Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale user tracking, while multi-bit methods are highly sensitive to certain image transformations or generative attacks, resulting in a lack of comprehensive robustness. In this paper, we propose OptMark, an optimization-based approach that embeds a robust multi-bit watermark into the intermediate latents of the diffusion denoising process. OptMark strategically inserts a structural watermark early to resist generative attacks and a detail watermark late to withstand image transformations, with tailored regularization terms to preserve image quality and ensure imperceptibility. To address the challenge of memory consumption growing linearly with the number of denoising steps during optimization, OptMark incorporates adjoint gradient methods, reducing memory usage from O(N) to O(1). Experimental results demonstrate that OptMark achieves invisible multi-bit watermarking while ensuring robust resilience against valuemetric transformations, geometric transformations, editing, and regeneration attacks.

Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, extending these capabilities to videos presents substantial challenges, particularly in ensuring precise and temporally consistent mask propagation in dynamic scenes. SAM 2 attempts to address this by training a model on massive image and video data from scratch to learn complex spatiotemporal associations, resulting in huge training costs that hinder research and practical deployment. In this paper, we introduce SAM-I2V++, a training-efficient image-to-video upgradation method for cultivating a promptable video segmentation (PVS) model. Our approach strategically upgrades the pre-trained SAM to support PVS, significantly reducing training complexity and resource requirements. To achieve this, we introduce three key innovations: (i) an image-to-video feature extraction upgrader built upon SAM's static image encoder to enable spatiotemporal video perception, (ii) a memory selective associator that retrieves the most relevant past frames via similarity-driven selection and uses multiscale-enhanced cross-attention to associate selected memory features with the current frame, and (iii) a memory-as-prompt mechanism leveraging object memory to ensure temporally consistent mask propagation in dynamic scenes. Comprehensive experiments demonstrate that our method achieves 93% of SAM 2's performance while using only 0.2% of its training cost. Our work presents a resource-efficient pathway to PVS, lowering barriers for further research in PVS model design and enabling broader applications and advancements in the field.

Fully-supervised category-level pose estimation aims to determine the 6-DoF poses of unseen instances from known categories, requiring expensive manual labeling costs. Recently, various self-supervised category-level pose estimation methods have been proposed to reduce the requirement of the annotated datasets. However, most methods rely on synthetic data or 3D CAD model, and they are typically limited to addressing single-object pose problems without considering multi-objective tasks or shape reconstruction. To overcome these challenges and limitations, we introduce a diffusion-driven self-supervised network for multi-object shape reconstruction and categorical pose estimation, only leveraging the shape priors. Specifically, to capture the SE(3)-equivariant pose features and 3D scale-invariant shape information, we present a Prior-Aware Pyramid 3D Point Transformer. This module adopts a point convolutional layer with radial-kernels for pose-aware learning and a 3D scale-invariant graph convolution layer for object-level shape representation. Furthermore, we introduce a Pretrain-to-Refine Self-Supervised Training Paradigm to train our network. It enables proposed network to capture the associations between shape priors and observations, addressing the challenge of intra-class shape variations by utilising the diffusion mechanism. Extensive experiments conducted on four public datasets and a self-built dataset demonstrate that our method significantly outperforms state-of-the-art self-supervised category-level baselines and even surpasses some fully-supervised instance-level and category-level methods. The project page is released at Self-SRPE.

Large Language Model (LLM)-based agents have shown promise in procedural tasks, but the potential of multimodal instructions augmented by texts and videos to assist users remains under-explored. To address this gap, we propose the Visually Grounded Text-Video Prompting (VG-TVP) method which is a novel LLM-empowered Multimodal Procedural Planning (MPP) framework. It generates cohesive text and video procedural plans given a specified high-level objective. The main challenges are achieving textual and visual informativeness, temporal coherence, and accuracy in procedural plans. VG-TVP leverages the zero-shot reasoning capability of LLMs, the video-to-text generation ability of the video captioning models, and the text-to-video generation ability of diffusion models. VG-TVP improves the interaction between modalities by proposing a novel Fusion of Captioning (FoC) method and using Text-to-Video Bridge (T2V-B) and Video-to-Text Bridge (V2T-B). They allow LLMs to guide the generation of visually-grounded text plans and textual-grounded video plans. To address the scarcity of datasets suitable for MPP, we have curated a new dataset called Daily-Life Task Procedural Plans (Daily-PP). We conduct comprehensive experiments and benchmarks to evaluate human preferences (regarding textual and visual informativeness, temporal coherence, and plan accuracy). Our VG-TVP method outperforms unimodal baselines on the Daily-PP dataset.

Large language models demonstrate remarkable capabilities across various domains, especially mathematics and logic reasoning. However, current evaluations overlook physics-based reasoning - a complex task requiring physics theorems and constraints. We present PhysReason, a 1,200-problem benchmark comprising knowledge-based (25%) and reasoning-based (75%) problems, where the latter are divided into three difficulty levels (easy, medium, hard). Notably, problems require an average of 8.1 solution steps, with hard requiring 15.6, reflecting the complexity of physics-based reasoning. We propose the Physics Solution Auto Scoring Framework, incorporating efficient answer-level and comprehensive step-level evaluations. Top-performing models like Deepseek-R1, Gemini-2.0-Flash-Thinking, and o3-mini-high achieve less than 60% on answer-level evaluation, with performance dropping from knowledge questions (75.11%) to hard problems (31.95%). Through step-level evaluation, we identified four key bottlenecks: Physics Theorem Application, Physics Process Understanding, Calculation, and Physics Condition Analysis. These findings position PhysReason as a novel and comprehensive benchmark for evaluating physics-based reasoning capabilities in large language models.

Recent advancements in video generation models, like Stable Video Diffusion, show promising results, but primarily focus on short, single-scene videos. These models struggle with generating long videos that involve multiple scenes, coherent narratives, and consistent characters. Furthermore, there is no publicly available dataset tailored for the analysis, evaluation, and training of long video generation models. In this paper, we present MovieBench: A Hierarchical Movie-Level Dataset for Long Video Generation, which addresses these challenges by providing unique contributions: (1) movie-length videos featuring rich, coherent storylines and multi-scene narratives, (2) consistency of character appearance and audio across scenes, and (3) hierarchical data structure contains high-level movie information and detailed shot-level descriptions. Experiments demonstrate that MovieBench brings some new insights and challenges, such as maintaining character ID consistency across multiple scenes for various characters. The dataset will be public and continuously maintained, aiming to advance the field of long video generation. Data can be found at: MovieBench.

Adapting generative models to specific domains presents an effective solution for satisfying specialized requirements. However, adapting to some complex domains remains challenging, especially when these domains require substantial paired data to capture the targeted distributions. Since unpaired data from a single modality, such as vision or language, is more readily available, we utilize the bidirectional mappings between vision and language learned by the unified generative model to enable training on unpaired data for domain adaptation. Specifically, we propose DoraCycle, which integrates two multimodal cycles: text-to-image-to-text and image-to-text-to-image. The model is optimized through cross-entropy loss computed at the cycle endpoints, where both endpoints share the same modality. This facilitates self-evolution of the model without reliance on annotated text-image pairs. Experimental results demonstrate that for tasks independent of paired knowledge, such as stylization, DoraCycle can effectively adapt the unified model using only unpaired data. For tasks involving new paired knowledge, such as specific identities, a combination of a small set of paired image-text examples and larger-scale unpaired data is sufficient for effective domain-oriented adaptation. The code will be released at https://github.com/showlab/DoraCycle.

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data pipeline for YouTube videos and their closed captions (CC), resulting in Live-CC-10M pre-training set and Live-WhisperX-408K high-quality supervised fine-tuning (SFT) set. Remarkably, even without SFT, the pre-trained model LiveCC-7B demonstrates significant improvements in general video QA and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new benchmark LiveSports-3K, using LLM-as-a-judge to measure the free-form commentary. Experiments show our final model LiveCC-7B can surpass LLaVA-Video-72B in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B scale on popular benchmarks such as VideoMME, demonstrating its broad generalizability. All resources of this paper have been released at showlab.github.io/livecc.

Natural language often struggles to accurately associate positional and attribute information with multiple instances, which limits current text-based visual generation models to simpler compositions featuring only a few dominant instances. To address this limitation, this work enhances diffusion models by introducing regional instance control, where each instance is governed by a bounding box paired with a free-form caption. Previous methods in this area typically rely on implicit position encoding or explicit attention masks to separate regions of interest (ROIs), resulting in either inaccurate coordinate injection or large computational overhead. Inspired by ROI-Align in object detection, we introduce a complementary operation called ROI-Unpool. Together, ROI-Align and ROI- Unpool enable explicit, efficient, and accurate ROI manipulation on high-resolution feature maps for visual generation. Building on ROI-Unpool, we propose ROICtrl, an adapter for pretrained diffusion models that enables precise regional instance control. ROICtrl is compatible with community-finetuned diffusion models, as well as with existing spatial-based add-ons (e.g., ControlNet, T2I- Adapter) and embedding-based add-ons (e.g., IP-Adapter, ED-LoRA), extending their applications to multi-instance generation. Experiments show that ROICtrl achieves superior performance in regional instance control while significantly reducing computational costs.

Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances. With above components, ShowUI, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding. Its UI-guided token selection further reduces 33% of redundant visual tokens during training and speeds up the performance by 1.4×. Navigation experiments across web [12], mobile [35], and online [39] environments further underscore the effectiveness and potential of our model in advancing GUI visual agents. The models are available at https://github.com/showlab/ShowUI.

Human daily activities can be concisely narrated as sequences of routine events (e.g., turning off an alarm) in video streams, forming an event vocabulary. Motivated by this, we introduce VLog, a novel video understanding framework that define video narrations as vocabulary, going beyond the typical subword vocabularies in existing generative video-language models. Built on the lightweight language model GPT-2, VLog feature three key innovations: (i) A generative retrieval model, marrying language model’s complex reasoning capabilities with contrastive retrieval’s efficient similarity search. (ii) A hierarchical vocabulary derived from large-scale video narrations using our narration pair encoding algorithm, enabling efficient indexing of specific events (e.g., cutting a tomato) by identifying broader scenarios (e.g., kitchen) with expressive postfixes (e.g., by the left hand). (iii) A vocabulary update strategy leveraging generative models to extend the vocabulary for novel events encountered during inference. To validate our approach, we introduce VidCap-Eval, a development set requiring concise narrations with reasoning relationships (e.g., before and after). Experiments on EgoSchema, COIN, and HiREST further demonstrate the effectiveness of VLog, highlighting its ability to generate concise, contextually accurate, and efficient narrations, offering a novel perspective on video understanding. Codes are released at https://github.com/showlab/VLog.

Foundation models like the Segment Anything Model (SAM) have significantly advanced promptable image segmentation in computer vision. However, extending these capabilities to videos presents substantial challenges, particularly in ensuring precise and temporally consistent mask propagation in dynamic scenes. SAM 2 attempts to address this by training a model on massive image and video data from scratch to learn complex spatiotemporal associations, resulting in huge training costs that hinder research and practical deployment. In this paper, we introduce SAM-I2V, an effective image-to-video upgradation method for cultivating a promptable video segmentation (PVS) model. Our approach strategically upgrades the pre-trained SAM to support PVS, significantly reducing training complexity and resource requirements. To achieve this, we introduce three key innovations: (i) an image-to-video feature extraction upgrader built upon SAM’s static image encoder to enable spatiotemporal video perception, (ii) a memory filtering strategy that selects the most relevant past frames for more effective utilization of historical information, and (iii) a memory-as-prompt mechanism leveraging object memory to ensure temporally consistent mask propagation in dynamic scenes. Comprehensive experiments demonstrate that our method achieves over 90% of SAM 2’s performance while using only 0.2% of its training cost. Our work presents a resource-efficient pathway to PVS, lowering barriers for further research in PVS model design and enabling broader applications and advancements in the field. Code and model will be available at: https://github.com/showlab/SAM-I2V.

Recently, zero-shot methods like InstantID have revolutionized identity-preserving generation. Unlike multi-image finetuning approaches such as DreamBooth, these zero-shot methods leverage powerful facial encoders to extract identity information from a single portrait photo, enabling efficient identity-preserving generation through a single inference pass. However, this convenience introduces new threats to the facial identity protection. This paper aims to safeguard portrait photos from unauthorized encoder-based customization. We introduce IDProtector, an adversarial noise encoder that applies imperceptible adversarial noise to portrait photos in a single forward pass. Our approach offers universal protection for portraits against multiple state-of-the-art encoder-based methods, including InstantID, IP-Adapter, and PhotoMaker, while ensuring robustness to common image transformations such as JPEG compression, resizing, and affine transformations. Experiments across diverse portrait datasets and generative models reveal that IDProtector generalizes effectively to unseen data and even closed-source proprietary models. Project page: https://github.com/showlab/IDProtector.

Neural Radiance Fields and 3D Gaussian Splatting have revolutionized 3D reconstruction and novel-view synthesis task. However, achieving photorealistic rendering from extreme novel viewpoints remains challenging, as artifacts persist across representations. In this work, we introduce Difix3D+, a novel pipeline designed to enhance 3D reconstruction and novel-view synthesis through single-step diffusion models. At the core of our approach is Difix, a single-step image diffusion model trained to enhance and remove artifacts in rendered novel views caused by under-constrained regions of the 3D representation. Difix serves two critical roles in our pipeline. First, it is used during the reconstruction phase to clean up pseudo-training views that are rendered from the reconstruction and then distilled back into 3D. This greatly enhances underconstrained regions and improves the overall 3D representation quality. More importantly, Difix also acts as a neural enhancer during inference, effectively removing residual artifacts arising from imperfect 3D supervision and the limited capacity of current reconstruction models. Difix3D+ is a general solution, a single model compatible with both NeRF and 3DGS representations, and it achieves an average 2× improvement in FID score over baselines while maintaining 3D consistency.

Recently, breakthroughs in video modeling have allowed for controllable camera trajectories in generated videos. However, these methods cannot be directly applied to user-provided videos that are not generated by a video model. In this paper, we present ReCapture, a method for generating new videos with novel camera trajectories from a single user-provided video. Our method allows us to re-generate the reference video, with all its existing scene motion, from vastly different angles and with cinematic camera motion. Notably, using our method we can also plausibly hallucinate parts of the scene that were not observable in the reference video. Our method works by (1) generating a noisy anchor video with a new camera trajectory using multiview diffusion models or depth-based point cloud rendering and then (2) regenerating the anchor video into a clean and temporally consistent reangled video using our proposed masked video fine-tuning technique.

Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer based framework that bridges this gap by learning designers' layered SVG creation processes from a novel dataset of sequential design operations. Our approach operates in two phases: First, a text-conditioned DiT generates multi-phase rasterized construction blueprints that simulate human design workflows. Second, layer-wise vectorization with path deduplication produces clean, editable SVGs. For image vectorization, we introduce a conditional diffusion mechanism that encodes reference images into latent tokens, guiding hierarchical reconstruction while preserving structural integrity. Extensive experiments demonstrate LayerTracer's superior performance against optimization-based and neural baselines in both generation quality and editability, effectively aligning AI-generated vectors with professional design cognition.

Diffusion models have fundamentally transformed the field of generative models, making the assessment of similarity between customized model outputs and reference inputs critically important. However, traditional perceptual similarity metrics operate primarily at the pixel and patch levels, comparing low-level colors and textures but failing to capture mid-level similarities and differences in image layout, object pose, and semantic content. Contrastive learning-based CLIP and self-supervised learning-based DINO are often used to measure semantic similarity, but they highly compress image features, inadequately assessing appearance details. This paper is the first to discover that pretrained diffusion models can be utilized for measuring visual similarity and introduces the DiffSim method, addressing the limitations of traditional metrics in capturing perceptual consistency in custom generation tasks. By aligning features in the attention layers of the denoising U-Net, DiffSim evaluates both appearance and style similarity, showing superior alignment with human visual preferences. Additionally, we introduce the Sref and IP benchmarks to evaluate visual similarity at the level of style and instance, respectively. Comprehensive evaluations across multiple benchmarks demonstrate that DiffSim achieves state-of-the-art performance, providing a robust tool for measuring visual coherence in generative models.

As online video content rapidly grows, the task of text-video retrieval (TVR) becomes increasingly important. A key challenge in TVR is the information asymmetry between video and text: videos are inherently richer in information, while their textual descriptions often capture only fragments of this complexity. This paper introduces a novel, data-centric framework to bridge this gap by enriching textual representations to better match the richness of video content. During training, videos are segmented into event-level clips and captioned to ensure comprehensive coverage. During retrieval, a large language model (LLM) generates semantically diverse queries to capture a broader range of possible matches. To enhance retrieval efficiency, we propose a query selection mechanism that identifies the most relevant and diverse queries, reducing computational cost while improving accuracy. Our method achieves state-of-the-art results across multiple benchmarks, demonstrating the power of data-centric approaches in addressing information asymmetry in TVR. This work paves the way for new research focused on leveraging data to improve cross-modal retrieval.

Human instance matting aims to estimate an alpha matte for each human instance in an image, which is challenging as it easily fails in complex cases requiring disentangling mingled pixels belonging to multiple instances along hairy and thin boundary structures. In this work, we address this by introducing MP-Mat, a novel 3D-and-instance-aware matting framework with multiplane representation, where the multiplane concept is designed from two different perspectives: scene geometry level and instance level. Specifically, we first build feature-level multiplane representations to split the scene into multiple planes based on depth differences. This approach makes the scene representation 3D-aware, and can serve as an effective clue for splitting instances in different 3D positions, thereby improving interpretability and boundary handling ability especially in occlusion areas. Then, we introduce another multiplane representation that splits the scene in an instance-level perspective, and represents each instance with both matte and color. We also treat background as a special instance, which is often overlooked by existing methods. Such an instance-level representation facilitates both foreground and background content awareness, and is useful for other down-stream tasks like image editing. Once built, the representation can be reused to realize controllable instance-level image editing with high efficiency. Extensive experiments validate the clear advantage of MP-Mat in matting task. We also demonstrate its superiority in image editing tasks, an area under-explored by existing matting-focused methods, where our approach under zero-shot inference even outperforms trained specialized image editing techniques by large margins. Code is open-sourced at https://github.com/JiaoSiyi/MPMat.git.

Recent advancements in Multimodal Large Language Models (MLLMs) have accelerated the development of Graphical User Interface (GUI) agents capable of automating complex tasks across digital platforms. However, precise GUI element grounding remains a key challenge for accurate interaction and generalization. In this work, we present an effective GUI grounding framework, which includes an automated data collection engine that gathers extensive GUI screenshots and annotations to ensure broad generalization. We also propose a lightweight and flexible GUI grounding module designed to efficiently localize UI elements by pre-training on the collected data, and introduce a novel method to integrate this module with MLLMs for the effective execution of GUI tasks. Our approach demonstrates superior performance in task accuracy and adaptability, as validated by benchmarks such as ScreenSpot, MiniWob, AITW, and Mind2Web.

Image watermark techniques provide an effective way to assert ownership, deter misuse, and trace content sources, which has become increasingly essential in the era of large generative models. A critical attribute of watermark techniques is their robustness against various manipulations. In this paper, we introduce a watermark removal approach capable of effectively nullifying state-of-the-art watermarking techniques. Our primary insight involves regenerating the watermarked image starting from a \textbf{clean Gaussian noise} via a controllable diffusion model, utilizing the extracted semantic and spatial features from the watermarked image. The semantic control adapter and the spatial control network are specifically trained to control the denoising process towards ensuring image quality and enhancing consistency between the cleaned image and the original watermarked image. To achieve a smooth trade-off between watermark removal performance and image consistency, we further propose an adjustable and controllable regeneration scheme. This scheme adds varying numbers of noise steps to the latent representation of the watermarked image, followed by a controlled denoising process starting from this noisy latent representation. As the number of noise steps increases, the latent representation progressively approaches clean Gaussian noise, facilitating the desired trade-off. We apply our watermark removal methods across various watermarking techniques, and the results demonstrate that our methods offer superior visual consistency/quality and enhanced watermark removal performance compared to existing regeneration approaches. Our code is available at \url{https://github.com/yepengliu/CtrlRegen}.

We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model.

Synthetic videos nowadays is widely used to complement data scarcity and diversity of real-world videos. Current synthetic datasets primarily replicate real-world scenarios, leaving impossible, counterfactual and anti-reality video concepts underexplored. This work aims to answer two questions: 1) Can today’s video generation models effectively follow prompts to create impossible video content? 2) Are today’s video understanding models good enough for understanding impossible videos? To this end, we introduce IPV-Bench, a novel benchmark designed to evaluate and foster progress in video understanding and generation. IPV-Bench is underpinned by a comprehensive taxonomy, encompassing 4 domains, 14 categories. It features diverse scenes that defy physical, biological, geographical, or social laws. Based on the taxonomy, a prompt suite is constructed to evaluate video generation models, challenging their prompt following and creativity capabilities. In addition, a video benchmark is curated to assess Video-LLMs on their ability of understanding impossible videos, which particularly requires reasoning on temporal dynamics and world knowledge. Comprehensive evaluations reveal limitations and insights for future directions of video models, paving the way for next-generation video models.

Watermarking is essential for protecting the copyright of AI-generated images. We propose WMAdapter, a diffusion model watermark plugin that embeds user-specified watermark information seamlessly during the diffusion generation process. Unlike previous methods that modify diffusion modules to incorporate watermarks, WMAdapter is designed to keep all diffusion components intact, resulting in sharp, artifact-free images. To achieve this, we introduce two key innovations: (1) We develop a contextual adapter that conditions on the content of the cover image to generate adaptive watermark embeddings. (2) We implement an additional finetuning step and a hybrid finetuning strategy that suppresses noticeable artifacts while preserving the integrity of the diffusion components. Empirical results show that WMAdapter provides strong flexibility, superior image quality, and competitive watermark robustness.

Natural images often exhibit underlying sparse structures, with information density varying significantly across different spatial locations. However, most generative models rely on dense grid-based pixels or latents, neglecting this inherent sparsity. In this paper, we explore modeling visual generation paradigm via sparse non-grid latent representations. Specifically, we design a sparse autoencoder that represents an image as a small number of latents with their positional properties (i.e., regions of interest, RoIs) with high reconstruction quality. We then explore training flow-matching transformers jointly on non-grid latents and RoI values. To the best knowledge, we are the first to address spatial sparsity using RoIs in generative process. Experimental results show that our sparse flow-based transformers have competitive performance compared with dense grid-based counterparts with significantly reduced lower compute, and reaches a competitive 2.76 FID with just 64 latents on class-conditional ImageNet $256\times 256$ generation.

Vision-language foundation models (VLMs), such as CLIP, exhibit remarkable performance across a wide range of tasks. However, deploying these models can be unreliable when significant distribution gaps exist between training and test data, while fine-tuning for diverse scenarios is often costly. Cache-based test-time adapters offer an efficient alternative by storing representative test samples to guide subsequent classifications. Yet, these methods typically employ naive cache management with limited capacity, leading to severe catastrophic forgetting when samples are inevitably dropped during updates. In this paper, we propose DOTA (DistributiOnal Test-time Adaptation), a simple yet effective method addressing this limitation. Crucially, instead of merely memorizing individual test samples, DOTA continuously estimates the underlying distribution of the test data stream. Test-time posterior probabilities are then computed using these dynamically estimated distributions via Bayes' theorem for adaptation. This distribution-centric approach enables the model to continually learn and adapt to the deployment environment. Extensive experiments validate that DOTA significantly mitigates forgetting and achieves state-of-the-art performance compared to existing methods.

Diffusion models have advanced image stylization significantly, yet two core challenges persist: (1) maintaining consistent stylization in complex scenes, particularly identity, composition, and fine details, and (2) preventing style degradation in image-to-image pipelines with style LoRAs. GPT-4o's exceptional stylization consistency highlights the performance gap between open-source methods and proprietary models. To bridge this gap, we propose \textbf{OmniConsistency}, a universal consistency plugin leveraging large-scale Diffusion Transformers (DiTs). OmniConsistency contributes: (1) an in-context consistency learning framework trained on aligned image pairs for robust generalization; (2) a two-stage progressive learning strategy decoupling style learning from consistency preservation to mitigate style degradation; and (3) a fully plug-and-play design compatible with arbitrary style LoRAs under the Flux framework. Extensive experiments show that OmniConsistency significantly enhances visual coherence and aesthetic quality, achieving performance comparable to commercial state-of-the-art model GPT-4o.

Reinforcement Learning (RL) has proven to be an effective post-training strategy for enhancing reasoning in vision–language models (VLMs). Group Relative Policy Optimization (GRPO) is a recent prominent method that encourages models to generate complete reasoning traces before answering, leading to increased token usage and computational cost. Inspired by the human-like thinking process—where people skip reasoning for easy questions but think carefully when needed—we explore how to enable VLMs to first decide *when reasoning is necessary*. To realize this, we propose \ours, a two-stage training strategy: **(i)** a supervised fine-tuning (SFT) stage with a simple yet effective “**thought dropout**” operation, where reasoning traces are randomly replaced with empty thoughts. This introduces a think-or-not format that serves as a cold start for selective reasoning; **(ii)** a GRPO stage that enables the model to freely explore when to think or not, while maximizing task-aware outcome rewards. Experimental results show that \ours can *reduce the completion length by up to **90%** compared to vanilla GRPO, without sacrificing performance or even improving it*. Further evaluations across LLM (GSM8K), VLM (CLEVR, Super-CLEVR, GeoQA), and Agentic (AITZ) tasks—covering a range of reasoning difficulties under both 3B and 7B models—consistently reveal that the \textit{model progressively learns to bypass unnecessary reasoning steps as training advances}. These findings shed light on the path toward human-like reasoning patterns in RL approaches. Our code is available at https://github.com/kokolerk/TON.

This paper presents improved native unified multimodal models, \emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at https://github.com/showlab/Show-o.

Graphical User Interface (GUI) agents show promising capabilities for automating computer-use tasks and facilitating accessibility, but existing interactive benchmarks are mostly English-only, covering web-use or Windows, Linux, and Android environments, but not macOS. macOS is a major OS with distinctive GUI patterns and exclusive applications. To bridge the gaps, we present macOSWorld, the first comprehensive benchmark for evaluating GUI agents on macOS. macOSWorld features 202 multilingual interactive tasks across 30 applications (28 macOS-exclusive), with task instructions and OS interfaces offered in 5 languages (English, Chinese, Arabic, Japanese, and Russian). As GUI agents are shown to be vulnerable to deception attacks, macOSWorld also includes a dedicated safety benchmarking subset. Our evaluation on six GUI agents reveals a dramatic gap: proprietary computer-use agents lead at above 30\% success rate, while open-source lightweight research models lag at below 5\%, highlighting the need for macOS domain adaptation. Multilingual benchmarks also expose common weaknesses, especially in Arabic, with a 28.8\% average degradation compared to English. Results from safety benchmarking also highlight that deception attacks are more general and demand immediate attention. Project page: https://macos-world.github.io.

Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Previous methods typically rely on domain-specific training data and manual adjustments when applying to new scenarios and unseen anomaly types, suffering from high labor costs and limited generalization. Therefore, we aim to achieve generalist VAD, \ie, automatically handle any scene and any anomaly types without training data or human involvement. In this work, we propose PANDA, an agentic AI engineer based on MLLMs. Specifically, we achieve PANDA by comprehensively devising four key capabilities: (1) self-adaptive scene-aware strategy planning, (2) goal-driven heuristic reasoning, (3) tool-augmented self-reflection, and (4) self-improving chain-of-memory. Concretely, we develop a self-adaptive scene-aware RAG mechanism, enabling PANDA to retrieve anomaly-specific knowledge for anomaly detection strategy planning. Next, we introduce a latent anomaly-guided heuristic prompt strategy to enhance reasoning precision. Furthermore, PANDA employs a progressive reflection mechanism alongside a suite of context-aware tools to iteratively refine decision-making in complex scenarios. Finally, a chain-of-memory mechanism enables PANDA to leverage historical experiences for continual performance improvement. Extensive experiments demonstrate that PANDA achieves state-of-the-art performance in multi-scenario, open-set, and complex scenario settings without training and manual involvement, validating its generalizable and robust anomaly detection capability. Code is released at https://github.com/showlab/PANDA.

Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrelevant information, VLMs are susceptible to interference, thus generating excessive task-irrelevant reasoning processes or even hallucinations. This limitation stems from their inability to discover and process the required regions during reasoning precisely. To address this limitation, we present the Chain of Foresight-Focus Thought (CoFFT), a novel training-free approach that enhances VLMs' visual reasoning by emulating human visual cognition. Each Foresight-Focus Thought consists of three stages: (1) Diverse Sample Generation: generates diverse reasoning samples to explore potential reasoning paths, where each sample contains several reasoning steps; (2) Dual Foresight Decoding: rigorously evaluates these samples based on both visual focus and reasoning progression, adding the first step of optimal sample to the reasoning process; (3) Visual Focus Adjustment: precisely adjust visual focus toward regions most beneficial for future reasoning, before returning to stage (1) to generate subsequent reasoning samples until reaching the final answer. These stages function iteratively, creating an interdependent cycle where reasoning guides visual focus and visual focus informs subsequent reasoning. Empirical results across multiple benchmarks using Qwen2.5-VL, InternVL-2.5, and Llava-Next demonstrate consistent performance improvements of 3.1-5.8\% with controllable increasing computational overhead.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset (BOVText). There are four features for BOVText. Firstly, we provide 2,021 videos with more than 1,750,000 frames, 25 times larger than the existing largest dataset with incidental text in videos. Secondly, our dataset covers 32 open scenarios, including many virtual scenarios, e.g., Life Vlog, Driving, Movie, Game, etc. Thirdly, abundant text types annotation (i.e., title, caption or scene text) are provided for the different representational meanings in the video. Fourthly, the BOVText provides bilingual text annotation to promote multiple cultures’ lives and communication. Besides, we propose a real-time end-to-end video text spotting with Contrastive Learning of Semantic and Visual Representation (CoText), which includes two advantages: 1) With a lightweight architecture, CoText simultaneously addresses the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) CoText tracks texts by comprehending them and relating them to each other with visual and semantic representations. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting$\mathrm { ID_{F1}}$of 71.7% at 32.3 FPS on ICDAR2015video, with 10.2% and 23.3 FPS improvement the previous best method. The dataset and code of CoText can be found at: Dataset and CoText, respectively.

Recent Large Language Models (LLMs) have been en-hanced with vision capabilities, enabling them to compre-hend images, videos, and interleaved vision-language con-tent. However, the learning methods of these large multi-modal models (LMMs) typically treat videos as predeter-mined clips, rendering them less effective and efficient at handling streaming video inputs. In this paper, we pro-pose a novel Learning-In- Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time dialogue within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training ob-jective designed to perform language modeling for contin-uous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming di-alogue format, and (3) an optimized inference pipeline to speed up interactive chat in real-world video streams. With our LIVE framework, we develop a simplified model called VideoLLM-online and demonstrate its significant advan-tages in processing streaming videos. For instance, our VideoLLM-online-7B model can operate at over 10 FPS on an A100 GPU for a 5-minute video clip from Ego4D narration. Moreover, VideoLLM-online also showcases state-of-the-art performance on public offline video bench-marks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at showlab.github. iolvideollm-online.

Graphical User Interface (GUI) automation holds significant promise for assisting users with complex tasks, thereby boosting human productivity. Existing works leveraging Large Language Model (LLM) or LLM-based AI agents have shown capabilities in automating tasks on Android and Web platforms. However, these tasks are primarily aimed at simple device usage and entertainment operations. This paper presents a novel benchmark, Assistgui, to evaluate whether models are capable of manipulating the mouse and keyboard on the Windows platform in response to user-requested tasks. We carefully collected a set of 100 tasks from nine widely-used software applications, such as, After Effects and MS Word, each accompanied by the necessary project files for better evaluation. Moreover, we propose a multi-agent collaboration framework, which incorporates four agents to perform task decomposition, GUI parsing, action generation, and reflection. Our experimental results reveal that our multi-agent collaboration mechanism outshines existing methods in performance. Nevertheless, the potential remains substantial, with the best model attaining only a 46% success rate on our benchmark. We conclude with a thorough analysis of the current methods' limitations, setting the stage for future breakthroughs in this domain.

The recently proposed SparseFormer architecture provides an alternative approach to visual understanding by utilizing a significantly lower number of visual tokens via adjusting RoIs, greatly reducing computational costs while still achieving promising performance. However, training SparseFormers from scratch is still expensive, and scaling up the number of parameters can be challenging. In this paper, we propose to bootstrap SparseFormers from ViT-based vision foundation models in a simple and efficient way. Since the majority of SparseFormer blocks are the standard transformer ones, we can inherit weights from large-scale pre-trained vision transformers and freeze them as much as possible. Therefore, we only need to train the SparseFormer-specific lightweight focusing transformer to adjust token RoIs and fine-tune a few early pre-trained blocks to align the final token representation. In such a way, we can bootstrap SparseFormer architectures from various large-scale pre-trained models (e.g., IN-21 K pre-trained AugRegs or CLIPs) using a rather smaller amount of training samples (e.g., IN-IK) and without labels or captions within just a few hours. As a result, the bootstrapped unimodal SparseFormer (from AugReg-ViT-L/16-384) can reach 84.9% accuracy on IN-IK with only 49 tokens, and the multimodal SparseFormer from CLIPs also demonstrates notable zero-shot performance with highly reduced computational cost without seeing any caption during the bootstrapping procedure. In addition, CLIP-bootstrapped SparseFormers, which align the output space with language without seeing a word, can serve as efficient vision encoders in multimodal large language models. Code and models are available at https://github.com/showlab/sparseformer

Vector-Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how the improvement in reconstruction affects the generation ability of generative transformers. In this paper, we surprisingly find that improving the reconstruction fidelity of VQ tokenizers does not necessarily improve the generation. Instead, learning to compress semantic features within VQ tokenizers significantly improves generative transformers' ability to capture textures and structures. We thus highlight two competing objectives of VQ tokeniz-ers for image synthesis: semantic compression and details preservation. Different from previous work that pri-oritizes better details preservation, we propose Semantic-Quantized GAN (SeQ-GAN) with two learning phases to balance the two objectives. In the first phase, we propose a semantic-enhanced perceptual loss for better semantic compression. In the second phase, we fix the encoder and codebook, but enhance and finetune the decoder to achieve better details preservation. Our proposed SeQ-GAN significantly improves VQ-based generative models for both un-conditional and conditional image generation. Specifically, SeQ-GAN achieves a Fré chet Inception Distance (FID) of 6.25 and Inception Score (IS) of 140.9 on 256×256 Ima-geNet generation, which is a remarkable improvement over VIT-VQGAN (714M), which obtains 11.2 FID and 97.2 IS.

Current diffusion-based video editing primarily focuses on structure-preserved editing by utilizing various dense correspondences to ensure temporal consistency and motion alignment. However, these approaches are often in-effective when the target edit involves a shape change. To embark on video editing with shape change, we explore customized video subject swapping in this work, where we aim to replace the main subject in a source video with a target subject having a distinct identity and potentially different shape. In contrast to previous methods that rely on dense correspondences, we introduce the Video Swap framework that exploits semantic point correspondences, inspired by our observation that only a small number of semantic points are necessary to align the subject's motion trajectory and modify its shape. We also introduce various user-point interactions (e.g., removing points and dragging points) to address various semantic point correspondence. Extensive experiments demonstrate state-of-the-art video subject swapping results across a variety of real-world videos.

Aiming to advance AI agents, large foundation models significantly improve reasoning and instruction execution, yet the current focus on vision and language neglects the potential of perceiving diverse modalities in open-world environments. However, the success of data-driven vision and language models is costly or even infeasible to be reproduced for rare modalities. In this paper, we present Vit-lens that facilitates efficient omni-modal representation learning by perceiving novel modalities with a pretrained- ViT and aligning them to a pre-defined space. Specifically, the modality-specific lens is tuned to project any-modal signals to an intermediate embedding space, which are then processed by a strong ViT with pre-trained visual knowledge. The encoded representations are optimized toward aligning with the modal-independent space, pre-defined by off-the-shelf foundation models. Vit-lensprovides a unified solution for representation learning of increasing modalities with two appealing advantages: (i) Unlocking the great potential of pretrained- ViTs to novel modalities effectively with efficient parameters and data regime; (ii) Enabling emergent down- stream capabilities through modality alignment and shared ViT parameters. We tailor Vit-lensto learn representations for 3D point cloud, depth, audio, tactile and EEG, and set new state-of-the-art results across various understanding tasks, such as zero-shot classification. By seamlessly integrating Vit-lensinto Multimodal Foundation Models, we enable Any-modality to Text and Image Generation in a zero-shot manner. Code and models are available at https://github.com/TencentARC/ViT-Lens.

Despite recent progress in diffusion-based video editing, existing methods are limited to short-length videos due to the contradiction between long-range consistency and frame-wise editing. Prior attempts to address this challenge by introducing video-2D representations encounter significant difficulties with large motion- and view-change videos, especially in human-centric scenarios. To overcome this, we propose to introduce the dynamic Neural Radiance Fields (NeRF) as the innovative video representation, where the editing can be performed in the 3D spaces and propagated to the entire video via the deformation field. To provide consistent and controllable editing, we propose the image-based video-NeRF editing pipeline with a set of innovative designs, including multi-view multi-pose Score Distillation Sampling (SDS) from both the 2D personalized diffusion prior and 3D diffusion prior, reconstruction losses, text-guided local parts super-resolution, and style transfer. Extensive experiments demonstrate that our method dubbed as DynVideo-E, significantly outperforms SOTA approaches on two challenging datasets by a large margin of 50% ~ 95% for human preference. Code will be released at https://showlab.github.io/DynVideo-E/.

We introduce X-Adapter, a universal upgrader to enable the pretrained plug-and-play modules (e.g., ControlNet, LoRA) to work directly with the upgraded text-to-image diffusion model (e.g., SDXL) without further retraining. We achieve this goal by training an additional network to control the frozen upgraded model with the new text-image data pairs. In detail, X-Adapter keeps a frozen copy of the old model to preserve the connectors of different plugins. Additionally, X-Adapter adds trainable mapping layers that bridge the decoders from models of different versions for feature remapping. The remapped features will be used as guidance for the upgraded model. To enhance the guidance ability of X-Adapter, we employ a null-text training strategy for the upgraded model. After training, we also introduce a two-stage denoising strategy to align the initial latents of X Adapter and the upgraded model. Thanks to our strategies, X-Adapter demonstrates universal compatibility with various plugins and also enables plugins of different versions to work together, thereby expanding the functionalities of diffusion community. To verify the effectiveness of the proposed method, we conduct extensive experiments and the results show that X-Adapter may facilitate wider application in the upgraded foundational diffusion model. Project page at: https://showlab.github.io/X-Adapter/.

3D visual language multi-modal modeling plays an important role in actual human-computer interaction. However, the inaccessibility of large-scale 3D-language pairs restricts their applicability in real-world scenarios. In this paper, we aim to handle a real-time multi-task for 6-DoF pose tracking of unknown objects, leveraging 3D-language pre-training scheme from a series of 3D point cloud video streams, while simultaneously performing 3D shape reconstruction in current observation. To this end, we present a generic Language-to-4D modeling paradigm termed L4D-Track, that tackles zero-shot 6-DoF Tracking and shape reconstruction by learning pairwise implicit 3D representation and multi-level multi-modal alignment. Our method constitutes two core parts. 1) Pairwise Implicit 3D Space Representation, that establishes spatial-temporal to language coherence descriptions across continuous 3D point cloud video. 2) Language-to-4D Association and Contrastive Alignment, enables multi-modality semantic connections between 3D point cloud video and language. Our method trained exclusively on public NOCS-REAL275 dataset, achieves promising results on both two publicly benchmarks. This not only shows powerful generalization performance, but also proves its remarkable capability in zero-shot inference. The project is released at L4D- Track.

Visual prompting of large vision language models such as CLIP exhibits intriguing zero-shot capabilities. A manually drawn red circle, commonly used for highlighting, can guide CLIP's attention to the surrounding region, to identify specific objects within an image. Without precise object proposals, however, it is insufficient for localization. Our novel, simple yet effective approach, i.e., Differentiable Visual Prompting, enables CLIP to zero-shot localize: given an image and a text prompt describing an object, we first pick a rendered ellipse from uniformly distributed anchor ellipses on the image grid via visual prompting, then use three loss functions to tune the ellipse coefficients to encap-sulate the target region gradually. This yields promising ex-perimental results for referring expression comprehension without precisely specified object proposals. In addition, we systematically present the limitations of visual prompting inherent in CLIP and discuss potential solutions.

This paper studies the human image animation task, which aims to generate a video of a certain reference iden-tity following a particular motion sequence. Existing an-imation works typically employ the frame-warping technique to animate the reference image towards the target motion. Despite achieving reasonable results, these approaches face challenges in maintaining temporal consistency throughout the animation due to the lack of temporal modeling and poor preservation of reference identity. In this work, we introduce Magic/snimate, a diffusion-based framework that aims at enhancing temporal consistency, preserving reference image faithfully, and improving animation fidelity. To achieve this, we first develop a video diffusion model to encode temporal information. Second, to maintain the appearance coherence across frames, we introduce a novel appearance encoder to retain the intricate details of the reference image. Leveraging these two inno-vations, we further employ a simple video fusion technique to encourage smooth transitions for long video animation. Empirical results demonstrate the superiority of our method over baseline approaches on two benchmarks. Notably, our approach outperforms the strongest baseline by over 38% in terms of video fidelity on the challenging TikTok dancing dataset. Code and model will be made available at https://showlab.github.io/magicanimate.

Brain-inspired spiking neural networks (SNNs) have demonstrated great potential for temporal signal processing. However, their performance in speech processing remains limited due to the lack of an effective auditory front-end. To address this limitation, we introduce Spiking-LEAF, a learnable auditory front-end meticulously designed for SNN-based speech processing. Spiking-LEAF combines a learnable filter bank with a novel two-compartment spiking neuron model called IHC-LIF. The IHC-LIF neurons draw inspiration from the structure of inner hair cells (IHC) and they leverage segregated dendritic and somatic compartments to effectively capture multi-scale temporal dynamics of speech signals. Additionally, the IHC-LIF neurons incorporate the lateral feedback mechanism along with spike regularization loss to enhance spike encoding efficiency. On keyword spotting and speaker identification tasks, the proposed Spiking-LEAF outperforms both SOTA spiking auditory front-ends and conventional real-valued acoustic features in terms of classification accuracy, noise robustness, and encoding efficiency.

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than every detail being traversed uniformly. However, most current vision networks follow a dense paradigm, processing every single visual unit (such as pixels or patches) in a uniform manner. In this paper, we challenge this dense convention and present a new vision transformer, coined SparseFormer, to explicitly imitate human's sparse visual recognition in an end-to-end manner. SparseFormer learns to represent images using a highly limited number of tokens (e.g., down to $9$) in the latent space with sparse feature sampling procedure instead of processing dense units in the original image space. Therefore, SparseFormer circumvents most of dense operations on the image space and has much lower computational costs. Experiments on the ImageNet-1K classification show that SparseFormer delivers performance on par with canonical or well-established models while offering more favorable accuracy-throughput tradeoff. Moreover, the design of our network can be easily extended to the video classification task with promising performance with lower compute. We hope our work can provide an alternative way for visual modeling and inspire further research on sparse vision architectures. Code and weights are available at https://github.com/showlab/sparseformer.

Graphical User Interface (GUI) Automation has shown significant potential recently. Previous works built GUI Agent systems to handle short-procedure tasks such as element grounding or functional assistance. In this paper, we propose a novel PC-Copilot, AssistEditor, that focuses on automating the video editing workflow. Unlike previous approaches, our system does not require users to input specific commands to control the computer. Instead, users simply describe their requirements, such as the content and style of the video, and upload the necessary materials. The system then autonomously translates these requirements into detailed actions for controlling video understanding models and professional video editing software, e.g., Premiere Pro to produce the final video. This functionality is enabled by a collaborative AI agent framework of multiple GUI agents, each capable of dialogue, knowledge retrieval, and software usage. These agents have distinct roles, including interacting with users to gather requirements, generating storyboards, and performing editing tasks. This approach significantly streamlines the video editing process, making advanced editing accessible to users with varying levels of expertise.

We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA addresses these challenges by integrating a Sparse Dense Sampling strategy into the video-LLM, which balances temporal context and spatial detail within computational constraints. Additionally, we propose a One-Token-Seg-All approach using a specially designed <TRK> token, enabling the model to segment and track objects across multiple frames. Extensive evaluations on diverse benchmarks, including our newly introduced ReasonVOS benchmark, demonstrate VideoLISA's superior performance in video object segmentation tasks involving complex reasoning, temporal understanding, and object tracking. While optimized for videos, VideoLISA also shows promising generalization to image segmentation, revealing its potential as a unified foundation model for language-instructed object segmentation. Code and model will be available at: https://github.com/showlab/VideoLISA.

Graphical User Interface (GUI) automation holds significant promise for enhancing human productivity by assisting with computer tasks. Existing task formulations primarily focus on simple tasks that can be specified by a single, language-only instruction, such as “Insert a new slide.” In this work, we introduce VideoGUI, a novel multi-modal benchmark designed to evaluate GUI assistants on visual-centric GUI tasks. Sourced from high-quality web instructional videos, our benchmark focuses on tasks involving professional and novel software (e.g., Adobe Pho- toshop or Stable Diffusion WebUI) and complex activities (e.g., video editing). VideoGUI evaluates GUI assistants through a hierarchical process, allowing for identification of the specific levels at which they may fail: (i) high-level planning: reconstruct procedural subtasks from visual conditions without language descrip- tions; (ii) middle-level planning: generate sequences of precise action narrations based on visual state (i.e., screenshot) and goals; (iii) atomic action execution: perform specific actions such as accurately clicking designated elements. For each level, we design evaluation metrics across individual dimensions to provide clear signals, such as individual performance in clicking, dragging, typing, and scrolling for atomic action execution. Our evaluation on VideoGUI reveals that even the SoTA large multimodal model GPT4o performs poorly on visual-centric GUI tasks, especially for high-level planning. The data and code are available at https://github.com/showlab/videogui.

We introduce Exo2Ego-V, a novel exocentric-to-egocentric diffusion-based video generation method for daily-life skilled human activities where sparse 4-view exocentric viewpoints are configured 360° around the scene. This task is particularly challenging due to the significant variations between exocentric and egocentric viewpoints and high complexity of dynamic motions and real-world daily-life environments. To address these challenges, we first propose a new diffusion-based multi-view exocentric encoder to extract the dense multi-scale features from multi-view exocentric videos as the appearance conditions for egocentric video generation. Then, we design an exocentric-to-egocentric view translation prior to provide spatially aligned egocentric features as a concatenation guidance for the input of egocentric video diffusion model. Finally, we introduce the temporal attention layers into our egocentric video diffusion pipeline to improve the temporal consistency cross egocentric frames. Extensive experiments demonstrate that Exo2Ego-V significantly outperforms SOTA approaches on 5 categories from the Ego-Exo4D dataset with an average of 35% in terms of LPIPS. Our code and model will be made available on https://github.com/showlab/Exo2Ego-V.

Existing Multimodal Large Language Models (MLLMs) follow the paradigm that perceives visual information by aligning visual features with the input space of Large Language Models (LLMs) and concatenating visual tokens with text tokens to form a unified sequence input for LLMs. These methods demonstrate promising results on various vision-language tasks but are limited by the high computational effort due to the extended input sequence resulting from the involvement of visual tokens. In this paper, instead of input space alignment, we propose a novel parameter space alignment paradigm that represents visual information as model weights. For each input image, we use a vision encoder to extract visual features, convert features into perceptual weights, and merge the perceptual weights with LLM's weights. In this way, the input of LLM does not require visual tokens, which reduces the length of the input sequence and greatly improves efficiency. Following this paradigm, we propose VLoRA with the perceptual weights generator. The perceptual weights generator is designed to convert visual features to perceptual weights with low-rank property, exhibiting a form similar to LoRA. The experimental results show that our VLoRA achieves comparable performance on various benchmarks for MLLMs, while significantly reducing the computational costs for both training and inference. Code and models are released at \url{https://github.com/FeipengMa6/VLoRA}.

Training models with longer in-context lengths is a significant challenge for multimodal machine learning due to substantial GPU memory and computational costs. This exploratory study does not present state-of-the-art models; rather, it introduces an innovative method designed to increase in-context text length in multi-modality large language models (MLLMs) efficiently. We present \ModelFullName (\ModelName), which processes long in-context text using visual tokens. This technique significantly reduces GPU memory usage and floating point operations (FLOPs). For instance, our method expands the pre-training in-context length from 256 to 2048 tokens with fewer FLOPs for a 56 billion parameter MOE model. Experimental results demonstrate that \ModelName enhances OCR capabilities and delivers superior performance on common downstream benchmarks for in-context few-shot evaluation. Additionally, \ModelName proves effective for long context inference, achieving results comparable to full text input while maintaining computational efficiency.

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially in long-term, dense video frame streaming scenarios. Although learnable approaches like Q-Former and Perceiver Resampler have been developed to reduce the vision token burden, they overlook the context causally modeled by LLMs (i.e., key-value cache), potentially leading to missed visual cues when addressing user queries. In this paper, we introduce a novel approach to reduce vision compute by leveraging redundant vision tokens ``skipping layers'' rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video. Specifically, for certain transformer layer, we learn to skip the computation for a high proportion (e.g., 80\%) of vision tokens, passing them directly to the next layer. This approach significantly enhances model efficiency, achieving approximately 42% time and 30% memory savings for the entire training. Moreover, our method reduces the computation in the context and avoid decreasing the vision tokens, thus preserving or even improving performance compared to the vanilla model. We conduct extensive experiments to demonstrate the effectiveness of VideoLLM-MoD, showing its state-of-the-art results on multiple benchmarks, including narration, forecasting, and summarization tasks in COIN, Ego4D, and Ego-Exo4D datasets. The code and checkpoints will be made available at github.com/showlab/VideoLLM-online.

Federated Instruction Tuning (FIT) advances collaborative training on decentralized data, crucially enhancing model's capability and safeguarding data privacy. However, existing FIT methods are dedicated to handling data heterogeneity across different clients (i.e., client-aware data heterogeneity), while ignoring the variation between data from different domains (i.e., domain-aware data heterogeneity). When scarce data needs supplementation from related fields, these methods lack the ability to handle domain heterogeneity in cross-domain training. This leads to domain-information catastrophic forgetting in collaborative training and therefore makes model perform sub-optimally on the individual domain. To address this issue, we introduce DoFIT, a new Domain-aware FIT framework that alleviates catastrophic forgetting through two new designs. First, to reduce interference information from the other domain, DoFIT finely aggregates overlapping weights across domains on the inter-domain server side. Second, to retain more domain information, DoFIT initializes intra-domain weights by incorporating inter-domain information into a less-conflicted parameter space. Experimental results on diverse datasets consistently demonstrate that DoFIT excels in cross-domain collaborative training and exhibits significant advantages over conventional FIT methods in alleviating catastrophic forgetting. Code is available at [this link](https://github.com/1xbq1/DoFIT).

Digital watermarking techniques are crucial for copyright protection and source identification of images, especially in the era of generative AI models. However, many existing watermarking methods, particularly content-agnostic approaches that embed fixed patterns regardless of image content, are vulnerable to steganalysis attacks that can extract and remove the watermark with minimal perceptual distortion. In this work, we categorise watermarking algorithms into content-adaptive and content-agnostic ones, and demonstrate how averaging a collection of watermarked images could reveal the underlying watermark pattern. We then leverage this extracted pattern for effective watermark removal under both greybox and blackbox settings, even when the collection of images contains multiple watermark patterns. For some algorithms like Tree-Ring watermarks, the extracted pattern can also forge convincing watermarks on clean images. Our quantitative and qualitative evaluations across twelve watermarking methods highlight the threat posed by steganalysis to content-agnostic watermarks and the importance of designing watermarking techniques resilient to such analytical attacks. We propose security guidelines calling for using content-adaptive watermarking strategies and performing security evaluation against steganalysis. We also suggest multi-key assignments as potential mitigations against steganalysis vulnerabilities. Github page: \url{https://github.com/showlab/watermark-steganalysis}.

Capturing and maintaining geometric interactions among different body parts is crucial for successful motion retargeting in skinned characters. Existing approaches often overlook body geometries or add a geometry correction stage after skeletal motion retargeting. This results in conflicts between skeleton interaction and geometry correction, leading to issues such as jittery, interpenetration, and contact mismatches. To address these challenges, we introduce a new retargeting framework, MeshRet, which directly models the dense geometric interactions in motion retargeting. Initially, we establish dense mesh correspondences between characters using semantically consistent sensors (SCS), effective across diverse mesh topologies. Subsequently, we develop a novel spatio-temporal representation called the dense mesh interaction (DMI) field. This field, a collection of interacting SCS feature vectors, skillfully captures both contact and non-contact interactions between body geometries. By aligning the DMI field during retargeting, MeshRet not only preserves motion semantics but also prevents self-interpenetration and ensures contact preservation. Extensive experiments on the public Mixamo dataset and our newly-collected ScanRet dataset demonstrate that MeshRet achieves state-of-the-art performance. Code available at https://github.com/abcyzj/MeshRet.

Question answering, asking, and assessment are three innate human traits crucial for understanding the world and acquiring knowledge. By enhancing these capabilities, humans can more effectively utilize data, leading to better comprehension and learning outcomes. However, current Multimodal Large Language Models (MLLMs) primarily focus on question answering, often neglecting the full potential of questioning and assessment skills. In this study, we introduce LOVA3, an innovative framework named ``Learning tO Visual Question Answering, Asking and Assessment,'' designed to equip MLLMs with these additional capabilities. Our approach involves the creation of two supplementary training tasks GenQA and EvalQA, aiming at fostering the skills of asking and assessing questions in the context of images. To develop the questioning ability, we compile a comprehensive set of multimodal foundational tasks. For assessment, we introduce a new benchmark called EvalQABench, comprising 64,000 training samples (split evenly between positive and negative samples) and 5,000 testing samples. We posit that enhancing MLLMs with the capabilities to answer, ask, and assess questions will enhance their multimodal comprehension, ultimately improving overall performance. To validate this hypothesis, we train MLLMs using the LOVA3 framework and evaluate them on a range of multimodal datasets and benchmarks. Our results demonstrate consistent performance gains, underscoring the critical role of these additional tasks in fostering comprehensive intelligence in MLLMs.

Recent advancements in generation models have showcased remarkable capabilities in generating fantastic content. However, most of them are trained on proprietary high-quality data, and some models withhold their parameters and only provide accessible application programming interfaces (APIs), limiting their benefits for downstream tasks. To explore the feasibility of training a text-to-image generation model comparable to advanced models using publicly available resources, we introduce EvolveDirector. This framework interacts with advanced models through their public APIs to obtain text-image data pairs to train a base model. Our experiments with extensive data indicate that the model trained on generated data of the advanced model can approximate its generation capability. However, it requires large-scale samples of 10 million or more. This incurs significant expenses in time, computational resources, and especially the costs associated with calling fee-based APIs. To address this problem, we leverage pre-trained large vision-language models (VLMs) to guide the evolution of the base model. VLM continuously evaluates the base model during training and dynamically updates and refines the training dataset by the discrimination, expansion, deletion, and mutation operations. Experimental results show that this paradigm significantly reduces the required data volume. Furthermore, when approaching multiple advanced models, EvolveDirector can select the best samples generated by them to learn powerful and balanced abilities. The final trained model Edgen is demonstrated to outperform these advanced models. The code and model weights are available at https://github.com/showlab/EvolveDirector.

Vision-Language Pre-Training (VLP) has demonstrated remarkable potential in aligning image and text pairs, paving the way for a wide range of cross-modal learning tasks. Nevertheless, we have observed that VLP models often fall short in terms of visual grounding and localization capabilities, which are crucial for many downstream tasks, such as visual reasoning. In response, we introduce a novel Position-guided Text Prompt (PTP) paradigm to bolster the visual grounding abilities of cross-modal models trained with VLP. In the VLP phase, PTP divides an image into N x N blocks and employs a widely-used object detector to identify objects within each block. PTP then reframes the visual grounding task as a fill-in-the-blank problem, encouraging the model to predict objects in given blocks or regress the blocks of a given object, exemplified by filling "[P]" or "[O]" in a PTP sentence such as "The block [P] has a [O]." This strategy enhances the visual grounding capabilities of VLP models, enabling them to better tackle various downstream tasks. Additionally, we integrate the seconda-order relationships between objects to further enhance the visual grounding capabilities of our proposed PTP paradigm. Incorporating PTP into several state-of-the-art VLP frameworks leads to consistently significant improvements across representative cross-modal learning model architectures and multiple benchmarks, such as zero-shot Flickr30 k Retrieval (+5.6 in average recall@1) for ViLT baseline, and COCO Captioning (+5.5 in CIDEr) for the state-of-the-art BLIP baseline. Furthermore, PTP attains comparable results with object-detector-based methods and a faster inference speed, as it discards its object detector during inference, unlike other approaches.

Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually. In this paper, we propose a simple, yet effective Continual Image Segmentation method with incremental Dynamic Query (CISDQ), which decouples the representation learning of both old and new knowledge with lightweight query embedding. CISDQ mainly includes three contributions: 1) We definedynamic querieswith adaptive background class to exploit past knowledge and learn future classes naturally. 2) CISDQ proposes a class/instance-aware Query Guided Knowledge Distillation strategy to overcome catastrophic forgetting by capturing the inter-class diversity and intra-class identity. 3) Apart from semantic segmentation, CISDQ introduce the continual learning forinstance segmentationin which instance-wise labeling and supervision are considered. Extensive experiments on three datasets for two tasks (i.e. continual semantic and instance segmentation are conducted to demonstrate that CISDQ achieves the state-of-the-art performance, specifically, obtaining 4.4% and 2.9% mIoU improvements for the ADE 100-10 (6 steps) setting and ADE 100-5 (11 steps) setting.

In the metaverse the physical space and the virtual space co-exist, and interact simultaneously. While the physical space is virtually enhanced with information, the virtual space is continuously refreshed with real-time, real-world information. To allow users to process and manipulate information seamlessly between the real and digital spaces, novel technologies must be developed. These include smart interfaces, new augmented realities, and efficient data storage, management, and dissemination techniques. In this paper, we first discuss some promising co-space applications. These applications offer opportunities that neither of the spaces can realize on its own. Then, we further discuss several emerging technologies that empower the construction of metaverse. After that, we discuss comprehensively the data centric challenges. Finally, we discuss and envision what are likely to be required from the database and system perspectives.

Learning discriminative and robust representations is important for facial expression recognition (FER) due to subtly different emotional faces and their subjective annotations. Previous works usually address one representation solely because these two goals seem to be contradictory for optimization. Their performances inevitably suffer from challenges from the other representation. In this article, by considering this problem from two novel perspectives, we demonstrate that discriminative and robust representations can be learned in a unified approach, i.e., DR-FER, and mutually benefit each other. Moreover, we make it with the supervision from only original annotations. Specifically, to learn discriminative representations, we propose performing masked image modeling (MIM) as an auxiliary task to force our network to discover expression-related facial areas. This is the first attempt to employ MIM to explore discriminative patterns in a self-supervised manner. To extract robust representations, we present a category-aware self-paced learning schedule to mine high-quality annotated (easy) expressions and incorrectly annotated (hard) counterparts. We further introduce a retrieval similarity-based relabeling strategy to correct hard expression annotations, exploiting them more effectively. By enhancing the discrimination ability of the FER classifier as a bridge, these two learning goals significantly strengthen each other. Extensive experiments on several popular benchmarks demonstrate the superior performance of our DR-FER. Moreover, thorough visualizations and extra experiments on manually annotation-corrupted datasets show that our approach successfully accomplishes learning both discriminative and robust representations simultaneously.

VQA is an ambitious task aiming to answer any image-related question. However, in reality, it is hard to build such a system once for all since the needs of users are continuously updated, and the system has to implement new functions. Thus, Continual Learning (CL) ability is a must in developing advanced VQA systems. Recently, a pioneer work split a VQA dataset into disjoint answer sets to study this topic. However, CL on VQA involves not only the expansion of label sets (new Answer sets). It is crucial to study how to answer questions when deploying VQA systems to new environments (new Visual scenes) and how to answer questions requiring new functions (new Question types). Thus, we propose CLOVE, a benchmark for Continual Learning On Visual quEstion answering, which contains scene- and function-incremental settings for the two aforementioned CL scenarios. In terms of methodology, the main difference between CL on VQA and classification is that the former additionally involves expanding and preventing forgetting of reasoning mechanisms, while the latter focusing on class representation. Thus, we propose a real-data-free replay-based method tailored for CL on VQA, named Scene Graph as Prompt for Symbolic Replay. Using a piece of scene graph as a prompt, it replays pseudo scene graphs to represent the past images, along with correlated QA pairs. A unified VQA model is also proposed to utilize the current and replayed data to enhance its QA ability. Finally, experimental results reveal challenges in CLOVE and demonstrate the effectiveness of our method. Code and data are available at https://github.com/showlab/CLVQA.

Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account the structure of objects during pre-training on large-scale video-text pairs. Given a video, our module (1) first quantizes continuous visual features via clustering patch-features into the same cluster according to content similarity, then (2) generates learnable masks to aggregate fragmentary features into regions with complete semantics, and finally (3) models the spatio-temporal dependencies between different semantic regions. In contrast to using off-the-shelf object detectors, our proposed module does not require explicit supervision and is much more computationally efficient. We pre-train the proposed approach on the public WebVid2M and CC3M datasets. Extensive evaluations on four downstream video-text retrieval benchmarks clearly demonstrate the effectiveness of our RegionLearner.

The traditional model upgrading paradigm for retrieval requires recomputing all gallery embeddings before deploying the new model (dubbed as "backfilling"), which is quite expensive and time-consuming considering billions of instances in industrial applications. BCT presents the first step towards backward-compatible model upgrades to get rid of backfilling. It is workable but leaves the new model in a dilemma between new feature discriminativeness and new-to-old compatibility due to the undifferentiated compatibility constraints. In this work, we propose Darwinian Model Upgrades (DMU), which disentangle the inheritance and variation in the model evolving with selective backward compatibility and forward adaptation, respectively. The old-to-new heritable knowledge is measured by old feature discriminativeness, and the gallery features, especially those of poor quality, are evolved in a lightweight manner to become more adaptive in the new latent space. We demonstrate the superiority of DMU through comprehensive experiments on large-scale landmark retrieval and face recognition benchmarks. DMU effectively alleviates the new-to-new degradation at the same time improving new-to-old compatibility, rendering a more proper model upgrading paradigm in large-scale retrieval systems.Code: https://github.com/TencentARC/OpenCompatible.

Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, W.k. Chan, Chong-Wah Ngo, Mike Zheng Shou, Nan Duan. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Multi-channel video-language retrieval require models to understand information from different channels (e.g. video+question, video+speech) to correctly link a video with a textual response or query. Fortunately, contrastive multimodal models are shown to be highly effective at aligning entities in images/videos and text, e.g., CLIP [20]; text contrastive models are extensively studied recently for their strong ability of producing discriminative sentence embeddings, e.g., SimCSE [5]. However, there is not a clear way to quickly adapt these two lines to multi-channel video-language retrieval with limited data and resources. In this paper, we identify a principled model design space with two axes: how to represent videos and how to fuse video and text information. Based on categorization of recent methods, we investigate the options of representing videos using continuous feature vectors or discrete text tokens; for the fusion method, we explore the use of a multimodal transformer or a pretrained contrastive text model. We extensively evaluate the four combinations on five video-language datasets. We surprisingly find that discrete text tokens coupled with a pretrained contrastive text model yields the best performance, which can even outperform state-of-the-art on the iVQA and How2QA datasets without additional training on millions of video-text data. Further analysis shows that this is because representing videos as text tokens captures the key visual information and text tokens are naturally aligned with text models that are strong retrievers after the contrastive pretraining process. All the empirical analysis establishes a solid foundation for future research on affordable and upgradable multimodal intelligence.

The quadratic computational complexity to the number of tokens limits the practical applications of Vision Transformers (ViTs). Several works propose to prune redundant tokens to achieve efficient ViTs. However, these methods generally suffer from (i) dramatic accuracy drops, (ii) application difficulty in the local vision transformer, and (iii) non-general-purpose networks for downstream tasks. In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks. The semantic tokens represent cluster centers, and they are initialized by pooling image tokens in space and recovered by attention, which can adaptively represent global or local semantic information. Due to the cluster properties, a few semantic tokens can attain the same effect as vast image tokens, for both global and local vision transformers. For instance, only 16 semantic tokens on DeiT-(Tiny,Small,Base) can achieve the same accuracy with more than 100% inference speed improvement and nearly 60% FLOPs reduction; on Swin-(Tiny,Small,Base), we can employ 16 semantic tokens in each window to further speed it up by around 20% with slight accuracy increase. Besides great success in image classification, we also extend our method to video recognition. In addition, we design a STViT-R(ecovery) network to restore the detailed spatial information based on the STViT, making it work for downstream tasks, which is powerless for previous token sparsification methods. Experiments demonstrate that our method can achieve competitive results compared to the original networks in object detection and instance segmentation, with over 30% FLOPs reduction for backbone.

Humans excel at learning from expert demonstrations and solving their own problems. To equip intelligent robots and assistants, such as AR glasses, with this ability, it is essential to ground human hand interactions (i.e., affordances) from demonstration videos and apply them to a target image like a user's AR glass view. This video-to-image affordance grounding task is challenging due to (1) the need to predict fine-grained affordances, and (2) the limited training data, which inadequately covers video-image discrepancies and negatively impacts grounding. To tackle them, we propose Affordance Transformer (Afformer), which has a fine-grained transformer-based decoder that gradually refines affordance grounding. Moreover, we introduce Mask Affordance Hand (MaskAHand), a self-supervised pre-training technique for synthesizing video-image data and simulating context changes, enhancing affordance grounding across video-image discrepancies. Afformer with MaskAHand pre-training achieves state-of-the-art performance on multiple benchmarks, including a sub-stantial 37% improvement on the OPRA dataset. Code is made available at https://github.com/showlab/afformer.

To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising performance on images or short video clips, especially with the recent success of large-scale multi-modal pre-training. However, when extending these methods to long-form videos, new challenges arise. On the one hand, using a dense video sampling strategy is computationally prohibitive. On the other hand, methods relying on sparse sampling struggle in scenarios where multi-event and multi-granularity visual reasoning are required. In this work, we introduce a new model named$\mathcal{M}ulti{-}$· modal Iterative$\mathcal{S}$.patial-temporal Transformer$(\mathcal{MIST})$) to better adapt pre-trained models for long-form VideoQA. Specifically,$\mathcal{MIST}$decomposes traditional dense spatial-temporal self-attention into cascaded segment and region selection modules that adaptively select frames and image regions that are closely relevant to the question itself. Visual concepts at different granularities are then processed efficiently through an attention module. In addition,$\mathcal{MIST}$iteratively conducts selection and attention over multiple layers to support reasoning over multiple events. The experimental results on four VideoQA datasets, including AGQA, NExT-QA, STAR, and Env-QA, show that$\mathcal{MIST}$achieves state-of-the-art performance and is superior at efficiency. The code is available at github.com/showlab/mist.

Mainstream Video-Language Pre-training (VLP) models [10, 26, 64] consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end VLP model, namely all-in-one Transformer, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified model. Our pretrained ali-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and video captioning. State-of-the-art performances with the minimal model FLOPs on ten datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained models are available at https://github.com/showlab/all-in-one.

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N x N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling “[P]” or “[O]” in a PTP “The block [P] has a [O]”. This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT [16] baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP [19] baseline. Moreover, PTP achieves comparable results with object-detector based methods [8, 23, 45], and much faster inference speed since PTP discards its object detector for inference while the later cannot.

The usage of exocentric and egocentric videos in Video Question Answering (VQA) is a new endeavor in human-robot interaction and collaboration studies.Particularly for egocentric videos, one may leverage eye-gaze information to understand human intentions during the task.In this paper, we build a novel task-oriented VQA dataset, called GazeVQA, for collaborative tasks where gaze information is captured during the task process.GazeVQA is designed with a novel QA format that covers thirteen different reasoning types to capture multiple aspects of task information and user intent.For each participant, GazeVQA consists of more than 1,100 textual questions and more than 500 labeled images that were annotated with the assistance of the Segment Anything Model.In total, 2,967 video clips, 12,491 labeled images, and 25,040 questions from 22 participants were included in the dataset.Additionally, inspired by the assisting models and common ground theory for industrial task collaboration, we propose a new AI model called AssistGaze that is designed to answer the questions with three different answer types, namely textual, image, and video.AssistGaze can effectively ground the perceptual input into semantic information while reducing ambiguities.We conduct comprehensive experiments to demonstrate the challenges of GazeVQA 1 and the effectiveness of AssistGaze 2 .

Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths. Specifically, we equivalently transform the traditional cascade of multi-head self-attention (MSA) and feed-forward network (FFN) into three parallel paths in each transformer layer. Then, we utilize the identity connection in our new transformer form and further transform the ViT into an explicit multi-path ensemble network. From the new perspective, these paths perform two functions: the first is to provide the feature for the classifier directly, and the second is to provide the lower-level feature representation for subsequent longer paths. We investigate the influence of each path for the final prediction and discover that some paths even pull down the performance. Therefore, we propose the path pruning and EnsembleScale skills for improvement, which cut out the underperforming paths and reweight the ensemble components, respectively, to optimize the path combination and make the short paths focus on providing high-quality representation for subsequent paths. We also demonstrate that our path combination strategies can help ViTs go deeper and act as high-pass filters to filter out partial low-frequency signals. To further enhance the representation of paths served for subsequent paths, self-distillation is applied to transfer knowledge from the long paths to the short paths. This work calls for more future research to explain and design ViTs from new perspectives.

In this paper, we show that recent advances in video representation learning and pre-trained vision-language models allow for substantial improvements in self-supervised video object localization. We propose a method that first localizes objects in videos via a slot attention approach and then assigns text to the obtained slots. The latter is achieved by an unsupervised way to read localized semantic information from the pre-trained CLIP model. The resulting video object localization is entirely unsupervised apart from the implicit annotation contained in CLIP, and it is effectively the first unsupervised approach that yields good results on regular video benchmarks.

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Second, they are vulnerable to practical attacking scenarios where attackers probe for privacy from an entire video rather than individual frames. To address these issues, we propose a novel framework STPrivacy to perform video-level PPAR. For the first time, we introduce vision Transformers into PPAR by treating a video as a tubelet sequence, and accordingly design two complementary mechanisms, i.e., sparsification and anonymization, to remove privacy from a spatio-temporal perspective. In specific, our privacy sparsification mechanism applies adaptive token selection to abandon action-irrelevant tubelets. Then, our anonymization mechanism implicitly manipulates the remaining action-tubelets to erase privacy in the embedding space through adversarial learning. These mechanisms provide significant advantages in terms of privacy preservation for human eyes and action-privacy trade-off adjustment during deployment. We additionally contribute the first two large-scale PPAR benchmarks, VP-HMDB51 and VP-UCF101, to the community. Extensive evaluations on them, as well as two other tasks, validate the effectiveness and generalization capability of our framework.

Video Temporal Grounding (VTG), which aims to ground target clips from videos (such as consecutive intervals or disjoint shots) according to custom language queries (e.g., sentences or words), is key for video browsing on social media. Most methods in this direction develop task-specific models that are trained with type-specific labels, such as moment retrieval (time interval) and highlight detection (worthiness curve), which limits their abilities to generalize to various VTG tasks and labels. In this paper, we propose to Unify the diverse VTG labels and tasks, dubbed UniVTG, along three directions: Firstly, we revisit a wide range of VTG labels and tasks and define a unified formulation. Based on this, we develop data annotation schemes to create scalable pseudo supervision. Secondly, we develop an effective and flexible grounding model capable of addressing each task and making full use of each label. Lastly, thanks to the unified framework, we are able to unlock temporal grounding pretraining from large-scale diverse labels and develop stronger grounding abilities e.g., zero-shot grounding. Extensive experiments on three tasks (moment retrieval, highlight detection and video summarization) across seven datasets (QVHighlights, Charades-STA, TACoS, Ego4D, YouTube Highlights, TVSum, and QFVS) demonstrate the effectiveness and flexibility of our proposed framework. The codes are available at https://github.com/showlab/UniVTG.

We introduce HOSNeRF, a novel 360° free-viewpoint rendering method that reconstructs neural radiance fields for dynamic human-object-scene from a single monocular in-the-wild video. Our method enables pausing the video at any frame and rendering all scene details (dynamic humans, objects, and backgrounds) from arbitrary viewpoints. The first challenge in this task is the complex object motions in human-object interactions, which we tackle by introducing the new object bones into the conventional human skeleton hierarchy to effectively estimate large object deformations in our dynamic human-object model. The second challenge is that humans interact with different objects at different times, for which we introduce two new learnable object state embeddings that can be used as conditions for learning our human-object representation and scene representation, respectively. Extensive experiments show that HOSNeRF significantly outperforms SOTA approaches on two challenging datasets by a large margin of 40%~50% in terms of LPIPS. The code, data, and compelling examples of 360° free-viewpoint renderings from single videos: https://showlab.github.io/HOSNeRF.

Video-language pre-training (VLP) has become increasingly important due to its ability to generalize to various vision and language tasks. However, existing egocentric VLP frameworks utilize separate video and language encoders and learn task-specific cross-modal information only during fine-tuning, limiting the development of a unified system. In this work, we introduce the second generation of egocentric video-language pre-training (EgoVLPv2), a significant improvement from the previous generation, by incorporating cross-modal fusion directly into the video and language backbones. EgoVLPv2 learns strong video-text representation during pre-training and reuses the cross-modal attention modules to support different downstream tasks in a flexible and efficient manner, reducing fine-tuning costs. Moreover, our proposed fusion in the backbone strategy is more lightweight and compute-efficient than stacking additional fusion-specific layers. Extensive experiments on a wide range of VL tasks demonstrate the effectiveness of EgoVLPv2 by achieving consistent state-of-the-art performance over strong baselines across all downstream. Our project page can be found at https://shramanpramanick.github.io/EgoVLPv2/.

Curriculum design is a fundamental component of education. For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication. These and other concepts must be mastered before our first algebra lesson, which also reinforces our addition and multiplication skills. Designing a curriculum for teaching either a human or a machine shares the underlying goal of maximizing knowledge transfer from earlier to later tasks, while also minimizing forgetting of learned tasks. Prior research on curriculum design for image classification focuses on the ordering of training examples during a single offline task. Here, we investigate the effect of the order in which multiple distinct tasks are learned in a sequence. We focus on the online class-incremental continual learning setting, where algorithms or humans must learn image classes one at a time during a single pass through a dataset. We find that curriculum consistently influences learning outcomes for humans and for multiple continual machine learning algorithms across several benchmark datasets. We introduce a novel-object recognition dataset for human curriculum learning experiments and observe that curricula that are effective for humans are highly correlated with those that are effective for machines. As an initial step towards automated curriculum design for online class-incremental learning, we propose a novel algorithm, dubbed Curriculum Designer (CD), that designs and ranks curricula based on inter-class feature similarities. We find significant overlap between curricula that are empirically highly effective and those that are highly ranked by our CD. Our study establishes a framework for further research on teaching humans and machines to learn continuously using optimized curricula. Our code and data are available through this link.

This paper examines the problems of severe image-text misalignment and high redundancy in the widely-used large-scale Vision-Language Pre-Training (VLP) datasets. To address these issues, we propose an efficient and straightforward Vision-Language learning algorithm called ${\color {Purple}{TL;DR}}$, which aims to compress the existing large VLP data into a small, high-quality set. Our approach consists of two major steps. First, a codebook-based encoder-decoder captioner is developed to select representative samples. Second, a new caption is generated to complement the original captions for selected samples, mitigating the text-image misalignment problem while maintaining uniqueness. As the result, ${\color {Purple}{TL;DR}}$ enables us to reduce the large dataset into a small set of high-quality data, which can serve as an alternative pre-training dataset. This algorithm significantly speeds up the time-consuming pretraining process. Specifically, ${\color {Purple}{TL;DR}}$ can compress the mainstream VLP datasets at a high ratio, e.g., reduce well-cleaned CC3M dataset from 2.82M to 0.67M (~24%) and noisy YFCC15M from 15M to 2.5M (~16.7%). Extensive experiments with three popular VLP models over seven downstream tasks show that VLP model trained on the compressed dataset provided by ${\color {Purple}{TL;DR}}$ can perform similar or even better results compared with training on the full-scale dataset1.

To replicate the success of text-to-image (T2I) generation, recent works employ large-scale video datasets to train a text-to-video (T2V) generator. Despite their promising results, such paradigm is computationally expensive. In this work, we propose a new T2V generation setting—One-Shot Video Tuning, where only one text-video pair is presented. Our model is built on state-of-the-art T2I diffusion models pre-trained on massive image data. We make two key observations: 1) T2I models can generate still images that represent verb terms; 2) extending T2I models to generate multiple images concurrently exhibits surprisingly good content consistency. To further learn continuous motion, we introduce Tune-A-Video, which involves a tailored spatio-temporal attention mechanism and an efficient one-shot tuning strategy. At inference, we employ DDIM inversion to provide structure guidance for sampling. Extensive qualitative and numerical experiments demonstrate the remarkable ability of our method across various applications.

Humans can watch a continuous video stream and effortlessly perform continual acquisition and transfer of new knowledge with minimal supervision yet retaining previously learnt experiences. In contrast, existing continual learning (CL) methods require fully annotated labels to effectively learn from individual frames in a video stream. Here, we examine a more realistic and challenging problem—Label-Efficient Online Continual Object Detection (LEOCOD) in streaming video. We propose a plug-and-play module, Efficient-CLS, that can be easily inserted into and consistently improve existing CL algorithms for object detection in video streams with reduced data annotation costs and model retraining time. We show that our method has achieved significant improvement with minimal forgetting across all supervision levels on two challenging CL benchmarks for streaming real-world videos. Remarkably, with only 25% annotated video frames, our proposed method still outperforms the state-of-the-art CL models trained with 100% annotations on all video frames. The data and source code will be publicly available at https://github.com/showlab/Efficient-CLS.

Collecting and annotating images with pixel-wise labels is time-consuming and laborious. In contrast, synthetic data can be freely available using a generative model (e.g., DALL-E, Stable Diffusion). In this paper, we show that it is possible to automatically obtain accurate semantic masks of synthetic images generated by the Off-the-shelf Stable Diffusion model, which uses only text-image pairs during training. Our approach, termed DiffuMask, exploits the potential of the cross-attention map between text and image, which is natural and seamless to extend the text-driven image synthesis to semantic mask generation. DiffuMask uses text-guided cross-attention information to localize class/word-specific regions, which are combined with practical techniques to create a novel high-resolution and class-discriminative pixel-wise mask. The methods help to significantly reduce data collection and annotation costs. Experiments demonstrate that the existing segmentation methods trained on synthetic data of DiffuMask can achieve a competitive performance over the counterpart of real data (VOC 2012, Cityscapes). For some classes (e.g., bird), DiffuMask presents promising performance, close to the state-of-the-art result of real data (within 3% mIoU gap). Moreover, in the open-vocabulary segmentation (zero-shot) setting, DiffuMask achieves new state-of-the-art results on the Unseen classes of VOC 2012. The project website can be found at ${\color{red}{\text{DiffuMask}}}$.

Recent text-to-image diffusion models have demonstrated an astonishing capacity to generate high-quality images. However, researchers mainly studied the way of synthesizing images with only text prompts. While some works have explored using other modalities as conditions, considerable paired data, e.g., box/mask-image pairs, and fine-tuning time are required for nurturing models. As such paired data is time-consuming and labor-intensive to acquire and restricted to a closed set, this potentially becomes the bottleneck for applications in an open world. This paper focuses on the simplest form of user-provided conditions, e.g., box or scribble. To mitigate the aforementioned problem, we propose a training-free method to control objects and contexts in the synthesized images adhering to the given spatial conditions. Specifically, three spatial constraints, i.e., Inner-Box, Outer-Box, and Corner Constraints, are designed and seamlessly integrated into the denoising step of diffusion models, requiring no additional training and massive annotated layout data. Extensive experimental results demonstrate that the proposed constraints can control what and where to present in the images while retaining the ability of Diffusion models to synthesize with high fidelity and diverse concept coverage.

In the metaverse the physical space and the virtual space co-exist, and interact simultaneously. While the physical space is virtually enhanced with information, the virtual space is continuously refreshed with real-time, real-world information. To allow users to process and manipulate information seamlessly between the real and digital spaces, novel technologies must be developed. These include smart interfaces, new augmented realities, and efficient data storage, management, and dissemination techniques. In this paper, we first discuss some promising co-space applications. These applications offer opportunities that neither of the spaces can realize on its own. We then discuss challenges. Finally, we discuss and envision what are likely to be required from the database and system perspectives.

Open-World Instance Segmentation (OWIS) is an emerging research topic that aims to segment class-agnostic object instances from images. The mainstream approaches use a two-stage segmentation framework, which first locates the candidate object bounding boxes and then performs instance segmentation. In this work, we instead promote a single-stage transformer-based framework for OWIS. We argue that the end-to-end training process in the single-stage framework can be more convenient for directly regularizing the localization of class-agnostic object pixels. Based on the transformer-based instance segmentation framework, we propose a regularization model to predict foreground pixels and use its relation to instance segmentation to construct a cross-task consistency loss. We show that such a consistency loss could alleviate the problem of incomplete instance annotation - a common problem in the existing OWIS datasets. We also show that the proposed loss lends itself to an effective solution to semi-supervised OWIS that could be considered an extreme case that all object annotations are absent for some images. Our extensive experiments demonstrate that the proposed method achieves impressive results in both fully-supervised and semi-supervised settings. Compared to SOTA methods, the proposed method significantly improves the AP_100 score by 4.75% in UVO dataset →UVO dataset setting and 4.05% in COCO dataset →UVO dataset setting.

Public large-scale text-to-image diffusion models, such as Stable Diffusion, have gained significant attention from the community. These models can be easily customized for new concepts using low-rank adaptations (LoRAs). However, the utilization of multiple-concept LoRAs to jointly support multiple customized concepts presents a challenge. We refer to this scenario as decentralized multi-concept customization, which involves single-client concept tuning and center-node concept fusion. In this paper, we propose a new framework called Mix-of-Show that addresses the challenges of decentralized multi-concept customization, including concept conflicts resulting from existing single-client LoRA tuning and identity loss during model fusion. Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-client tuning and gradient fusion for the center node to preserve the in-domain essence of single concepts and support theoretically limitless concept fusion. Additionally, we introduce regionally controllable sampling, which extends spatially controllable sampling (e.g., ControlNet and T2I-Adapter) to address attribute binding and missing object problems in multi-concept sampling. Extensive experiments demonstrate that Mix-of-Show is capable of composing multiple customized concepts with high fidelity, including characters, objects, and scenes.

Learning object-centric representations from complex natural environments enables both humans and machines with reasoning abilities from low-level perceptual features. To capture compositional entities of the scene, we proposed cyclic walks between perceptual features extracted from vision transformers and object entities. First, a slot-attention module interfaces with these perceptual features and produces a finite set of slot representations. These slots can bind to any object entities in the scene via inter-slot competitions for attention. Next, we establish entity-feature correspondence with cyclic walks along high transition probability based on the pairwise similarity between perceptual features (aka "parts") and slot-binded object representations (aka "whole"). The whole is greater than its parts and the parts constitute the whole. The part-whole interactions form cycle consistencies, as supervisory signals, to train the slot-attention module. Our rigorous experiments on \textit{seven} image datasets in \textit{three} \textit{unsupervised} tasks demonstrate that the networks trained with our cyclic walks can disentangle foregrounds and backgrounds, discover objects, and segment semantic objects in complex scenes. In contrast to object-centric models attached with a decoder for the pixel-level or feature-level reconstructions, our cyclic walks provide strong learning signals, avoiding computation overheads and enhancing memory efficiency. Our source code and data are available at: \href{https://github.com/ZhangLab-DeepNeuroCogLab/Parts-Whole-Object-Centric-Learning/}{link}.

Current deep networks are very data-hungry and benefit from training on large-scale datasets, which are often time-consuming to collect and annotate. By contrast, synthetic data can be generated infinitely using generative models such as DALL-E and diffusion models, with minimal effort and cost. In this paper, we present DatasetDM, a generic dataset generation model that can produce diverse synthetic images and the corresponding high-quality perception annotations (e.g., segmentation masks, and depth). Our method builds upon the pre-trained diffusion model and extends text-guided image synthesis to perception data generation. We show that the rich latent code of the diffusion model can be effectively decoded as accurate perception annotations using a decoder module. Training the decoder only needs less than 1% (around 100 images) of manually labeled images, enabling the generation of an infinitely large annotated dataset. Then these synthetic data can be used for training various perception models on downstream tasks. To showcase the power of the proposed approach, we generate datasets with rich dense pixel-wise labels for a wide range of downstream tasks, including semantic15 segmentation, instance segmentation, and depth estimation. Notably, it achieves 1) state-of-the-art results on semantic segmentation and instance segmentation; 2) significantly more efficient and robust in domain generalization than the real data; 3) state-of-the-art results in zero-shot segmentation setting; and 4) flexibility for efficient application and novel task composition (e.g., image editing)

Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts many vision tasks. For example, in conditional image synthesis, spatial conditions failing to adhere to the prior can result in visually inaccurate synthetic results. This work aims to explicitly learn the visual prior and enable the customization of sampling. Inspired by advances in language modeling, we propose to learn Visual prior via Generative Pre-Training, dubbed VisorGPT. By discretizing visual locations, e.g., bounding boxes, human pose, and instance masks, into sequences, VisorGPT can model visual prior through likelihood maximization. Besides, prompt engineering is investigated to unify various visual locations and enable customized sampling of sequential outputs from the learned prior. Experimental results demonstrate the effectiveness of VisorGPT in modeling visual prior and extrapolating to novel scenes, potentially motivating that discrete visual locations can be integrated into the learning paradigm of current language models to further perceive visual world. Code is available at https://sierkinhane.github.io/visor-gpt.

Recent advances in 3D-aware GAN models have enabled the generation of realistic and controllable human body images. However, existing methods focus on the control of major body joints, neglecting the manipulation of expressive attributes, such as facial expressions, jaw poses, hand poses, and so on. In this work, we present XAGen, the first 3D generative model for human avatars capable of expressive control over body, face, and hands. To enhance the fidelity of small-scale regions like face and hands, we devise a multi-scale and multi-part 3D representation that models fine details. Based on this representation, we propose a multi-part rendering technique that disentangles the synthesis of body, face, and hands to ease model training and enhance geometric quality. Furthermore, we design multi-part discriminators that evaluate the quality of the generated avatars with respect to their appearance and fine-grained control capabilities. Experiments show that XAGen surpasses state-of-the-art methods in terms of realism, diversity, and expressive control abilities. Code and data will be made available at https://showlab.github.io/xagen.

Early activity prediction/recognition aims to recognize action categories before they are fully conveyed. Compared to full-length action sequences, partial video sequences only provide insufficient discrimination information, which makes predicting the class labels for some similar activities challenging, especially when only very few frames can be observed. To address this challenge, in this paper, we propose a novel meta negative network, namely, Magi-Net, that utilizes a contrastive learning scheme to alleviate the insufficiency of discriminative information. In our Magi-Net model, the positive samples are generated by augmenting an input anchor conditioned on all observation ratios, while the negative samples are selected from a trainable negative look-up memory (LUM) table, which stores the training samples and the corresponding misleading categories. Furthermore, a meta negative sample optimization strategy (MetaSOS) is proposed to boost the training of Magi-Net by encouraging the model to learn from the most informative negative samples via a meta learning scheme. Extensive experiments are conducted on several public skeleton-based activity datasets, and the results show the efficacy of the proposed Magi-Net model.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

As an important area in computer vision, object tracking has formed two separate communities that respectively study Single Object Tracking (SOT) and Multiple Object Tracking (MOT). However, current methods in one tracking scenario are not easily adapted to the other due to the divergent training datasets and tracking objects of both tasks. Although UniTrack [45] demonstrates that a shared appearance model with multiple heads can be used to tackle individual tracking tasks, it fails to exploit the large-scale tracking datasets for training and performs poorly on the single object tracking. In this work, we present the Unified Transformer Tracker (UTT) to address tracking problems in different scenarios with one paradigm. A track transformer is developed in our UTT to track the target in both SOT and MOT where the correlation between the target feature and the tracking frame feature is exploited to localize the target. We demonstrate that both SOT and MOT tasks can be solved within this framework, and the model can be simultaneously end-to-end trained by alternatively optimizing the SOT and MOT objectives on the datasets of individual tasks. Extensive experiments are conducted on several benchmarks with a unified model trained on both SOT and MOT datasets.

Recently, by introducing large-scale dataset and strong transformer network, video-language pre-training has shown great success especially for retrieval. Yet, existing video-language transformer models do not explicitly fine-grained semantic align. In this work, we present Object-aware Transformers, an object-centric approach that extends video-language transformer to incorporate object representations. The key idea is to leverage the bounding boxes and object tags to guide the training process. We evaluate our model on three standard sub-tasks of video-text matching on four widely used benchmarks. We also provide deep analysis and detailed ablation about the proposed method. We show clear improvement in performance across all tasks and datasets considered, demonstrating the value of a model that incorporates object representations into a video-language architecture. The code has been released in https://github.com/FingerRec/OA-Transformer.

Text-based Visual Question Answering (Text-VQA) is a question-answering task to understand scene text, where the text is usually recognized by Optical Character Recognition (OCR) systems. However, the text from OCR systems often includes spelling errors, such as "pepsi" being recognized as "peosi". These OCR errors are one of the major challenges for Text-VQA systems. To address this, we propose a novel Text-VQA method to alleviate OCR errors via OCR token evolution. First, we artificially create the misspelled OCR tokens in the training time, and make the system more robust to the OCR errors. To be specific, we propose an OCR Token-Word Contrastive (TWC) learning task, which pre-trains word representation by augmenting OCR tokens via the Levenshtein distance between the OCR tokens and words in a dictionary. Second, by assuming that the majority of characters in misspelled OCR tokens are still correct, a multimodal transformer is proposed and fine-tuned to predict the answer using character-based word embedding. Specifically, we introduce a vocabulary predictor with character-level semantic matching, which enables the model to recover the correct word from the vocabulary even with misspelled OCR tokens. A variety of experimental evaluations show that our method outperforms the state-of-the-art methods on both TextVQA and ST-VQA datasets. The code will be released at https://github.com/xiaojino/TWA.

Audio-visual speaker diarization aims at detecting "who spoke when'' using both auditory and visual signals. Existing audio-visual diarization datasets are mainly focused on indoor environments like meeting rooms or news studios, which are quite different from in-the-wild videos in many scenarios such as movies, documentaries, and audience sitcoms. To develop diarization methods for these challenging videos, we create the AVA Audio-Visual Diarization (AVA-AVD) dataset. Our experiments demonstrate that adding AVA-AVD into training set can produce significantly better diarization models for in-the-wild videos despite that the data is relatively small. Moreover, this benchmark is challenging due to the diverse scenes, complicated acoustic conditions, and completely off-screen speakers. As a first step towards addressing the challenges, we design the Audio-Visual Relation Network (AVR-Net) which introduces a simple yet effective modality mask to capture discriminative information based on face visibility. Experiments show that our method not only can outperform state-of-the-art methods but is more robust as varying the ratio of off-screen speakers. Our data and code has been made publicly available at \textcolormagenta \urlhttps://github.com/showlab/AVA-AVD .

Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Best performing works rely on large-scale, 3rd-person video-text datasets, such as HowTo100M. In this work, we exploit the recently released Ego4D dataset to pioneer Egocentric VLP along three directions. (i) We create EgoClip, a 1st-person video-text pretraining dataset comprising 3.8M clip-text pairs well-chosen from Ego4D, covering a large variety of human daily activities. (ii) We propose a novel pretraining objective, dubbed EgoNCE, which adapts video-text contrastive learning to the egocentric domain by mining egocentric-aware positive and negative samples. (iii) We introduce EgoMCQ, a development benchmark that is close to EgoClip and hence can support effective validation and fast exploration of our design decisions in EgoClip and EgoNCE. Furthermore, we demonstrate strong performance on five egocentric downstream tasks across three datasets: video-text retrieval on EPIC-KITCHENS-100; action recognition on Charades-Ego; natural language query, moment query, and object state change classification on Ego4D challenge benchmarks. The dataset and code are available at https://github.com/showlab/EgoVLP.

Modeling dynamic scenes is important for many applications such as virtual reality and telepresence. Despite achieving unprecedented fidelity for novel view synthesis in dynamic scenes, existing methods based on Neural Radiance Fields (NeRF) suffer from slow convergence (i.e., model training time measured in days). In this paper, we present DeVRF, a novel representation to accelerate learning dynamic radiance fields. The core of DeVRF is to model both the 3D canonical space and 4D deformation field of a dynamic, non-rigid scene with explicit and discrete voxel-based representations. However, it is quite challenging to train such a representation which has a large number of model parameters, often resulting in overfitting issues. To overcome this challenge, we devise a novel static-to-dynamic learning paradigm together with a new data capture setup that is convenient to deploy in practice. This paradigm unlocks efficient learning of deformable radiance fields via utilizing the 3D volumetric canonical space learnt from multi-view static images to ease the learning of 4D voxel deformation field with only few-view dynamic sequences. To further improve the efficiency of our DeVRF and its synthesized novel view's quality, we conduct thorough explorations and identify a set of strategies. We evaluate DeVRF on both synthetic and real-world dynamic scenes with different types of deformation. Experiments demonstrate that DeVRF achieves two orders of magnitude speedup (100× faster) with on-par high-fidelity results compared to the previous state-of-the-art approaches. The code and dataset are released in https://github.com/showlab/DeVRF.

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels. Currently, most state-of-the-art WSTAL methods follow a Multi-Instance Learning (MIL) pipeline: producing snippet-level predictions first and then aggregating to the video-level prediction. However, we argue that existing methods have overlooked two important drawbacks: 1) inadequate use of motion information and 2) the incompatibility of prevailing cross-entropy training loss. In this paper, we analyze that the motion cues behind the optical flow features are complementary informative. Inspired by this, we propose to build a context-dependent motion prior, termed as motionness. Specifically, a motion graph is introduced to model motionness based on the local motion carrier (e.g., optical flow). In addition, to highlight more informative video snippets, a motion-guided loss is proposed to modulate the network training conditioned on motionness scores. Extensive ablation studies confirm that motionness efficaciously models action-of-interest, and the motion-guided loss leads to more accurate results. Besides, our motion-guided loss is a plug-and-play loss function and is applicable with existing WSTAL methods. Without loss of generality, based on the standard MIL pipeline, our method achieves new state-of-the-art performance on three challenging benchmarks, including THUMOS'14, ActivityNet v1.2 and v1.3.

Localizing persons and recognizing their actions from videos is a challenging task towards high-level video understanding. Recent advances have been achieved by modeling direct pairwise relations between entities. In this paper, we take one step further, not only model direct relations between pairs but also take into account indirect higher-order relations established upon multiple elements. We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context. To this end, we design an Actor-Context-Actor Relation Network (ACAR-Net) which builds upon a novel High-order Relation Reasoning Operator and an Actor-Context Feature Bank to enable indirect relation reasoning for spatio-temporal action localization. Experiments on AVA and UCF101-24 datasets show the advantages of modeling actor-context-actor relations, and visualization of attention maps further verifies that our model is capable of finding relevant higher-order relations to support action detection. Notably, our method ranks first in the AVA-Kinetics action localization task of ActivityNet Challenge 2020, outperforming other entries by a significant margin (+6.71 mAP). The code is available online.1

Video grounding aims to localize the temporal segment corresponding to a sentence query from an untrimmed video.Almost all existing video grounding methods fall into two frameworks: 1) Top-down model: It predefines a set of segment candidates and then conducts segment classification and regression.2) Bottomup model: It directly predicts frame-wise probabilities of the referential segment boundaries.However, all these methods are not end-to-end, i.e., they always rely on some time-consuming post-processing steps to refine predictions.To this end, we reformulate video grounding as a set prediction task and propose a novel end-toend multi-modal Transformer model, dubbed as GTR.Specifically, GTR has two encoders for video and language encoding, and a crossmodal decoder for grounding prediction.To facilitate the end-to-end training, we use a Cubic Embedding layer to transform the raw videos into a set of visual tokens.To better fuse these two modalities in the decoder, we design a new Multi-head Cross-Modal Attention.The whole GTR is optimized via a Many-to-One matching loss.Furthermore, we conduct comprehensive studies to investigate different model design choices.Extensive results on three benchmarks have validated the superiority of GTR.All three typical GTR variants achieve recordbreaking performance on all datasets and metrics, with several times faster inference speed.Our project is available at GTR.

Conventional video models rely on a single stream to capture the complex spatial-temporal features. Recent work on two-stream video models, such as SlowFast network and AssembleNet, prescribe separate streams to learn complementary features, and achieve stronger performance. However, manually designing both streams as well as the in-between fusion blocks is a daunting task, requiring to explore a tremendously large design space. Such manual exploration is time-consuming and often ends up with suboptimal architectures when computational resources are limited and the exploration is insufficient. In this work, we present a pragmatic neural architecture search approach, which is able to search for two-stream video models in giant spaces efficiently. We design a multivariate search space, including 6 search variables to capture a wide variety of choices in designing two-stream models. Furthermore, we propose a progressive search procedure, by searching for the architecture of individual streams, fusion blocks and attention blocks one after the other. We demonstrate two-stream models with significantly better performance can be automatically discovered in our design space. Our searched two-stream models, namely Auto-TSNet, consistently outperform other models on standard benchmarks. On Kinetics, compared with the SlowFast model, our Auto-TSNet-L model reduces FLOPS by nearly 11× while achieving the same accuracy 78.9%. On Something-Something-V2, Auto- TSNet-M improves the accuracy by at least 2% over other methods which use less than 50 GFLOPS per video.

This paper presents a novel task together with a new benchmark for detecting generic, taxonomy-free event boundaries that segment a whole video into chunks. Conventional work in temporal video segmentation and action detection focuses on localizing pre-defined action categories and thus does not scale to generic videos. Cognitive Science has known since last century that humans consistently segment videos into meaningful temporal chunks. This segmentation happens naturally, without pre-defined event categories and without being explicitly asked to do so. Here, we repeat these cognitive experiments on mainstream CV datasets; with our novel annotation guideline which addresses the complexities of taxonomy-free event boundary annotation, we introduce the task of Generic Event Boundary Detection (GEBD) and the new benchmark Kinetics-GEBD. We view GEBD as an important stepping stone towards understanding the video as a whole, and believe it has been previously neglected due to a lack of proper task definition and annotations. Through experiment and human study we demonstrate the value of the annotations. Further, we benchmark supervised and un-supervised GEBD approaches on the TAPOS dataset and our Kinetics-GEBD. We release our annotations and baseline codes at CVPR’21 LOVEU Challenge: https://sites.google.com/view/loveucvpr21.

This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem. For data augmentation, most existing methods directly adopt the standard operations designed for single-modality visible images, and thus do not fully consider the imagery properties in visible to infrared matching. Our basic idea is to homogenously generate color-irrelevant images by randomly exchanging the color channels. It can be seamlessly integrated into existing augmentation operations without modifying the network, consistently improving the robustness against color variations. Incorporated with a random erasing strategy, it further greatly enriches the diversity by simulating random occlusions. For cross-modality metric learning, we design an enhanced channel-mixed learning strategy to simultaneously handle the intra-and cross-modality variations with squared difference for stronger discriminability. Besides, a channel-augmented joint learning strategy is further developed to explicitly optimize the outputs of augmented images. Extensive experiments with insightful analysis on two visible-infrared recognition tasks show that the proposed strategies consistently improve the accuracy. Without auxiliary information, it improves the state-of-the-art Rank-1/mAP by 14.59%/13.00% on the large-scale SYSU-MM01 dataset.

Active speaker detection (ASD) seeks to detect who is speaking in a visual scene of one or more speakers. The successful ASD depends on accurate interpretation of short-term and long-term audio and visual information, as well as audio-visual interaction. Unlike the prior work where systems make decision instantaneously using short-term features, we propose a novel framework, named TalkNet, that makes decision by taking both short-term and long-term features into consideration. TalkNet consists of audio and visual temporal encoders for feature representation, audio-visual cross-attention mechanism for inter-modality interaction, and a self-attention mechanism to capture long-term speaking evidence. The experiments demonstrate that TalkNet achieves 3.5% and 2.2% improvement over the state-of-the-art systems on the AVA-ActiveSpeaker dataset and Columbia ASD dataset, respectively. Code has been made available at: https://github.com/TaoRuijie/TalkNet_ASD.

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very timeconsuming. Recent works directly leverage the motion vectors and residuals readily available in the compressed video to represent motion at no cost. While this avoids flow computation, it also hurts accuracy since the motion vector is noisy and has substantially reduced resolution, which makes it a less discriminative motion representation. To remedy these issues, we propose a lightweight generator network, which reduces noises in motion vectors and captures fine motion details, achieving a more Discriminative Motion Cue (DMC) representation. Since optical flow is a more accurate motion representation, we train the DMC generator to approximate flow using a reconstruction loss and a generative adversarial loss, jointly with the downstream action classification task. Extensive evaluations on three action recognition benchmarks (HMDB-51, UCF-101, and a subset of Kinetics) confirm the effectiveness of our method. Our full system, consisting of the generator and the classifier, is coined as DMC-Net which obtains high accuracy close to that of using flow and runs two orders of magnitude faster than using optical flow at inference time.

Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either assume that intra-class variances can always be generalized to new classes, or employ naive generation methods to hallucinate finite examples without modeling their latent distributions. In this work, we propose Covariance-Preserving Adversarial Augmentation Networks to overcome existing limits of low-shot learning. Specifically, a novel Generative Adversarial Network is designed to model the latent distribution of each novel class given its related base counterparts. Since direct estimation on novel classes can be inductively biased, we explicitly preserve covariance information as the ``variability'' of base examples during the generation process. Empirical results show that our model can generate realistic yet diverse examples, leading to substantial improvements on the ImageNet benchmark over the state of the art.

Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to localize the start time and end time of each instance. Many state-of-the-art systems use segment-level classifiers to select and rank proposal segments of pre-determined boundaries. However, a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. To this end, we design a novel Convolutional-De-Convolutional (CDC) network that places CDC filters on top of 3D ConvNets, which have been shown to be effective for abstracting action semantics but reduce the temporal length of the input data. The proposed CDC filter performs the required temporal upsampling and spatial downsampling operations simultaneously to predict actions at the frame-level granularity. It is unique in jointly modeling action semantics in space-time and fine-grained temporal dynamics. We train the CDC network in an end-to-end manner efficiently. Our model not only achieves superior performance in detecting actions in every frame, but also significantly boosts the precision of localizing temporal boundaries. Finally, the CDC network demonstrates a very high efficiency with the ability to process 500 frames per second on a single GPU server. Source code and trained models are available online at https://bitbucket.org/columbiadvmm/cdc.

We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other activities. To address this challenging issue, we exploit the effectiveness of deep networks in temporal action localization via three segment-based 3D ConvNets: (1) a proposal network identifies candidate segments in a long video that may contain actions, (2) a classification network learns one-vs-all action classification model to serve as initialization for the localization network, and (3) a localization network fine-tunes the learned classification network to localize each action instance. We propose a novel loss function for the localization network to explicitly consider temporal overlap and achieve high temporal localization accuracy. In the end, only the proposal network and the localization network are used during prediction. On two largescale benchmarks, our approach achieves significantly superior performances compared with other state-of-the-art systems: mAP increases from 1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014.