reasoning process to capture the contextual knowledge of key objects step-by-step. Specifically, (i) we propose a relation prediction module for accurately locating the region of interest of critical objects; (ii) we design a depth-aware attention calibration module for calibrating the OCR tokens' attention according to critical objects. Extensive experiments show that our method achieves state-of-the-art performance on TextVQA and ST-VQA datasets. More encouragingly, our model surpasses others by clear margins of 5.7% and 12.1% on questions that involve spatial reasoning in TextVQA and ST-VQA valid split. Besides, we also verify the generalizability of our model on the text-based image captioning task.

Referring Expression Comprehension (REC) is an important task in the vision-and-language community, since it is an essential step for many cross-modal tasks such as VQA, image retrieval and image caption. To obtain a better trade-off between speed and accuracy, existing researches usually follow a one-stage paradigm, where this task can be considered as a language-conditioned object detection task. Meanwhile, previous one-stage REC frameworks provide many different research perspectives, such as the strategies of fusion, the stage of fusion and the design of detection head. Surprisingly, these works mostly ignore the value of integrating multi-level features and even only apply single-scale features to locate the target. In this paper, we focus on rethinking and improving feature pyramids for one-stage REC. By experimental validations, we first prove that although multi-scale fusion is an effective approach for improving performance, the mature neck structures from object detection (e.g., FPN, BFN and HRFPN) have a limited impact on this task. Further, we visualize the outputs of FPN and find the underlying reason is that these coarse-grained FPN fusion strategies suffer from semantic ambiguity problem. Based on the above insights, we propose a new Language-Guided FPN (LG-FPN) method, which can dynamically allocate and select the fine-grained information by stacking language-gate and union-gate. A large number of contrastive and ablative experiments show that our LG-FPN is an effective and reliable module that can adapt to different visual backbones, fusion strategies and detection heads. Finally, our method achieves state-of-the-art performance on four referring expression datasets.

Referring Expression Comprehension (REC) and Generation (REG) have become one of the most important tasks in visual reasoning, since it is an essential step for many vision-and-language tasks such as visual question answering or visual dialogue. However, it has not been widely used in many downstream tasks, mainly for the following reasons: 1) mainstream two-stage methods rely on additional annotations or off-the-shelf detectors to generate proposals. It would heavily degrade the generalization ability of models and lead to inevitable error accumulation. 2) Although one-stage strategies for REC have been proposed, these methods have to depend on lots of hyper-parameters (such as anchors) to generate bounding box. In this paper, we present a proposal-free one-stage (PFOS) framework that can directly regress the region-of-interest from the image or generate unambiguous descriptions in an end-to-end manner. Instead of using the dominant two-stage fashion, we take the dense-grid of images as input for a cross-attention transformer that learns multi-modal correspondences. The final bounding box or sentence is directly predicted from the image without the anchor selection or the computation of visual difference. Furthermore, we expand the traditional two-stage listener-speaker framework to jointly train by a one-stage learning paradigm. Our model achieves state-of-the-art performance on both accuracy and speed for comprehension and competitive results for generation.

Reasoning is a dynamic process. In cognitive theories, the dynamics of reasoning refers to reasoning states over time after successive state transitions. Modeling the cognitive dynamics is of utmost importance to simulate human reasoning capability. In this paper, we propose to learn the reasoning dynamics of visual relational reasoning by casting it as a path routing task. We present a reinforced path routing method that represents an input image via a structured visual graph and introduces a reinforcement learning based model to explore paths (sequences of nodes) over the graph based on an input sentence to infer reasoning results. By exploring such paths, the proposed method represents reasoning states clearly and characterizes state transitions explicitly to fully model the reasoning dynamics for accurate and transparent visual relational reasoning. Extensive experiments on referring expression comprehension and visual question answering demonstrate the effectiveness of our method.

A long-term goal of AI research is to build intelligent agents that can communicate with humans in natural language, perceive the environment, and perform real-world tasks.Visionand-Language Navigation (VLN) is a fundamental and interdisciplinary research topic towards this goal, and receives increasing attention from natural language processing, computer vision, robotics, and machine learning communities.In this paper, we review contemporary studies in the emerging field of VLN, covering tasks, evaluation metrics, methods, etc.Through structured analysis of current progress and challenges, we highlight the limitations of current VLN and opportunities for future work.This paper serves as a thorough reference for the VLN research community.1

Existing Voice Cloning (VC) tasks aim to convert a para-graph text to a speech with desired voice specified by a ref-erence audio. This has significantly boosted the development of artificial speech applications. However, there also exist many scenarios that cannot be well reflected by these VC tasks, such as movie dubbing, which requires the speech to be with emotions consistent with the movie plots. To fill this gap, in this work we propose a new task named Vi-sual Voice Cloning (V2C), which seeks to convert a para-graph of text to a speech with both desired voice speci-fied by a reference audio and desired emotion specified by a reference video. To facilitate research in this field, we construct a dataset, V2C-Animation, and propose a strong baseline based on existing state-of-the-art (SoTA) VC techniques. Our dataset contains 10,217 animated movie clips covering a large variety of genres (e.g., Comedy, Fantasy) and emotions (e.g., happy, sad). We further design a set of evaluation metrics, named MCD-DTW-SL, which help eval-uate the similarity between ground-truth speeches and the synthesised ones. Extensive experimental results show that even SoTA VC methods cannot generate satisfying speeches for our V2C task. We hope the proposed new task together with the constructed dataset and evaluation metric will fa-cilitate the research in the field of voice cloning and broader vision-and-language community. Source code and dataset will be released in https://github.com/chenqi008/V2C.

Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding. One limitation of existing solutions is that they capture relevant knowledge from text-only knowledge bases, which merely contain facts expressed by first-order predicates or language descriptions while lacking complex but indispensable multimodal knowledge for visual understanding. How to construct vision-relevant and explainable multimodal knowledge for the VQA scenario has been less studied. In this paper, we propose MuKEA to represent multimodal knowledge by an explicit triplet to correlate visual objects and fact answers with implicit relations. To bridge the heterogeneous gap, we propose three objective losses to learn the triplet representations from complementary views: embedding structure, topological relation and semantic space. By adopting a pretraining and fine-tuning learning strategy, both basic and domain-specific multimodal knowledge are progressively accumulated for answer prediction. We outperform the state-of-the-art by 3.35% and 6.08% respectively on two challenging knowledge-required datasets: OK-VQA and KRVQA. Experimental results prove the complementary benefits of the multimodal knowledge with existing knowledge bases and the advantages of our end-to-end framework over the existing pipeline methods. The code is available at https://github.com/AndersonStra/MuKEA.

Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. Although learning to navigate in continuous spaces is closer to the real-world, training such an agent is significantly more difficult than training an agent in discrete spaces. However, recent advances in discrete VLN are challenging to translate to continuous VLN due to the domain gap. The fundamental difference between the two setups is that discrete navigation assumes prior knowledge of the connectivity graph of the environment, so that the agent can effectively transfer the problem of navigation with low-level controls to jumping from node to node with high-level actions by grounding to an image of a navigable direction. To bridge the discrete-to-continuous gap, we propose a predictor to generate a set of candidate waypoints during navigation, so that agents designed with high-level actions can be transferred to and trained in continuous environments. We refine the connectivity graph of Matterport3D to fit the continuous Habitat-Matterport3D, and train the waypoints predictor with the refined graphs to produce accessible waypoints at each time step. Moreover, we demonstrate that the predicted waypoints can be augmented during training to diversify the views and paths, and therefore enhance agent's generalization ability. Through extensive experiments we show that agents navigating in continuous environments with predicted waypoints perform significantly better than agents using low-level actions, which reduces the absolute discrete-to-continuous gap by 11.76% Success Weighted by Path Length (SPL) for the Cross-Modal Matching Agent and 18.24% SPL for the VLN$$BERT. Our agents, trained with a simple imitation learning objective, outperform previous methods by a large margin, achieving new state-of-the-art results on the testing environments of the R2R-CE and the RxR-CE datasets.

A compositional question refers to a question that contains multiple visual concepts (e.g., objects, attributes, and relationships) and requires compositional reasoning to answer. Existing VQA models can answer a compositional question well, but cannot work well in terms of reasoning consistency in answering the compositional question and its sub-questions. For example, a compositional question for an image is: “Are there any elephants to the right of the white bird?” and one of its sub-questions is “Is any bird visible in the scene?”. The models may answer “yes” to the compositional question, but “no” to the sub-question. This paper presents a dialog-like reasoning method for maintaining reasoning consistency in answering a compositional question and its sub-questions. Our method integrates the reasoning processes for the sub-questions into the reasoning process for the compositional question like a dialog task, and uses a consistency constraint to penalize inconsistent answer predictions. In order to enable quantitative evaluation of reasoning consistency, we construct a GQA-Sub dataset based on the well-organized GQA dataset. Experimental results on the GQA dataset and the GQA-Sub dataset demonstrate the effectiveness of our method.

Pretraining has been adopted in a few of recent works for Vision-and-Language Navigation (VLN). However, pre-vious pre-training methods for VLN either lack the ability to predict future actions or ignore the trajectory contexts, which are essential for a greedy navigation process. In this work, to promote the learning of spatio-temporal visual-textual correspondence as well as the agent's capability of decision making, we propose a novel history-and-order aware pre-training paradigm (HOP) with VLN-specific objectives that exploit the past observations and support future action prediction. Specifically, in addition to the commonly used Masked Language Modeling (MLM) and Trajectory-Instruction Matching (TIM), we design two proxy tasks to model temporal order information: Trajectory Order Modeling (TOM) and Group Order Modeling (GOM). Moreover, our navigation action prediction is also enhanced by intro-ducing the task of Action Prediction with History (APH), which takes into account the history visual perceptions. Extensive experimental results on four downstream VLN tasks (R2R, REVERIE, NDH, RxR) demonstrate the effectiveness of our proposed method compared against several state-of-the-art agents.

Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Wang, Qi Wu, Miguel Eckstein, William Yang Wang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Over the years, state-of-the-art (SoTA) image captioning methods have achieved promising results on some evaluation metrics (e.g., CIDEr). However, recent findings show that the captions generated by these methods tend to be biased toward the "average" caption that only captures the most general mode (a.k.a, language pattern) in the training corpus, i.e., the so-called mode collapse problem. Affected by it, the generated captions are limited in diversity and usually less informative than natural image descriptions made by humans. In this paper, we seek to avoid this problem by proposing a Discrete Mode Learning (DML) paradigm for image captioning. Our innovative idea is to explore the rich modes in the training caption corpus to learn a set of "mode embeddings", and further use them to control the mode of the generated captions for existing image captioning models. Specifically, the proposed DML optimizes a dual architecture that consists of an image-conditioned discrete variational autoencoder (CdVAE) branch and a mode-conditioned image captioning (MIC) branch. The CdVAE branch maps each image caption to one of the mode embeddings stored in a learned codebook, and is trained with a pure non-autoregressive generation objective to make the modes distinct and representative. The MIC branch can be simply modified from an existing image captioning model, where the mode embedding is added to the original word embeddings as the control signal. In the experiments, we apply the proposed DML to two widely used image captioning models, Transformer and AoANet. The results show that the learned mode embedding successfully facilitates these models to generate high-quality image captions with different modes, further leading to better performance for both diversity and quality on the MS COCO dataset.

In this work, we present a method to improve the efficiency and robustness of the previous model-free Reinforcement Learning (RL) algorithms for the task of object-goal visual navigation. Despite achieving state-of-the-art results, one of the major drawbacks of those approaches is the lack of a forward model that informs the agent about the potential consequences of its actions, i.e., being model-free. In this work, we augment the model-free RL with such a forward model that can predict a representation of a future state, from the beginning of a navigation episode, if the episode were to be successful. Furthermore, in order for efficient training, we develop an algorithm to integrate a replay buffer into the model-free RL that alternates between training the policy and the forward model. We call our agent ForeSI; ForeSI is trained to imagine a future latent state that leads to success. By explicitly imagining such a state, during the navigation, our agent is able to take better actions leading to two main advantages: first, in the absence of an object detector, ForeSI presents a more robust policy, i.e., it leads to about 5% absolute improvement on the Success Rate (SR); second, when combined with an off-the-shelf object detector to help better distinguish the target object, our method leads to about 3% absolute improvement on the SR and about 2% absolute improvement on Success weighted by inverse Path Length (SPL), i.e., presents higher efficiency.

Visual grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. Generally, it requires the machine to first understand the query, identify the key concepts in the image, and then locate the target object by specifying its bounding box. However, in many real-world visual grounding applications, we have to face with ambiguous queries and images with complicated scene structures. Identifying the target based on highly redundant and correlated information can be very challenging, and often leading to unsatisfactory performance. To tackle this, in this paper, we exploit an attention module for each kind of information to reduce internal redundancies. We then propose an accumulated attention (A-ATT) mechanism to reason among all the attention modules jointly. In this way, the relation among different kinds of information can be explicitly captured. Moreover, to improve the performance and robustness of our VG models, we additionally introduce some noises into the training procedure to bridge the distribution gap between the human-labeled training data and the real-world poor quality data. With this "noised" training strategy, we can further learn a bounding box regressor, which can be used to refine the bounding box of the target object. We evaluate the proposed methods on four popular datasets (namely ReferCOCO, ReferCOCO+, ReferCOCOg, and GuessWhat?!). The experimental results show that our methods significantly outperform all previous works on every dataset in terms of accuracy.

Text based Visual Question Answering (TextVQA) is a recently raised challenge requiring models to read text in images and answer natural language questions by jointly reasoning over the question, textual information and visual content. Introduction of this new modality - Optical Character Recognition (OCR) tokens ushers in demanding reasoning requirements. Most of the state-of-the-art (SoTA) VQA methods fail when answer these questions because of three reasons: (1) poor text reading ability; (2) lack of textual-visual reasoning capacity; and (3) choosing discriminative answering mechanism over generative couterpart (although this has been further addressed by M4C). In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above. SMA first uses a structural graph representation to encode the object-object, object-text and text-text relationships appearing in the image, and then designs a multimodal graph attention network to reason over it. Finally, the outputs from the above modules are processed by a global-local attentional answering module to produce an answer splicing together tokens from both OCR and general vocabulary iteratively by following M4C. Our proposed model outperforms the SoTA models on TextVQA dataset and two tasks of ST-VQA dataset among all models except pre-training based TAP. Demonstrating strong reasoning ability, it also won first place in TextVQA Challenge 2020. We extensively test different OCR methods on several reasoning models and investigate the impact of gradually increased OCR performance on TextVQA benchmark. With better OCR results, different models share dramatic improvement over the VQA accuracy, but our model benefits most blessed by strong textual-visual reasoning ability. To grant our method an upper bound and make a fair testing base available for further works, we also provide human-annotated ground-truth OCR annotations for the TextVQA dataset, which were not given in the original release. The code and ground-truth OCR annotations for the TextVQA dataset are available at https://github.com/ChenyuGAO-CS/SMA.

Negotiation, as an essential and complicated aspect of online shopping, is still challenging for an intelligent agent. To that end, we propose thePrice Negotiator, a modular deep neural network that addresses the unsolved problems in recent studies by (1) considering images of the items as a crucial, though neglected, source of information in a negotiation, (2) heuristically finding the most similar items from an external online source to predict the potential value and an acceptable agreement price, (3) predicting a general price-based “action” at each turn which is fed into the language generator to output the supporting natural language, and (4) adjusting the prices based on the predicted actions. Empirically, we show that our model, that is trained in both supervised and reinforcement learning setting, significantly improves negotiation on the CraigslistBargain dataset, in terms of the agreement price, price consistency, and dialogue quality.

Performances of deep neural networks are prone to be degraded by label noise due to their powerful capability in fitting training data. Deeming low-loss instances as clean data is one of the most promising strategies in tackling label noise and has been widely adopted by state-of-the-art methods. However, prior works tend to drop high-loss instances directly, neglecting their valuable information. To address this issue, we propose an end-to-end framework named Co-LDL, which incorporates the low-loss sample selection strategy with label distribution learning. Specifically, we simultaneously train two deep neural networks and let them communicate useful knowledge by selecting low-loss and high-loss samples for each other. Low-loss samples are leveraged conventionally for updating network parameters. On the contrary, high-loss samples are trained in a label distribution learning manner to update network parameters and label distributions concurrently. Moreover, we propose a self-supervised module to further boost the model performance by enhancing the learned representations. Comprehensive experiments on both synthetic and real-world noisy datasets are provided to demonstrate the superiority of our Co-LDL method over state-of-the-art approaches in learning with noisy labels. The source code and models have been made available athttps://github.com/NUST-Machine-Intelligence-Laboratory/CoLDL.

Manually labeling fine-grained datasetsis laborious and typically requires domain-specific expert knowledge. Conversely, a vast amount of web data is relatively easy to obtain with nearly no human effort. Therefore, learning from noisy web data for fine-grained tasks is attracting increasing attention in recent years. However, the presence of noise in web images is a huge obstacle for training robust fine-grained recognition models. To this end, we propose a novel approach to identify noisy images as well as specifically distinguish in- and out-of-distribution samples. It can purify the noisy web training set by discarding out-of-distribution noise and relabeling in-distribution noisy samples. Then we can train the model on the purified dataset to alleviate the harmful effects of noise and make the most of web images to achieve better performance. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is far superior to current state-of-the-art web-supervised methods. The data and source code of this work have been made publicly available at:https://github.com/NUST-Machine-Intelligence-Laboratory/Dataset-Purification.

Reading and writing research papers is one of the most privileged abilities that a qualified researcher should master. However, it is difficult for new researchers (e.g., students) to fully grasp this ability. It would be fascinating if we could train an intelligent agent to help people read and summarize papers, and perhaps even discover and exploit the potential knowledge clues to write novel papers. Although there have been existing works focusing on summarizing (i.e., reading) the knowledge in a given text or generating (i.e., writing) a text based on the given knowledge, the ability of simultaneously reading and writing is still under development. Typically, this requires an agent to fully understand the knowledge from the given text materials and generate correct and fluent novel paragraphs, which is very challenging in practice. In this paper, we propose a Deep ReAder-Writer (DRAW) network, which consists of a Reader that can extract knowledge graphs (KGs) from input paragraphs and discover potential knowledge, a graph-to-text Writer that generates a novel paragraph, and a Reviewer that reviews the generated paragraph from three different aspects. Extensive experiments show that our DRAW network outperforms considered baselines and several state-of-the-art methods on AGENDA and M-AGENDA datasets. Our code and supplementary are released at https://github.com/menggehe/DRAW.

When describing an image, reading text in the visual scene is crucial to understand the key information. Recent work explores the TextCaps task, i.e. image captioning with reading Optical Character Recognition (OCR) tokens, which requires models to read text and cover them in generated captions. Existing approaches fail to generate accurate descriptions because of their (1) poor reading ability; (2) inability to choose the crucial words among all extracted OCR tokens; (3) repetition of words in predicted captions. To this end, we propose a Confidence-aware Non-repetitive Multimodal Transformers (CNMT) to tackle the above challenges. Our CNMT consists of a reading, a reasoning and a generation modules, in which Reading Module employs better OCR systems to enhance text reading ability and a confidence embedding to select the most noteworthy tokens. To address the issue of word redundancy in captions, our Generation Module includes a repetition mask to avoid predicting repeated word in captions. Our model outperforms state-of-the-art models on TextCaps dataset, improving from 81.0 to 93.0 in CIDEr. Our source code is publicly available.

Texts appearing in daily scenes that can be recognized by OCR (Optical Character Recognition) tools contain significant information, such as street name, product brand and prices. Two tasks -- text-based visual question answering and text-based image captioning, with a text extension from existing vision-language applications, are catching on rapidly. To address these problems, many sophisticated multi-modality encoding frameworks (such as heterogeneous graph structure) are being used. In this paper, we argue that a simple attention mechanism can do the same or even better job without any bells and whistles. Under this mechanism, we simply split OCR token features into separate visual- and linguistic-attention branches, and send them to a popular Transformer decoder to generate answers or captions. Surprisingly, we find this simple baseline model is rather strong -- it consistently outperforms state-of-the-art (SOTA) models on two popular benchmarks, TextVQA and all three tasks of ST-VQA, although these SOTA models use far more complex encoding mechanisms. Transferring it to text-based image captioning, we also surpass the TextCaps Challenge 2020 winner. We wish this work to set the new baseline for these two OCR text related applications and to inspire new thinking of multi-modality encoder design. Code is available at https://github.com/ZephyrZhuQi/ssbaseline

The dense video captioning task aims to detect and describe a sequence of events in a video for detailed and coherent storytelling. Previous works mainly adopt a "detect-then-describe" framework, which firstly detects event proposals in the video and then generates descriptions for the detected events. However, the definitions of events are diverse which could be as simple as a single action or as complex as a set of events, depending on different semantic con-texts. Therefore, directly detecting events based on video information is ill-defined and hurts the coherency and accuracy of generated dense captions. In this work, we reverse the predominant "detect-then-describe" fashion, proposing a top-down way to first generate paragraphs from a global view and then ground each event description to a video segment for detailed refinement. It is formulated as a Sketch, Ground, and Refine process (SGR). The sketch stage first generates a coarse-grained multi-sentence paragraph to describe the whole video, where each sentence is treated as an event and gets localised in the grounding stage. In the re-fining stage, we improve captioning quality via refinement-enhanced training and dual-path cross attention on both coarse-grained event captions and aligned event segments. The updated event caption can further adjust its segment boundaries. Our SGR model outperforms state-of-the-art methods on ActivityNet Captioning benchmark under traditional and story-oriented dense caption evaluations. Code will be released at github.com/bearcatt/SGR.

The Remote Embodied Referring Expression (REVERIE) is a recently raised task that requires an agent to navigate to and localise a referred remote object according to a high-level language instruction. Different from related VLN tasks, the key to REVERIE is to conduct goal-oriented exploration instead of strict instruction-following, due to the lack of step-by-step navigation guidance. In this paper, we propose a novel Cross-modality Knowledge Reasoning (CKR) model to address the unique challenges of this task. The CKR, based on a transformer-architecture, learns to generate scene memory tokens and utilise these informative history clues for exploration. Particularly, a Room-and-Object Aware Attention (ROAA) mechanism is devised to explicitly perceive the room- and object-type information from both linguistic and visual observations. Moreover, through incorporating commonsense knowledge, we propose a Knowledge-enabled Entity Relationship Reasoning (KERR) module to learn the internal-external correlations among room- and object-entities for agent to make proper action at each viewpoint. Evaluation on REVERIE benchmark demonstrates the superiority of the CKR model, which significantly boosts SPL and REVERIE-success rate by 64.67% and 46.05%, respectively. Code is available at: https://github.com/alloldman/CKR.

Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language (V&L) BERT. However, its application for the task of vision-and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state information for the agent. Through extensive experiments on R2R and REVERIE we demonstrate that our model can replace more complex encoder-decoder models to achieve state-of-the-art results. Moreover, our approach can be generalised to other transformer-based architectures, supports pre-training, and is capable of solving navigation and referring expression tasks simultaneously.

Text-based image captioning (TextCap) which aims to read and reason images with texts is crucial for a machine to understand a detailed and complex scene environment, considering that texts are omnipresent in daily life. This task, however, is very challenging because an image often contains complex texts and visual information that is hard to be described comprehensively. Existing methods attempt to extend the traditional image captioning methods to solve this task, which focus on describing the overall scene of images by one global caption. This is infeasible because the complex text and visual information cannot be described well within one caption. To resolve this difficulty, we seek to generate multiple captions that accurately describe different parts of an image in detail. To achieve this purpose, there are three key challenges: 1) it is hard to decide which parts of the texts of images to copy or paraphrase; 2) it is non-trivial to capture the complex relationship between diverse texts in an image; 3) how to generate multiple captions with diverse content is still an open problem. To conquer these, we propose a novel Anchor-Captioner method. Specifically, we first find the important tokens which are supposed to be paid more attention to and consider them as anchors. Then, for each chosen anchor, we group its rel-evant texts to construct the corresponding anchor-centred graph (ACG). Last, based on different ACGs, we conduct the multi-view caption generation to improve the content diversity of generated captions. Experimental results show that our method not only achieves SOTA performance but also generates diverse captions to describe images.

Semantic segmentation aims to classify every pixel of an input image. Considering the difficulty of acquiring dense labels, researchers have recently been resorting to weak labels to alleviate the annotation burden of segmentation. However, existing works mainly concentrate on expanding the seed of pseudo labels within the image’s salient region. In this work, we propose a non-salient region object mining approach for weakly supervised semantic segmentation. We introduce a graph-based global reasoning unit to strengthen the classification network’s ability to capture global relations among disjoint and distant regions. This helps the network activate the object features outside the salient area. To further mine the non-salient region objects, we propose to exert the segmentation network’s self-correction ability. Specifically, a potential object mining module is proposed to reduce the false-negative rate in pseudo labels. Moreover, we propose a non-salient region masking module for complex images to generate masked pseudo labels. Our non-salient region masking module helps further discover the objects in the non-salient region. Extensive experiments on the PASCAL VOC dataset demonstrate state-of-the-art results compared to current methods. The source codes are available at https://github.com/NUST-Machine-Intelligence-Laboratory/nsrom.

Due to the memorization effect in Deep Neural Networks (DNNs), training with noisy labels usually results in inferior model performance. Existing state-of-the-art methods primarily adopt a sample selection strategy, which selects small-loss samples for subsequent training. However, prior literature tends to perform sample selection within each mini-batch, neglecting the imbalance of noise ratios in different mini-batches. Moreover, valuable knowledge within high-loss samples is wasted. To this end, we propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency). Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution. Furthermore, we propose a joint loss to advance the model generalization performance by introducing consistency regularization. Extensive experiments have validated the superiority of our approach over existing state-of-the-art methods. The source code and models have been made available at https://github.com/NUST-Machine-Intelligence-Laboratory/Jo-SRC.

Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas. Most existing methods take the words in the instructions and the discrete views of each panorama as the minimal unit of encoding. However, this requires a model to match different nouns (e.g., TV, table) against the same input view feature. In this work, we propose an object-informed sequential BERT to encode visual perceptions and linguistic instructions at the same fine-grained level, namely objects and words. Our sequential BERT also enables the visual-textual clues to be interpreted in light of the temporal context, which is crucial to multi-round VLN tasks. Additionally, we enable the model to identify the relative direction (e.g., left/right/front/back) of each navigable location and the room type (e.g., bedroom, kitchen) of its current and final navigation goal, as such information is widely mentioned in instructions implying the desired next and final locations. We thus enable the model to know-where the objects lie in the images, and to know-where they stand in the scene. Extensive experiments demonstrate the effectiveness compared against several state-of-the-art methods on three indoor VLN tasks: REVERIE, NDH, and R2R. Project repository: https://github.com/YuankaiQi/ORIST

Vision-and-Language (VL) pre-training has shown great potential on many related downstream tasks, such as Visual Question Answering (VQA), one of the most popular problems in the VL field. All of these pre-trained models (such as VisualBERT, ViLBERT, LXMERT and UNITER) are built with Transformer, which extends the classical attention mechanism to multiple layers and heads. To investigate why and how these models work on VQA so well, in this paper we explore the roles of individual heads and layers in Transformer models when handling 12 different types of questions. Specifically, we manually remove (chop) heads (or layers) from a pre-trained VisualBERT model at a time, and test it on different levels of questions to record its performance. As shown in the interesting echelon shape of the result matrices, experiments reveal different heads and layers are responsible for different question types, with higher-level layers activated by higher-level visual reasoning questions. Based on this observation, we design a dynamic chopping module that can automatically remove heads and layers of the VisualBERT at an instance level when dealing with different questions. Our dynamic chopping module can effectively reduce the parameters of the original model by 50%, while only damaging the accuracy by less than 1% on the VQA task.

Referring Expression Comprehension (REC) has become one of the most important tasks in visual reasoning, since it is an essential step for many vision-and-language tasks such as visual question answering. However, it has not been widely used in many downstream tasks because it suffers 1) two-stage methods exist heavy computation cost and inevitable error accumulation, and 2) one-stage methods have to depend on lots of hyper-parameters (such as anchors) to generate bounding box. In this paper, we present a proposal-free one-stage (PFOS) model that is able to regress the region-of-interest from the image, based on a textual query, in an end-to-end manner. Instead of using the dominant anchor proposal fashion, we directly take the dense-grid of image as input for a cross-attention transformer that learns grid-word correspondences. The final bounding box is predicted directly from the image without the time-consuming anchor selection process that previous methods suffer. Our model achieves the state-of-the-art performance on four referring expression datasets with higher efficiency, comparing to previous best one-stage and two-stage methods.

Scene graphs are semantic abstraction of images that encourage visual understanding and reasoning. However, the performance of Scene Graph Generation (SGG) is unsatisfactory when faced with biased data in real-world scenarios. Conventional debiasing research mainly studies from the view of balancing data distribution or learning unbiased models and representations, ignoring the correlations among the biased classes. In this work, we analyze this problem from a novel cognition perspective: automatically building a hierarchical cognitive structure from the biased predictions and navigating that hierarchy to locate the relationships, making the tail relationships receive more attention in a coarse-to-fine mode. To this end, we propose a novel debiasing Cognition Tree (CogTree) loss for unbiased SGG. We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model. The CogTree distinguishes remarkably different relationships at first and then focuses on a small portion of easily confused ones. Then, we propose a debiasing loss specially for this cognitive structure, which supports coarse-to-fine distinction for the correct relationships. The loss is model-agnostic and consistently boosting the performance of several state-of-the-art models. The code is available at: https://github.com/CYVincent/Scene-Graph-Transformer-CogTree.

Vision and Language Navigation (VLN) requires an agent to navigate to a target location by following natural language instructions. Most of existing works represent a navigation candidate by the feature of the corresponding single view where the candidate lies in. However, an instruction may mention landmarks out of the single view as references, which might lead to failures of textual-visual matching of existing methods. In this work, we propose a multi-module Neighbor-View Enhanced Model (NvEM) to adaptively incorporate visual contexts from neighbor views for better textual-visual matching. Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views. The subject module fuses neighbor views at a global level, and the reference module fuses neighbor objects at a local level. Subjects and references are adaptively determined via attention mechanisms. Our model also includes an action module to utilize the strong orientation guidance (e.g., "turn left'') in instructions. Each module predicts navigation action separately and their weighted sum is used for predicting the final action. Extensive experimental results demonstrate the effectiveness of the proposed method on the R2R and R4R benchmarks against several state-of-the-art navigators, and NvEM even beats some pre-training ones. Our code is available at https://github.com/MarSaKi/NvEM.

Despite recent significant progress on generative models, context-rich text-to-image synthesis depicting multiple complex objects is still non-trivial. The main challenges lie in the ambiguous semantic of a complex description and the intricate scene of an image with various objects, different positional relationship and diverse appearances. To address these challenges, we propose R-GAN, which can generate reasonable images according to the given text in a human-like way. Specifically, just like humans will first find and settle the essential elements to create a simple sketch, we first capture a monolithic-structural text representation by building a scene graph to find the essential semantic elements. Then, based on this representation, we design a bounding box generator to estimate the layout with position and size of target objects, and a following shape generator, which draws a fine-detailed shape for each object. Different from previous work only generating coarse shapes blindly, we introduce a coarse-to-fine shape generator based on a shape knowledge base. At last, to finish the final image synthesis, we propose a multi-modal geometry-aware spatially-adaptive generator conditioned on the monolithic-structural text representation and the geometry-aware map of the shapes. Extensive experiments on the real-world dataset MSCOCO show the superiority of our method in terms of both quantitative and qualitative metrics.

In Vision-and-Language Navigation (VLN) task, an agent is asked to navigate inside 3D indoor environments following given instructions. Cross-modal alignment is one of the most critical challenges in VLN because the predicted trajectory needs to match the given instruction accurately. In this paper, we address the cross-modal alignment challenge from the perspective of fine-grain. Firstly, to alleviate weak cross-modal alignment supervision from coarse-grained data, we introduce a human-annotated fine-grained VLN dataset, namely Landmark-RxR. Secondly, to further enhance local cross-modal alignment under fine-grained supervision, we investigate the focal-oriented rewards with soft and hard forms, by focusing on the critical points sampled from fine-grained Landmark-RxR. Moreover, to fully evaluate the navigation process, we also propose a re-initialization mechanism that makes metrics insensitive to difficult points, which can cause the agent to deviate from the correct trajectories. Experimental results show that our agent has superior navigation performance on Landmark-RxR, en-RxR and R2R. Our dataset and code are available at https://github.com/hekj/Landmark-RxR.

Visual question answering (VQA) is designed to examine the visual-textual reasoning ability of an intelligent agent. However, recent observations show that many VQA models may only capture the biases between questions and answers in a dataset rather than showing real reasoning abilities. For example, given a question, some VQA models tend to output the answer that occurs frequently in the dataset and ignore the images. To reduce this tendency, existing methods focus on weakening the language bias. Meanwhile, only a few works also consider vision bias implicitly. However, these methods introduce additional annotations or show unsatisfactory performance. Moreover, not all biases are harmful to the models. Some “biases” learnt from datasets represent natural rules of the world and can help limit the range of answers. Thus, how to filter and remove the true negative biases in language and vision modalities remain a major challenge. In this paper, we propose a method named D-VQA to alleviate the above challenges from the feature and sample perspectives. Specifically, from the feature perspective, we build a question-to-answer and vision-to-answer branch to capture the language and vision biases, respectively. Next, we apply two unimodal bias detection modules to explicitly recognise and remove the negative biases. From the sample perspective, we construct two types of negative samples to assist the training of the models, without introducing additional annotations. Extensive experiments on the VQA-CP v2 and VQA v2 datasets demonstrate the effectiveness of our D-VQA method.

We humans can impeccably search for a target object, given its name only, even in an unseen environment. We argue that this ability is largely due to three main reasons: the incorporation of prior knowledge (or experience), the adaptation of it to the new environment using the observed visual cues and most importantly optimistically searching without giving up early. This is currently missing in the state-of-the-art visual navigation methods based on Reinforcement Learning (RL). In this paper, we propose to use externally learned prior knowledge of the relative object locations and integrate it into our model by constructing a neural graph. In order to efficiently incorporate the graph without increasing the state-space complexity, we propose Graph-based Value Estimation (GVE) module. GVE provides a more accurate baseline for estimating the Advantage function in actor-critic RL algorithm. This results in reduced value estimation error and, consequently, convergence to a more optimal policy. Through empirical studies, we show that our agent, dubbed as the optimistic agent, has a more realistic estimate of the state value during a navigation episode which leads to a higher success rate. Our extensive ablation studies show the efficacy of our simple method which achieves the state-of-the-art results measured by the conventional visual navigation metrics, e.g. Success Rate (SR) and Success weighted by Path Length (SPL), in AI2THOR environment.

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise mainly from two aspects: first, the agent needs to attend to the meaningful paragraphs of the language instruction corresponding to the dynamically-varying visual environments; second, during the training process, the agent usually imitate the expert demonstrations, i.e., the shortest-path to the target location specified by associated language instructions. Due to the discrepancy of action selection between training and inference, the agent solely on the basis of imitation learning does not perform well. Existing VLN approaches address this issue by sampling the next action from its predicted probability distribution during the training process. This allows the agent to explore diverse routes from the environments, yielding higher success rates. Nevertheless, without being presented with the golden shortest navigation paths during the training process, the agent may arrive at the target location through an unexpected longer route. To overcome these challenges, we design a cross-modal grounding module, which is composed of two complementary attention mechanisms, to equip the agent with a better ability to track the correspondence between the textual and visual modalities. We then propose to recursively alternate the learning schemes of imitation and exploration to narrow the discrepancy between training and inference. We further exploit the advantages of both these two learning schemes via adversarial learning. Extensive experimental results on the Room-to-Room (R2R) benchmark dataset demonstrate that the proposed learning scheme is generalized and complementary to prior arts. Our method performs well against state-of-the-art approaches in terms of effectiveness and efficiency.

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue task involves multiple rounds of dialogues which cover a broad range of visual content that could be related to any objects, relationships or high-level semantics. Thus one of the key challenges in Visual Dialogue task is to learn a more comprehensive and semantic-rich image representation that can adaptively attend to the visual content referred by variant questions. In this paper, we first propose a novel scheme to depict an image from both visual and semantic views. Specifically, the visual view aims to capture the appearance-level information in an image, including objects and their visual relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Furthermore, on top of such dual-view image representations, we propose a Dual Encoding Visual Dialogue (DualVD) module, which is able to adaptively select question-relevant information from the visual and semantic views in a hierarchical mode. To demonstrate the effectiveness of DualVD, we propose two novel visual dialogue models by applying it to the Late Fusion framework and Memory Network framework. The proposed models achieve state-of-the-art results on three benchmark datasets. A critical advantage of the DualVD module lies in its interpretability. We can analyze which modality (visual or semantic) has more contribution in answering the current question by explicitly visualizing the gate values. It gives us insights in understanding of information selection mode in the Visual Dialogue task. The code is available at https://github.com/JXZe/Learning_DualVD.

Referring expression comprehension (REC) aims to localize a target object in an image described by a referring expression phrased in natural language. Different from the object detection task that queried object labels have been pre-defined, the REC problem only can observe the queries during the test. It is more challenging than a conventional computer vision problem. This task has attracted a lot of attention from both computer vision and natural language processing community, and several lines of work have been proposed, from CNN-RNN model, modular network to complex graph-based model. In this survey, we first examine the state-of-the-art by comparing modern approaches to the problem. We classify methods by their mechanism to encode the visual and textual modalities. In particular, we examine the common approach of joint embedding images and expressions to a common feature space. We also discuss modular architectures and graph-based models that interface with structured graph representation. In the second part of this survey, we review the datasets available for training and evaluating REC approaches. We then group results according to the datasets, backbone models, settings so that they can be fairly compared. Finally, we discuss promising future directions for this field, in particular the compositional referring expression comprehension that requires more reasoning steps to address.

Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects, relationships or semantics. The key challenge in Visual Dialogue task is thus to learn a more comprehensive and semantic-rich image representation which may have adaptive attentions on the image for variant questions. In this research, we propose a novel model to depict an image from both visual and semantic perspectives. Specifically, the visual view helps capture the appearance-level information, including objects and their relationships, while the semantic view enables the agent to understand high-level visual semantics from the whole image to the local regions. Futhermore, on top of such multi-view image features, we propose a feature selection framework which is able to adaptively capture question-relevant information hierarchically in fine-grained level. The proposed method achieved state-of-the-art results on benchmark Visual Dialogue datasets. More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values. It gives us insights in understanding of human cognition in Visual Dialogue.

Most existing Visual Question Answering (VQA) models overly rely on language priors between questions and answers. In this paper, we present a novel method of language attention-based VQA that learns decomposed linguistic representations of questions and utilizes the representations to infer answers for overcoming language priors. We introduce a modular language attention mechanism to parse a question into three phrase representations: type representation, object representation, and concept representation. We use the type representation to identify the question type and the possible answer set (yes/no or specific concepts such as colors or numbers), and the object representation to focus on the relevant region of an image. The concept representation is verified with the attended region to infer the final answer. The proposed method decouples the language-based concept discovery and vision-based concept verification in the process of answer inference to prevent language priors from dominating the answering process. Experiments on the VQA-CP dataset demonstrate the effectiveness of our method.

As Computer Vision moves from passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will recover it. We propose a reinforcement-learning approach that maintains a distribution over its internal information, thus explicitly representing the ambiguity in what it knows, and needs to know, towards achieving its goal. Potential actions are then generated according to this distribution. For each potential action a distribution of the expected outcomes is calculated, and the value of the potential information gain assessed. The action taken is that which maximizes the potential information gain. We demonstrate this approach applied to two vision-and-language problems that have attracted significant recent interest, visual dialog and visual query generation. In both cases the method actively selects actions that will best reduce its internal uncertainty, and outperforms its competitors in achieving the goal of the challenge.

Humans are able to describe image contents with coarse to fine details as they wish. However, most image captioning models are intention-agnostic which cannot generate diverse descriptions according to different user intentions initiatively. In this work, we propose the Abstract Scene Graph (ASG) structure to represent user intention in fine-grained level and control what and how detailed the generated description should be. The ASG is a directed graph consisting of three types of abstract nodes (object, attribute, relationship) grounded in the image without any concrete semantic labels. Thus it is easy to obtain either manually or automatically. From the ASG, we propose a novel ASG2Caption model, which is able to recognise user intentions and semantics in the graph, and therefore generate desired captions following the graph structure. Our model achieves better controllability conditioning on ASGs than carefully designed baselines on both VisualGenome and MSCOCO datasets. It also significantly improves the caption diversity via automatically sampling diverse ASGs as control signals. Code will be released at https://github.com/cshizhe/asg2cap.

Referring expression comprehension (REF) aims at identifying a particular object in a scene by a natural language expression. It requires joint reasoning over the textual and visual domains to solve the problem. Some popular referring expression datasets, however, fail to provide an ideal test bed for evaluating the reasoning ability of the models, mainly because 1) their expressions typically describe only some simple distinctive properties of the object and 2) their images contain limited distracting information. To bridge the gap, we propose a new dataset for visual reasoning in context of referring expression comprehension with two main features. First, we design a novel expression engine rendering various reasoning logics that can be flexibly combined with rich visual properties to generate expressions with varying compositionality. Second, to better exploit the full reasoning chain embodied in an expression, we propose a new test setting by adding additional distracting images containing objects sharing similar properties with the referent, thus minimising the success rate of reasoning-free cross-domain alignment. We evaluate several state-of-the-art REF models, but find none of them can achieve promising performance. A proposed modular hard mining strategy performs the best but still leaves substantial room for improvement.

Home design is a complex task that normally requires architects to finish with their professional skills and tools. It will be fascinating that if one can produce a house plan intuitively without knowing much knowledge about home design and experience of using complex designing tools, for example, via natural language. In this paper, we formulate it as a language conditioned visual content generation problem that is further divided into a floor plan generation and an interior texture (such as floor and wall) synthesis task. The only control signal of the generation process is the linguistic expression given by users that describe the house details. To this end, we propose a House Plan Generative Model (HPGM) that first translates the language input to a structural graph representation and then predicts the layout of rooms with a Graph Conditioned Layout Prediction Network (GC-LPN) and generates the interior texture with a Language Conditioned Texture GAN (LCT-GAN). With some post-processing, the final product of this task is a 3D house model. To train and evaluate our model, we build the first Text-to-3D House Model dataset, which will be released at: https:// hidden-link-for-submission.

Cross-modal retrieval between videos and texts has attracted growing attentions due to the rapid emergence of videos on the web. The current dominant approach is to learn a joint embedding space to measure cross-modal similarities. However, simple embeddings are insufficient to represent complicated visual and textual details, such as scenes, objects, actions and their compositions. To improve fine-grained video-text retrieval, we propose a Hierarchical Graph Reasoning (HGR) model, which decomposes video-text matching into global-to-local levels. The model disentangles text into a hierarchical semantic graph including three levels of events, actions, entities, and generates hierarchical textual embeddings via attention-based graph reasoning. Different levels of texts can guide the learning of diverse and hierarchical video representations for cross-modal matching to capture both global and local details. Experimental results on three video-text datasets demonstrate the advantages of our model. Such hierarchical decomposition also enables better generalization across datasets and improves the ability to distinguish fine-grained semantic differences. Code will be released at https: //github.com/cshizhe/hgr_v2t.

One of the long-term challenges of robotics is to enable robots to interact with humans in the visual world via natural language, as humans are visual animals that communicate through language. Overcoming this challenge requires the ability to perform a wide variety of complex tasks in response to multifarious instructions from humans. In the hope that it might drive progress towards more flexible and powerful human interactions with robots, we propose a dataset of varied and complex robot tasks, described in natural language, in terms of objects visible in a large set of real images. Given an instruction, success requires navigating through a previously-unseen environment to identify an object. This represents a practical challenge, but one that closely reflects one of the core visual problems in robotics. Several state-of-the-art vision-and-language navigation, and referring-expression models are tested to verify the difficulty of this new task, but none of them show promising results because there are many fundamental differences between our task and previous ones. A novel Interactive Navigator-Pointer model is also proposed that provides a strong baseline on the task. The proposed model especially achieves the best performance on the unseen test split, but still leaves substantial room for improvement compared to the human performance. Repository: https://github.com/YuankaiQi/REVERIE.

Vision-and-language navigation requires an agent to navigate through a real 3D environment following natural language instructions.Despite significant advances, few previous works are able to fully utilize the strong correspondence between the visual and textual sequences.Meanwhile, due to the lack of intermediate supervision, the agent's performance at following each part of the instruction cannot be assessed during navigation.In this work, we focus on the granularity of the visual and language sequences as well as the traceability of agents through the completion of an instruction.We provide agents with fine-grained annotations during training and find that they are able to follow the instruction better and have a higher chance of reaching the target at test time.We enrich the benchmark dataset Roomto-Room (R2R) with sub-instructions and their corresponding paths.To make use of this data, we propose effective sub-instruction attention and shifting modules that select and attend to a single sub-instruction at each time-step.We implement our sub-instruction modules in four state-of-the-art agents, compare with their baseline models, and show that our proposed method improves the performance of all four agents.

Visual Dialogue task requires an agent to be engaged in a conversation with human about an image. The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation. In this paper, we propose a novel generative decoding architecture to generate high-quality responses, which moves away from decoding the whole encoded semantics towards the design that advocates both transparency and flexibility. In this architecture, word generation is decomposed into a series of attention-based information selection steps, performed by the novel recurrent Deliberation, Abandon and Memory (DAM) module. Each DAM module performs an adaptive combination of the response-level semantics captured from the encoder and the word-level semantics specifically selected for generating each word. Therefore, the responses contain more detailed and non-repetitive descriptions while maintaining the semantic accuracy. Furthermore, DAM is flexible to cooperate with existing visual dialogue encoders and adaptive to the encoder structures by constraining the information selection mode in DAM. We apply DAM to three typical encoders and verify the performance on the VisDial v1.0 dataset. Experimental results show that the proposed models achieve new state-of-the-art performance with high-quality responses. The code is available at https://github.com/JXZe/DAM.

Fact-based Visual Question Answering (FVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the final answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features. On top of the multi-layer graph representations, we propose a modality-aware heterogeneous graph convolutional network to capture evidence from different layers that is most relevant to the given question. Specifically, the intra-modal graph convolution selects evidence from each modality and cross-modal graph convolution aggregates relevant information across different graph layers. By stacking this process multiple times, our model performs iterative reasoning across three modalities and predicts the optimal answer by analyzing all question-oriented evidence. We achieve a new state-of-the-art performance on the FVQA task and demonstrate the effectiveness and interpretability of our model with extensive experiments.

Visual Grounding is the task of associating entities in a natural language sentence with objects in an image. In this paper, we formulate visual grounding as a graph matching problem to find node correspondences between a visual scene graph and a language scene graph. These two graphs are heterogeneous, representing structure layouts of the sentence and image, respectively. We learn unified contextual node representations of the two graphs by using a cross-modal graph convolutional network to reduce their discrepancy. The graph matching is thus relaxed as a linear assignment problem because the learned node representations characterize both node information and structure information. A permutation loss and a semantic cycle-consistency loss are further introduced to solve the linear assignment problem with or without ground-truth correspondences. Experimental results on two visual grounding tasks, i.e., referring expression comprehension and phrase localization, demonstrate the effectiveness of our method.

We study the problem of text-based visual question answering (T-VQA) in this paper. Unlike general visual question answering (VQA) which only builds connections between questions and visual contents, T-VQA requires reading and reasoning over both texts and visual concepts that appear in images. Challenges in T-VQA mainly lie in three aspects: 1) It is difficult to understand the complex logic in questions and extract specific useful information from rich image contents to answer them; 2) The text-related questions are also related to visual concepts, but it is difficult to capture cross-modal relationships between the texts and the visual concepts; 3) If the OCR (optical character recognition) system fails to detect the target text, the training will be very difficult. To address these issues, we propose a novel Cascade Reasoning Network (CRN) that consists of a progressive attention module (PAM) and a multimodal reasoning graph (MRG) module. Specifically, the PAM regards the multimodal information fusion operation as a stepwise encoding process and uses the previous attention results to guide the next fusion process. The MRG aims to explicitly model the connections and interactions between texts and visual concepts. To alleviate the dependence on the OCR system, we introduce an auxiliary task to train the model with accurate supervision signals, thereby enhancing the reasoning ability of the model in question answering. Extensive experiments on three popular T-VQA datasets demonstrate the effectiveness of our method compared with SOTA methods. The source code is available at https://github.com/guanghuixu/CRN_tvqa.

Conventional referring expression comprehension (REF) assumes people to query something from an image by describing its visual appearance and spatial location, but in practice, we often ask for an object by describing its affordance or other non-visual attributes, especially when we do not have a precise target. For example, sometimes we say 'Give me something to eat'. In this case, we need to use commonsense knowledge to identify the objects in the image. Unfortunately, there is no existing referring expression dataset reflecting this requirement, not to mention a model to tackle this challenge. In this paper, we collect a new referring expression dataset, called KB-Ref, containing $43$k expressions on 16k images. In KB-Ref, to answer each expression (detect the target object referred by the expression), at least one piece of commonsense knowledge must be required. We then test state-of-the-art (SoTA) REF models on KB-Ref, finding that all of them present a large drop compared to their outstanding performance on general REF datasets. We also present an expression conditioned image and fact attention (ECIFA) network that extracts information from correlated image regions and commonsense knowledge facts. Our method leads to a significant improvement over SoTA REF models, although there is still a gap between this strong baseline and human performance. The dataset and baseline models are available at: https://github.com/wangpengnorman/KB-Ref_dataset.

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method for fine-grained visual recognition. However, label noise in the web training set can severely degrade the model performance. To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition. Specifically, guided by a small amount of clean meta-set, we train a selection net in a meta-learning manner to distinguish in- and out-of-distribution noisy images. To further boost the robustness of the model, we also learn a labeling net to correct the labels of in-distribution noisy data. In this way, our proposed method can alleviate the harmful effects caused by out-of-distribution noise and properly exploit the in-distribution noisy samples for training. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to state-of-the-art noise-robust methods.

Vision-and-Language Navigation (VLN) requires an agent to navigate in a real-world environment following natural language instructions. From both the textual and visual perspectives, we find that the relationships among the scene, its objects, and directional cues are essential for the agent to interpret complex instructions and correctly perceive the environment. To capture and utilize the relationships, we propose a novel Language and Visual Entity Relationship Graph for modelling the inter-modal relationships between text and vision, and the intra-modal relationships among visual entities. We propose a message passing algorithm for propagating information between language elements and visual entities in the graph, which we then combine to determine the next action to take. Experiments show that by taking advantage of the relationships we are able to improve over state-of-the-art. On the Room-to-Room (R2R) benchmark, our method achieves the new best performance on the test unseen split with success rate weighted by path length of 52%. On the Room-for-Room (R4R) dataset, our method significantly improves the previous best from 13% to 34% on the success weighted by normalized dynamic time warping.

Image and sentence matching has made great progress recently, but it remains challenging due to the existing large visual-semantic discrepancy. This mainly arises from two aspects: 1) images consist of unstructured content which is not semantically abstract as the words in the sentences, so they are not directly comparable, and 2) arranging semantic concepts in different semantic order could lead to quite diverse meanings. The words in the sentences are sequentially arranged in a grammatical manner, while the semantic concepts in the images are usually unorganized. In this work, we propose a semantic concepts and order learning framework for image and sentence matching, which can improve the image representation by first predicting semantic concepts and then organizing them in a correct semantic order. Given an image, we first use a multi-regional multi-label CNN to predict its included semantic concepts in terms of object, property and action. These word-level semantic concepts are directly comparable with the words of noun, adjective and verb in the matched sentence. Then, to organize these concepts and make them express similar meanings as the matched sentence, we use a context-modulated attentional LSTM to learn the semantic order. It regards the predicted semantic concepts and image global scene as context at each timestep, and selectively attends to concept-related image regions by referring to the context in a sequential order. To further enhance the semantic order, we perform additional sentence generation on the image representation, by using the groundtruth order in the matched sentence as supervision. After obtaining the improved image representation, we learn the sentence representation with a conventional LSTM, and then jointly perform image and sentence matching and sentence generation for model learning. Extensive experiments demonstrate the effectiveness of our learned semantic concepts and order, by achieving the state-of-the-art results on two public benchmark datasets.

Generating videos given a text description (such as a script) is non-trivial due to the intrinsic complexity of image frames and the structure of videos. Although Generative Adversarial Networks (GANs) have been successfully applied to generate images conditioned on a natural language description, it is still very challenging to generate realistic videos in which the frames are required to follow both spatial and temporal coherence. In this paper, we propose a novel Bottom-up GAN (BoGAN) method for generating videos given a text description. To ensure the coherence of the generated frames and also make the whole video match the language descriptions semantically, we design a bottom-up optimisation mechanism to train BoGAN. Specifically, we devise a region-level loss via attention mechanism to preserve the local semantic alignment and draw details in different sub-regions of video conditioned on words which are most relevant to them. Moreover, to guarantee the matching between text and frame, we introduce a frame-level discriminator, which can also maintain the fidelity of each frame and the coherence across frames. Last, to ensure the global semantic alignment between whole video and given text, we apply a video-level discriminator. We evaluate the effectiveness of the proposed BoGAN on two synthetic datasets (i.e., SBMG and TBMG) and two real-world datasets (i.e., MSVD and KTH).

Cross-modal analysis has become a promising direction for artificial intelligence. Visual representation is crucial for various cross-modal analysis tasks that require visual content understanding. Visual features which contain semantical information can disentangle the underlying correlation between different modalities, thus benefiting the downstream tasks. In this paper, we propose a Visual Reasoning and Attention Network (VRANet) as a plug-and-play module to capture rich visual semantics and help to enhance the visual representation for improving cross-modal analysis. Our proposed VRANet is built based on the bilinear visual attention module which identifies the critical objects. We propose a novel Visual Relational Reasoning (VRR) module to reason about pair-wise and inner-group visual relationships among objects guided by the textual information. The two modules enhance the visual features at both relation level and object level. We demonstrate the effectiveness of the proposed VRANet by applying it to both Visual Question Answering (VQA) and Cross-Modal Information Retrieval (CMIR) tasks. Extensive experiments conducted on VQA 2.0, CLEVR, CMPlaces, and MS-COCO datasets indicate superior performance comparing with state-of-the-art work.

The task in referring expression comprehension is to localize the object instance in an image described by a referring expression phrased in natural language. As a language-to-vision matching task, the key to this problem is to learn a discriminative object feature that can adapt to the expression used. To avoid ambiguity, the expression normally tends to describe not only the properties of the referent itself, but also its relationships to its neighbourhood. To capture and exploit this important information we propose a graph-based, language-guided attention mechanism. Being composed of node attention component and edge attention component, the proposed graph attention mechanism explicitly represents inter-object relationships, and properties with a flexibility and power impossible with competing approaches. Furthermore, the proposed graph attention mechanism enables the comprehension decision to be visualizable and explainable. Experiments on three referring expression comprehension datasets show the advantage of the proposed approach.

One of the core challenges in Visual Dialogue problems is asking the question that will provide the most useful information towards achieving the required objective. Encouraging an agent to ask the right questions is difficult because we don't know a-priori what information the agent will need to achieve its task, and we don't have an explicit model of what it knows already. We propose a solution to this problem based on a Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output. By selecting the question that minimises the predicted regret with respect to this implicit model the agent actively reduces ambiguity. The Bayesian model of uncertainty also enables a principled method for identifying when enough information has been acquired, and an action should be selected. We evaluate our approach on two goal-oriented dialogue datasets, one for visual-based collaboration task and the other for a negotiation-based task. Our uncertainty-aware information-seeking model outperforms its counterparts in these two challenging problems.

As the visual reflections of our daily lives, images are frequently shared on the social network, which generates the abundant 'metadata' that records user interactions with images. Due to the diverse contents and complex styles, some images can be challenging to recognise when neglecting the context. Images with the similar metadata, such as 'relevant topics and textual descriptions', 'common friends of users' and 'nearby locations', form a neighbourhood for each image, which can be used to assist the annotation. In this paper, we propose a Metadata Neighbourhood Graph Co-Attention Network (MangoNet) to model the correlations between each target image and its neighbours. To accurately capture the visual clues from the neighbourhood, a co-attention mechanism is introduced to embed the target image and its neighbours as graph nodes, while the graph edges capture the node pair correlations. By reasoning on the neighbourhood graph, we obtain the graph representation to help annotate the target image. Experimental results on three benchmark datasets indicate that our proposed model achieves the best performance compared to the state-of-the-art methods.

Humans have a surprising capacity to induce general rules that describe the specific actions portrayed in a video sequence. The rules learned through this kind of process allow us to achieve similar goals to those shown in the video but in more general circumstances. Enabling an agent to achieve the same capacity represents a significant challenge. In this paper, we propose a Watch-Reason-Code(WRC) model to synthesise programs that describe the process carried out in a set of video sequences. The 'watch' stage is simply a video encoder that encodes videos to multiple feature vectors. The 'reason' stage takes as input the features from multiple diverse videos and generates a compact feature representation via a novel deviation-pooling method. The 'code' stage is a multi-sound decoder that the first step leverages to generate a draft program layout with possible useful statements and perceptions. Further steps then take these outputs and generate a fully structured, compile-able and executable program. We evaluate the effectiveness of our model in two video-to-program synthesis environments, Karel andVizDoom, showing that we can achieve the state-of-the-art under a variety of settings.

Real images often have multiple labels, i.e., each image is associated with multiple objects or attributes. Compared to single-label image classification, the multilabel classification problem is much more challenging due to several issues. At first, multiple objects can be anywhere in the image. Second, the importance of different regions in an image is different, and the regions of interest in a multilabel image can be very different from another one. Finally, multiple labels of an image can have label dependencies due to complex image structures. To address these challenges, in this paper, we propose to predict the labels sequentially by applying the recurrent neural networks (RNNs), which are used to encode the label dependencies. When predicting a specific label, we introduce a dynamic attention mechanism to enable the model to focus on only regions of interest in the image. Two benchmark datasets (i.e., Pascal VOC and MS-COCO) are adopted to demonstrate the effectiveness of our work. Moreover, we construct a new dataset, which includes many semantic dependent labels in each image, to verify the effectiveness of our model. Experimental results show that our method outperforms several state-of-the-arts, especially when predicting some semantic relative labels.

The number of social images has exploded by the wide adoption of social networks, and people like to share their comments about them. These comments can be a description of the image, or some objects, attributes, scenes in it, which are normally used as the user-provided tags. However, it is well-known that user-provided tags are incomplete and imprecise to some extent. Directly using them can damage the performance of related applications, such as the image annotation and retrieval. In this paper, we propose to learn an image annotation model and refine the user-provided tags simultaneously in a weakly-supervised manner. The deep neural network is utilized as the image feature learning and backbone annotation model, while visual consistency, semantic dependency, and user-error sparsity are introduced as the constraints at the batch level to alleviate the tag noise. Therefore, our model is highly flexible and stable to handle large-scale image sets. Experimental results on two benchmark datasets indicate that our proposed model achieves the best performance compared to the state-of-the-art methods.

Visual relationship detection aims to capture interactions between pairs of objects in images. Relationships between objects and humans represent a particularly important subset of this problem, with implications for challenges such as understanding human behavior, and identifying affordances, amongst others. In addressing this problem we first construct a large-scale human-centric visual relationship detection dataset (HCVRD), which provides many more types of relationship annotations (nearly 10K categories) than the previous released datasets. This large label space better reflects the reality of human-object interactions, but gives rise to a long-tail distribution problem, which in turn demands a zero-shot approach to labels appearing only in the test set. This is the first time this issue has been addressed. We propose a webly-supervised approach to these problems and demonstrate that the proposed model provides a strong baseline on our HCVRD dataset.

In this paper, we exploit memory-augmented neural networks to predict accurate answers to visual questions, even when those answers rarely occur in the training set. The memory network incorporates both internal and external memory blocks and selectively pays attention to each training exemplar. We show that memory-augmented neural networks are able to maintain a relatively long-term memory of scarce training exemplars, which is important for visual question answering due to the heavy-tailed distribution of answers in a general VQA setting. Experimental results in two large-scale benchmark datasets show the favorable performance of the proposed algorithm with the comparison to state of the art.

Image and sentence matching has made great progress recently, but it remains challenging due to the large visual-semantic discrepancy. This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic information as in its matched sentence. In this work, we propose a semantic-enhanced image and sentence matching model, which can improve the image representation by learning semantic concepts and then organizing them in a correct semantic order. Given an image, we first use a multi-regional multi-label CNN to predict its semantic concepts, including objects, properties, actions, etc. Then, considering that different orders of semantic concepts lead to diverse semantic meanings, we use a context-gated sentence generation scheme for semantic order learning. It simultaneously uses the image global context containing concept relations as reference and the groundtruth semantic order in the matched sentence as supervision. After obtaining the improved image representation, we learn the sentence representation with a conventional LSTM, and then jointly perform image and sentence matching and sentence generation for model learning. Extensive experiments demonstrate the effectiveness of our learned semantic concepts and order, by achieving the state-of-the-art results on two public benchmark datasets.

A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent advances in vision and language methods have made incredible progress in closely related areas. This is significant because a robot interpreting a natural-language navigation instruction on the basis of what it sees is carrying out a vision and language process that is similar to Visual Question Answering. Both tasks can be interpreted as visually grounded sequence-to-sequence translation problems, and many of the same methods are applicable. To enable and encourage the application of vision and language methods to the problem of interpreting visually-grounded navigation instructions, we present the Matter-port3D Simulator - a large-scale reinforcement learning environment based on real imagery [11]. Using this simulator, which can in future support a range of embodied vision and language tasks, we provide the first benchmark dataset for visually-grounded natural language navigation in real buildings - the Room-to-Room (R2R) dataset1.

Visual Grounding (VG) aims to locate the most relevant object or region in an image, based on a natural language query. The query can be a phrase, a sentence or even a multi-round dialogue. There are three main challenges in VG: 1) what is the main focus in a query; 2) how to understand an image; 3) how to locate an object. Most existing methods combine all the information curtly, which may suffer from the problem of information redundancy (i.e. ambiguous query, complicated image and a large number of objects). In this paper, we formulate these challenges as three attention problems and propose an accumulated attention (A-ATT) mechanism to reason among them jointly. Our A-ATT mechanism can circularly accumulate the attention for useful information in image, query, and objects, while the noises are ignored gradually. We evaluate the performance of A-ATT on four popular datasets (namely Refer-COCO, ReferCOCO+, ReferCOCOg, and Guesswhat?!), and the experimental results show the superiority of the proposed method in term of accuracy.

The visual dialog task requires an agent to engage in a conversation about an image with a human. It represents an extension of the visual question answering task in that the agent needs to answer a question about an image, but it needs to do so in light of the previous dialog that has taken place. The key challenge in visual dialog is thus maintaining a consistent, and natural dialog while continuing to answer questions correctly. We present a novel approach that combines Reinforcement Learning and Generative Adversarial Networks (GANS) to generate more human-like responses to questions. The GAN helps overcome the relative paucity of training data, and the tendency of the typical MLE-based approach to generate overly terse answers. Critically, the GAN is tightly integrated into the attention mechanism that generates human-interpretable reasons for each answer. This means that the discriminative model of the GAN has the task of assessing whether a candidate answer is generated by a human or not, given the provided reason. This is significant because it drives the generative model to produce high quality answers that are well supported by the associated reasoning. The method also generates the state-of-the-art results on the primary benchmark.

Recognising objects according to a pre-defined fixed set of class labels has been well studied in the Computer Vision. There are a great many practical applications where the subjects that may be of interest are not known beforehand, or so easily delineated, however. In many of these cases natural language dialog is a natural way to specify the subject of interest, and the task achieving this capability (a.k.a, Referring Expression Comprehension) has recently attracted attention. To this end we propose a unified framework, the ParalleL AttentioN (PLAN) network, to discover the object in an image that is being referred to in variable length natural expression descriptions, from short phrases query to long multi-round dialogs. The PLAN network has two attention mechanisms that relate parts of the expressions to both the global visual content and also directly to object candidates. Furthermore, the attention mechanisms are recurrent, making the referring process visualizable and explainable. The attended information from these dual sources are combined to reason about the referred object. These two attention mechanisms can be trained in parallel and we find the combined system outperforms the state-of-art on several benchmarked datasets with different length language input, such as RefCOCO, RefCOCO+ and GuessWhat?!.

Visual Question Answering (VQA) has attracted much attention in both computer vision and natural language processing communities, not least because it offers insight into the relationships between two important sources of information. Current datasets, and the models built upon them, have focused on questions which are answerable by direct analysis of the question and image alone. The set of such questions that require no external information to answer is interesting, but very limited. It excludes questions which require common sense, or basic factual knowledge to answer, for example. Here we introduce FVQA (Fact-based VQA), a VQA dataset which requires, and supports, much deeper reasoning. FVQA primarily contains questions that require external information to answer. We thus extend a conventional visual question answering dataset, which contains image-question-answer triplets, through additional image-question-answer-supporting fact tuples. Each supporting-fact is represented as a structural triplet, such as .

Much of the recent progress in Vision-to-Language problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we first propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We further show that the same mechanism can be used to incorporate external knowledge, which is critically important for answering high level visual questions. Specifically, we design a visual question answering model that combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. It particularly allows questions to be asked where the image alone does not contain the information required to select the appropriate answer. Our final model achieves the best reported results for both image captioning and visual question answering on several of the major benchmark datasets.

Deep convolution neural networks (CNNs) have demonstrated advanced performance on single-label image classification, and various progress also has been made to apply CNN methods on multilabel image classification, which requires annotating objects, attributes, scene categories, etc., in a single shot. Recent state-of-the-art approaches to the multilabel image classification exploit the label dependencies in an image, at the global level, largely improving the labeling capacity. However, predicting small objects and visual concepts is still challenging due to the limited discrimination of the global visual features. In this paper, we propose a regional latent semantic dependencies model (RLSD) to address this problem. The utilized model includes a fully convolutional localization architecture to localize the regions that may contain multiple highly dependent labels. The localized regions are further sent to the recurrent neural networks to characterize the latent semantic dependencies at the regional level. Experimental results on several benchmark datasets show that our proposed model achieves the best performance compared to the state-of-the-art models, especially for predicting small objects occurring in the images. Also, we set up an upper bound model (RLSD+ft-RPN) using bounding-box coordinates during training, and the experimental results also show that our RLSD can approach the upper bound without using the bounding-box annotations, which is more realistic in the real world.

One of the most intriguing features of the Visual Question Answering (VQA) challenge is the unpredictability of the questions. Extracting the information required to answer them demands a variety of image operations from detection and counting, to segmentation and reconstruction. To train a method to perform even one of these operations accurately from {image, question, answer} tuples would be challenging, but to aim to achieve them all with a limited set of such training data seems ambitious at best. Our method thus learns how to exploit a set of external off-the-shelf algorithms to achieve its goal, an approach that has something in common with the Neural Turing Machine [10]. The core of our proposed method is a new co-attention model. In addition, the proposed approach generates human-readable reasons for its decision, and can still be trained end-to-end without ground truth reasons being given. We demonstrate the effectiveness on two publicly available datasets, Visual Genome and VQA, and show that it produces the state-of-the-art results in both cases.

We describe a method for visual question answering which is capable of reasoning about an image on the basis of information extracted from a large-scale knowledge base. The method not only answers natural language questions using concepts not contained in the image, but can explain the reasoning by which it developed its answer. It is capable of answering far more complex questions than the predominant long short-term memory-based approach, and outperforms it significantly in testing. We also provide a dataset and a protocol by which to evaluate general visual question answering methods.

Much recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. In this paper we investigate whether this direct approach succeeds due to, or despite, the fact that it avoids the explicit representation of high-level information. We propose a method of incorporating high-level concepts into the successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art in both image captioning and visual question answering. We also show that the same mechanism can be used to introduce external semantic information and that doing so further improves performance. We achieve the best reported results on both image captioning and VQA on several benchmark datasets, and provide an analysis of the value of explicit high-level concepts in V2L problems.

We propose a method for visual question answering which combines an internal representation of the content of an image with information extracted from a general knowledge base to answer a broad range of image-based questions. This allows more complex questions to be answered using the predominant neural network-based approach than has previously been possible. It particularly allows questions to be asked about the contents of an image, even when the image itself does not contain the whole answer. The method constructs a textual representation of the semantic content of an image, and merges it with textual information sourced from a knowledge base, to develop a deeper understanding of the scene viewed. Priming a recurrent neural network with this combined information, and the submitted question, leads to a very flexible visual question answering approach. We are specifically able to answer questions posed in natural language, that refer to information not contained in the image. We demonstrate the effectiveness of our model on two publicly available datasets, Toronto COCO-QA [23] and VQA [1] and show that it produces the best reported results in both cases.

Cross-depiction is the recognition—and synthesis—of objects whether they are photographed, painted, drawn, etc. It is a significant yet underresearched problem. Emulating the remarkable human ability to recognise and depict objects in an astonishingly wide variety of depictive forms is likely to advance both the foundations and the applications of computer vision. In this paper we motivate the cross-depiction problem, explain why it is difficult, and discuss some current approaches. Our main conclusions are (i) appearance-based recognition systems tend to be over-fitted to one depiction, (ii) models that explicitly encode spatial relations between parts are more robust, and (iii) recognition and non-photorealistic synthesis are related tasks.

This paper provides evidence that about half of all the regions in segmented images can be classified as one a few simple shapes. Using three segmentation algorithms, three different image databases, and two shape descriptors, we empirically show that shapes such as triangles, squares, and circles are observed, up to an affine transform and at a much higher rate than random shapes. This result has potential value in applications such as scene understanding, visual object classification, and matching because qualitative shapes can be used as features. We show an application in scene categorisation based on what might be called ‘bag of shapes’ .

This paper provides evidence that about half of all the regions in segmented images can be classified as one a few simple shapes. Using three segmentation algorithms, three different image databases, and two shape descriptors, we empirically show that shapes such as triangles, squares, and circles are observed, up to an affine transform and at a much higher rate than random shapes. This result has potential value in applications such as scene understanding, visual object classification, and matching because qualitative shapes can be used as features. We show an application in scene categorisation based on what might be called ‘bag of shapes’ .