Retrieval-Augmented Generation (RAG) enhances the response capabilities of language models by integrating external knowledge sources.However, document chunking as an important part of RAG system often lacks effective evaluation tools.This paper first analyzes why existing RAG evaluation benchmarks are inadequate for assessing document chunking quality, specifically due to evidence sparsity.Based on this conclusion, we propose HiCBench, which includes manually annotated multi-level document chunking points, synthesized evidence-dense question answer(QA) pairs, and their corresponding evidence sources.We also propose HiChunk, a hierarchical document structuring framework using fine-tuned LLMs and the Auto-Merge retrieval algorithm to enhance retrieval quality.Experiments demonstrate that HiCBench effectively evaluates the impact of different chunking methods across the entire RAG pipeline.Moreover, HiChunk achieves better chunking quality within reasonable time consumption, thereby enhancing the overall performance of RAG systems.Source code is available at https: //github.com/TencentCloudADP/hichunk.

Chuang Zhou, Junnan Dong, Yilin Xiao, Shengyuan Chen, Su Dong, di Yin, Xing Sun, Zhaozhuo Xu, Xiao Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun, Xiao Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key–value states into a low-rank latent vector cKV, caching only this vector to reduce memory. In tensor parallelism (TP), however, attention heads are computed across multiple devices, and each device must load the full cKV, eroding the advantage of MLA over Grouped Query Attention (GQA). We present TPLA, a scheme that partitions both the latent representation and each head's input dimension across devices, performs attention independently on each shard, and aggregates the results with an all-reduce. Unlike GLA, every attention head in TPLA still attends to the full latent space, preserving MLA's representational capacity while reducing the per-device KV cache. To make TPLA drop-in compatible with MLA checkpoints, we further derive orthogonal reparameterizations of RMSNorm and softmax---instantiated with Hadamard and PCA transforms---that mitigate cross-shard discrepancies when slicing latent vectors across devices. Finally, we introduce a prefill-decode separation scheme that keeps the MLA form during compute-bound prefilling and switches to TPLA during memory-bound decoding, minimizing conversion-induced error. By reducing the per-device KV cache for DeepSeek-V3 and Kimi-K2, we achieve 1.79x) and 1.93) speedups respectively, at a 32K-token context length while maintaining accuracy on commonsense and LongBench benchmarks. TPLA can be further implemented on top of FlashAttention-3, enabling practical end-to-end acceleration.

In Semi-supervised learning(SSL), we always accept cluster assumption, assuming features in different high-density regions belong to other categories. However, it is always ignored by existing algorithms and needs mathematical explanations. This paper first proposes a theorem to statistically explain cluster assumption and prove that the probability density can significantly help to use the prior fully. A Probability-Density-Aware Measure(PM) is proposed based on the theorem to discern the similarity between neighbor points. The PM is deployed to improve Label Propagation and a new pseudo-labeling algorithm, the Probability-Density-Aware Label Propagation(PMLP), is proposed. We also prove that traditional first-order similarity pseudo-labeling could be viewed as a particular case of PMLP, which provides a comprehensive theoretical understanding of PMLP's superior performance. Extensive experiments demonstrate that PMLP achieves outstanding performance compared with other recent methods.

Pinyi Zhang, Siyu An, Lingfeng Qiao, Yifei Yu, Jingyang Chen, Jie Wang, Di Yin, Xing Sun, Kai Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

When carefully optimized by human experts, naive prompts can significantly enhance the task performance of large language models (LLMs). However, such expert-driven prompt optimizations are resource-intensive. To address this, some studies have proposed Automatic Prompt Optimization (APO), which refines naive prompts according to task outputs from in-box testing models, utilizing advanced LLMs (e.g., GPT-4) in an ad-hoc way. Although effective, current approaches face challenges in generalization and privacy risks. To overcome these limitations, we have developed the first large-scale Prompt Optimization Preference (POP) dataset, fine-tuned offline local LLM-based optimizers, and conducted fairly evaluations across various downstream models. Our method, named Free-from Instruction-oriented Prompt Optimization (FIPO), allows precise optimization of the core task instructions in naive prompts in a model-agnostic manner. FIPO uses a modular APO template that dynamically incorporates the naive task instructions, optional instruction responses, and optional ground truth to produce refined prompts. The POP dataset is meticulously constructed using advanced LLMs, undergoing rigorous cross-validation by human experts and analytical models. By leveraging insights from this dataset, along with Tulu2 models and diverse fine-tuning strategies, we validate the efficacy of the FIPO framework across five public benchmarks and six testing models. Our dataset and codes are available at: https://github.com/LuJunru/FIPO_Project.

Recent LLM-based Text-to-SQL methods usually suffer from significant performance degradation on “huge” databases and complex user questions that require multi-step reasoning. Moreover, most existing methods neglect the crucial significance of LLMs utilizing external tools and model collaboration. To address these challenges, we introduce MAC-SQL, a novel LLM-based multi-agent collaborative framework. Our framework comprises a core decomposer agent for Text-to-SQL generation with few-shot chain-of-thought reasoning, accompanied by two auxiliary agents that utilize external tools or models to acquire smaller sub-databases and refine erroneous SQL queries. The decomposer agent collaborates with auxiliary agents, which are activated as needed and can be expanded to accommodate new features or tools for effective Text-to-SQL parsing. In our framework, We initially leverage GPT-4 as the strong backbone LLM for all agent tasks to determine the upper bound of our framework. We then fine-tune an open-sourced instruction-followed model, SQL-Llama, by leveraging Code Llama 7B, to accomplish all tasks as GPT-4 does. Experiments show that SQL-Llama achieves a comparable execution accuracy of 43.94, compared to the baseline accuracy of 46.35 for vanilla GPT-4. At the time of writing, MAC-SQL+GPT-4 achieves an execution accuracy of 59.59 when evaluated on the BIRD benchmark, establishing a new state-of-the-art (SOTA) on its holdout test set.

In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The potential of MLLMs to process sequential visual data is still insufficiently explored, highlighting the lack of a comprehensive, high-quality assessment of their performance. In this paper, we introduce Video-MME, the first-ever full-spectrum, Multi-Modal Evaluation benchmark of MLLMs in Video analysis. Our work distinguishes from existing benchmarks through four key features: 1) Diversity in video types, spanning 6 primary visual domains with 30 subfields to ensure broad scenario generalizability; 2) Duration in temporal dimension, encompassing both short-, medium-, and long-term videos, ranging from 11 seconds to 1 hour, for robust contextual dynamics; 3) Breadth in data modalities, integrating multi-modal inputs besides video frames, including subtitles and audios, to unveil the all-round capabilities of MLLMs; 4) Quality in annotations, utilizing rigorous manual labeling by expert annotators to facilitate precise and reliable model assessment. With Video-MME, we extensively evaluate various state-of-the-art MLLMs, and reveal that Gemini 1.5 Pro is the best-performing commercial model, significantly outperforming the open-source models with an average accuracy of 75%, compared to 71.9% for GPT-4o. The results also demonstrate that Video-MME is a universal benchmark that applies to both image and video MLLMs. Further analysis indicates that subtitle and audio information could significantly enhance video understanding. Besides, a decline in MLLM performance is observed as video duration increases for all models. Our dataset along with these findings underscores the need for further improvements in handling longer sequences and multi-modal data, shedding light on future MLLM development. Project page: https://video-mme.github.io.

Yifei Yu, Qian-Wen Zhang, Lingfeng Qiao, Di Yin, Fang Li, Jie Wang, Chen Zeng Xi, Suncong Zheng, Xiaolong Liang, Xing Sun. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Current weakly supervised point cloud semantic segmentation struggles with insufficient utilization of limited annotations in unimodal representation learning due to the sparse and textureless nature of point clouds. In this work, we leverage cross-modality information by transferring knowledge from image and text sources to the point cloud network. The intuition is that images contribute rich texture, color, and discriminative information, complementing point clouds to boost semantic segmentation performance. To reduce extensive computational resources for cross-modality fusion, we introduce the Multi-Scale Deformable Knowledge Transfer, an innovative training scheme that optimizes and extends the one-to-one mapping to flexible one-to-many relations between multi-modal data. Furthermore, we employ pre-trained image-text models to generate pseudo labels for point clouds and construct positive and negative samples for semantic contrastive regularization, facilitating the full exploitation of unlabeled data. The experimental results evaluated on SemanticKITTI and nuScenes demonstrate substantial improvements, achieving an average gain of 3.8% over the previous weakly supervised methods, and comparable performances to fully supervised approaches.

Evaluating large language models (LLMs) in diverse and challenging scenarios is essential to align them with human preferences. To mitigate the prohibitive costs associated with human evaluations, utilizing a powerful LLM as a judge has emerged as a favored approach. Nevertheless, this methodology encounters several challenges, including substantial expenses, concerns regarding privacy and security, and reproducibility. In this paper, we propose a straightforward, replicable, and accurate automated evaluation method by leveraging a lightweight LLM as the judge, named RocketEval. Initially, we identify that the performance disparity between lightweight and powerful LLMs in evaluation tasks primarily stems from their ability to conduct comprehensive analyses, which is not easily enhanced through techniques such as chain-of-thought reasoning. By reframing the evaluation task as a multi-faceted Q\&A using an instance-specific checklist, we demonstrate that the limited judgment accuracy of lightweight LLMs is largely attributes to high uncertainty and positional bias. To address these challenges, we introduce an automated evaluation process grounded in checklist grading, which is designed to accommodate a variety of scenarios and questions. This process encompasses the creation of checklists, the grading of these checklists by lightweight LLMs, and the reweighting of checklist items to align with the supervised annotations. Our experiments carried out on the automated evaluation benchmarks, MT-Bench and WildBench datasets, reveal that RocketEval, when using $\textit{Gemma-2-2B}$ as the judge, achieves a high correlation (0.965) with human preferences, which is comparable to $\textit{GPT-4o}$. Moreover, RocketEval provides a cost reduction exceeding 50-fold for large-scale evaluation and comparison scenarios. Our code is available at https://github.com/Joinn99/RocketEval-ICLR.

The swift progress of Multi-modal Large Models (MLLMs) has showcased their impressive ability to tackle tasks blending vision and language. Yet, most current models and benchmarks cater to scenarios with a narrow scope of visual and textual contexts. These models often fall short when faced with complex comprehension tasks, which involve navigating through a plethora of irrelevant and potentially misleading information in both text and image forms. To bridge this gap, we introduce a new, more demanding task known as Interleaved Image-Text Comprehension (IITC). This task challenges models to discern and disregard superfluous elements in both images and text to accurately answer questions and to follow intricate instructions to pinpoint the relevant image. In support of this task, we further craft a new VEGA dataset, tailored for the IITC task on scientific content, and devised a subtask, Image-Text Association (ITA), to refine image-text correlation skills. Our evaluation of four leading closed-source models, as well as various open-source models using VEGA, underscores the rigorous nature of IITC. Even the most advanced models, such as Gemini-1.5-pro and GPT4V, only achieved modest success. By employing a multi-task, multi-scale post-training strategy, we have set a robust baseline for MLLMs on the IITC task, attaining an $85.8\%$ accuracy rate in image association and a $0.508$ Rouge score. These results validate the effectiveness of our dataset in improving MLLMs capabilities for nuanced image-text comprehension.

Vision-Language Models (VLMs) face two critical limitations in visual representation learning: degraded supervision due to information loss during gradient propagation, and the inherent semantic sparsity of textual supervision compared to visual data. We propose the Diffusion Supervision Vision-Language Model (DS-VLM), a plug-and-play framework that introduces diffusion-based direct supervision for vision-language alignment. By reconstructing input images through a diffusion model conditioned on outputs of the visual encoder and the connector, our method establishes a short-path gradient propagation channel from pixel space to visual features. This approach simultaneously preserves high-level semantic alignment through conventional text supervision while enhancing visual feature quality via pixel-level reconstruction constraints. Extensive experiments conducted across various visual encoders and LLMs of different scales demonstrate the effectiveness of our approach.

Multimodal person re-identification (Re-ID) aims to match pedestrian images across different modalities. However, most existing methods focus on limited cross-modal settings and fail to support arbitrary query-retrieval combinations, hindering practical deployment. We propose FlexiReID, a flexible framework that supports seven retrieval modes across four modalities: RGB, infrared, sketches, and text. FlexiReID introduces an adaptive mixture-of-experts (MoE) mechanism to dynamically integrate diverse modality features and a cross-modal query fusion module to enhance multimodal feature extraction. To facilitate comprehensive evaluation, we construct CIRS-PEDES, a unified dataset extending four popular Re-ID datasets to include all four modalities. Extensive experiments demonstrate that FlexiReID achieves state-of-the-art performance and offers strong generalization in complex scenarios.

The GPT-4o’s excellent duplex speech interaction ability has given users an impressive experience. Researchers have recently proposed several multimodal LLMs to achieve user-agent speech-to-speech conversations. In this paper, we propose a novel speech-text multimodal LLM architecture called Freeze-Omni, and our main contribution is that the speech input and output modalities can be easily connected to a textual LLM while keeping the LLM’s parameters frozen throughout the training process. We effectively ensure that the intelligence of the Freeze-Omni in the speech modality is at the same level as that in the text modality of its backbone LLM while achieving low latency in the end-to-end spoken response. In addition, we also designed a method to achieve duplex dialogue ability through multitask training, giving Freeze-Omni a more natural style of dialogue ability between users and agents. In summary, Freeze-Omni holds great potential to conduct speech-to-speech dialogue based on a multimodal LLM under the condition of a frozen LLM, avoiding the catastrophic forgetting problem caused by limited data and training resources.

Open-vocabulary object detection seeks to recognize objects from arbitrary language inputs, extending detection beyond fixed training categories. While recent methods have made progress in detecting unseen categories, they typically require a set of predefined categories during the inference stage, hindering practical deployment in open-world scenarios. To overcome this crucial limitation, we propose UniPerception , a novel universal perception framework based on open-vocabulary object detection. It not only excels at open-vocabulary object detection but is also capable of generating labels for target objects in the absence of predefined vocabularies, and can be adapted to a broad range of vision-language tasks simply by modifying the language instructions. UniPerception seamlessly integrates three key innovations: 1) a robust visual detector trained on diverse data sources to capture rich and generalizable visual representations; 2) a language model with interleaved cross-modality fusion layers to interpret instructions and generate fine-grained responses conditioned on visual features; and 3) a tailored multi-stage training strategy that effectively bridges detection-specific learning with general vision-language understanding. We conduct extensive experiments on multiple benchmarks for open-vocabulary object detection (COCO, LVIS, ODinW), referring expression comprehension (RefCOCO/+/g, D3), and vision-language understanding (Flickr30k, VQAv2, GQA). The results show that UniPerception achieves strong open-world generalization and multi-modal understanding, outperforming the existing state-of-the-art methods and establishing itself as a unified, instruction-driven perception system.

Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image. However, it is difficult for these case studies to fully reflect the performance of MLLM, lacking a comprehensive evaluation. In this paper, we fill in this blank, presenting the first comprehensive MLLM Evaluation benchmark MME. It measures both perception and cognition abilities on a total of 14 subtasks. In order to avoid data leakage that may arise from direct use of public datasets for evaluation, the annotations of instruction-answer pairs are all manually designed. The concise instruction design allows us to fairly compare MLLMs, instead of struggling in prompt engineering. Besides, with such an instruction, we can also easily carry out quantitative statistics. A total of 30 advanced MLLMs are comprehensively evaluated on our MME, which not only suggests that existing MLLMs still have a large room for improvement, but also reveals the potential directions for the subsequent model optimization. The data are released at the project page: https://github.com/BradyFU/Awesome-Multimodal-Large-Language-Models/tree/Evaluation.

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing against state-of-the-art counterparts across benchmarks for image, video, and speech, we demonstrate that our omni model is equipped with both strong visual and speech capabilities, making omni understanding and interaction.

Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing methods using Direct Preference Optimization (DPO) constrain optimization to a solitary image reference within the input sequence, neglecting holistic context modeling. To address this, we propose Context-to-Cue Direct Preference Optimization (CcDPO), a multi-level preference optimization framework that enhances per-image perception in multi-image settings by zooming into visual clues—from sequential context to local details. Our approach features two sequentially dependent components: (i) Context-Level Optimization: By introducing low-cost sequence preference pairs, we optimize the model to distinguish between complete and disrupted multi-image contexts, thereby correcting cognitive biases in MLLMs’ multi-image understanding. (ii) Needle-Level Optimization: By integrating region-specific visual prompts with multimodal preference supervision, we direct the model’s attention to critical visual details, effectively suppressing perceptual biases toward fine-grained visual information. To support scalable optimization, we also construct MultiScope-42k, an automatically generated multi-image dataset with hierarchical preference pairs. Experiments show that CcDPO significantly reduces hallucinations and yields consistent performance gains across general single- and multi-image tasks. Codes are available at https://github.com/LXDxmu/CcDPO.

Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research—relying on opaque numerical metrics that conceal fundamental limitations in spatial reasoning while providing no intuitive understanding of model capabilities. This deficiency creates a dangerous disconnect between reported performance and practical abilities, particularly for applications requiring physical world understanding. We introduce LTD-Bench, a breakthrough benchmark that transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code. This approach makes spatial reasoning limitations immediately apparent even to non-experts, bridging the fundamental gap between statistical performance and intuitive assessment. LTD-Bench implements a comprehensive methodology with complementary generation tasks (testing spatial imagination) and recognition tasks (assessing spatial perception) across three progressively challenging difficulty levels, methodically evaluating both directions of the critical language-spatial mapping. Our extensive experiments with state-of-the-art models expose an alarming capability gap: even LLMs achieving impressive results on traditional benchmarks demonstrate profound deficiencies in establishing bidirectional mappings between language and spatial concepts—a fundamental limitation that undermines their potential as genuine world models. Furthermore, LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity. Our dataset and codes are available at https://github.com/walktaster/LTD-Bench.

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience high latency when generating the first audio token during streaming, which poses a significant bottleneck for deployment. To address this issue, we propose VITA-Audio, an end-to-end large speech model with fast audio-text token generation. Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios. In addition, a four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality. To our knowledge, VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency. VITA-Audio is fully reproducible and is trained on open-source data only. Experimental results demonstrate that our model achieves an inference speedup of 3~5x at the 7B parameter scale, but also significantly outperforms open-source models of similar model size on multiple benchmarks for automatic speech recognition (ASR), text-to-speech (TTS), and spoken question answering (SQA) tasks.

Modern large-language models often face communication bottlenecks on current hardware rather than computational limitations. *Multi-head latent attention (MLA)* addresses this by compressing the key-value cache using low-rank matrices, while the Absorb operation prevents the KV cache from reverting to its original size, significantly boosting both training and inference speed. Despite the success of DeepSeek V2/V3/R1, most model providers have heavily invested in optimizing GQA-based models and, therefore, lack strong incentives to retrain MLA-based models from scratch. This paper demonstrates that MLA provides superior expressive power compared to GQA with the same KV cache overhead, thereby offering a rationale for transitioning from GQA to MLA. In addition, we introduce TransMLA, a framework that seamlessly converts any GQA-based pre-trained model (e.g., LLaMA, Qwen, Gemma, Mistral/Mixtral) into an MLA-based model. For the first time, our method enables *direct conversion of these models into a format compatible with DeepSeek's codebase*, allowing them to fully leverage the existing, highly-optimized support for the DeepSeek architecture within inference engines like vLLM and SGlang. By compressing 93\% of the KV cache in LLaMA-2-7B, we achieve a **10x speedup** with an 8K context length while maintaining meaningful output. Moreover, the model requires only **6B tokens** for fine-tuning to recover comparable performance across multiple benchmarks. TransMLA provides a practical path for migrating GQA-based models to the MLA structure, and when combined with DeepSeek’s advanced optimizations—such as FP8 quantization and Multi-Token Prediction—further inference acceleration can be achieved.

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabilities of LLMs. However, we find that the vanilla CoT exerts a negative impact on performance due to its superficial reasoning pattern of simply paraphrasing the instructions. It fails to peel back the compositions of constraints for identifying their relationship across hierarchies of types and dimensions. To this end, we propose RAIF, a systematic method to boost LLMs in dealing with complex instructions via incentivizing reasoning for test-time compute scaling. First, we stem from the decomposition of complex instructions under existing taxonomies and propose a reproducible data acquisition method. Second, we exploit reinforcement learning (RL) with verifiable rule-centric reward signals to cultivate reasoning specifically for instruction following. We address the shallow, non-essential nature of reasoning under complex instructions via sample-wise contrast for superior CoT enforcement. We also exploit behavior cloning of experts to facilitate steady distribution shift from fast-thinking LLMs to skillful reasoners. Extensive evaluations on seven comprehensive benchmarks confirm the validity of the proposed method, where a 1.5B LLM achieves 11.74% gains with performance comparable to a 8B LLM. Evaluation on OOD constraints also confirms the generalizability of our RAIF.

Knowledge distillation (KD) has been widely adopted to compress large language models (LLMs). Existing KD methods investigate various divergence measures including the Kullback-Leibler (KL), reverse KL (RKL), and Jensen-Shannon (JS) divergences. However, due to limitations inherent in their assumptions and definitions, these measures fail to deliver effective supervision when a distribution overlap exists between the teacher and the student. In this article, we show that the aforementioned KL, RKL, and JS divergences, respectively, suffer from issues of mode-averaging, mode-collapsing, and mode-underestimation, which deteriorates logits-based KD for diverse natural language processing (NLP) tasks. We propose the Sinkhorn KD (SinKD) that exploits the Sinkhorn distance to ensure a nuanced and precise assessment of the disparity between distributions of teacher and student models. Besides, thanks to the properties of the Sinkhorn metric, we get rid of sample-wise KD that restricts the perception of divergences inside each teacher-student sample pair. Instead, we propose a batch-wise reformulation to capture the geometric intricacies of distributions across samples in the high-dimensional space. A comprehensive evaluation of GLUE and SuperGLUE, in terms of comparability, validity, and generalizability, highlights our superiority over state-of-the-art (SOTA) methods on all kinds of LLMs with encoder-only, encoder-decoder, and decoder-only architectures. Codes and models are available at https://github.com/2018cx/SinKD.

Although In-Context Learning (ICL) brings remarkable performance gains to Large Language Models (LLMs), the improvements remain lower than fine-tuning on downstream tasks. This paper introduces Multi-Modal In-Context Tuning (MMICT), a novel multi-modal fine-tuning paradigm that boosts multi-modal fine-tuning by fully leveraging the promising ICL capability of Multi-Modal LLMs (MM-LLMs). We propose the Multi-Modal Hub (M-Hub), a unified module that captures various multi-modal features according to different inputs and objectives. Based on M-Hub, MMICT enables MM-LLMs to learn from in-context visual-guided textual features and subsequently generate outputs conditioned on the textual-guided visual features. Moreover, leveraging the flexibility of M-Hub, we design a variety of in-context demonstrations. Extensive experiments on a diverse range of downstream multi-modal tasks demonstrate that MMICT significantly outperforms traditional fine-tuning strategy and the vanilla ICT method that directly takes the concatenation of all information from different modalities as input. Our implementation is available at: https://github.com/KDEGroup/MMICT .

During the preceding biennium, vision-language pre-training has achieved noteworthy success on several downstream tasks. Nevertheless, acquiring high-quality image-text pairs, where the pairs are entirely exclusive of each other, remains a challenging task, and noise exists in the commonly used datasets. To address this issue, we propose SoftCLIP, a novel approach that relaxes the strict one-to-one constraint and achieves a soft cross-modal alignment by introducing a softened target, which is generated from the fine-grained intra-modal self-similarity. The intra-modal guidance is indicative to enable two pairs have some local similarities and model many-to-many relationships between the two modalities. Besides, since the positive still dominates in the softened target distribution, we disentangle the negatives in the distribution to further boost the relation alignment with the negatives in the cross-modal learning. Extensive experiments demonstrate the effectiveness of SoftCLIP. In particular, on ImageNet zero-shot classification task, using CC3M/CC12M as pre-training dataset, SoftCLIP brings a top-1 accuracy improvement of 6.8%/7.2% over the CLIP baseline.

Symmetric positive definite(SPD) matrices have shown important value and applications in statistics and machine learning, such as FMRI analysis and traffic prediction. Previous works on SPD matrices mostly focus on discriminative models, where predictions are made directly on E(X|y), where y is a vector and X is an SPD matrix. However, these methods are challenging to handle for large-scale data. In this paper, inspired by denoising diffusion probabilistic model(DDPM), we propose a novel generative model, termed SPD-DDPM, by introducing Gaussian distribution in the SPD space to estimate E(X|y). Moreover, our model can estimate p(X) unconditionally and flexibly without giving y. On the one hand, the model conditionally learns p(X|y) and utilizes the mean of samples to obtain E(X|y) as a prediction. On the other hand, the model unconditionally learns the probability distribution of the data p(X) and generates samples that conform to this distribution. Furthermore, we propose a new SPD net which is much deeper than the previous networks and allows for the inclusion of conditional factors. Experiment results on toy data and real taxi data demonstrate that our models effectively fit the data distribution both unconditionally and conditionally.

Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community. While impressive success, most single table component-based methods can not perform well on unregularized table cases distracted by not only complicated inner structure but also exterior capture distortion. In this paper, we raise it as Complex TSR problem, where the performance degeneration of existing methods is attributable to their inefficient component usage and redundant post-processing. To mitigate it, we shift our perspective from table component extraction towards the efficient multiple components leverage, which awaits further exploration in the field. Specifically, we propose a seminal method, termed GrabTab, equipped with newly proposed Component Deliberator, to handle various types of tables in a unified framework. Thanks to its progressive deliberation mechanism, our GrabTab can flexibly accommodate to most complex tables with reasonable components selected but without complicated post-processing involved. Quantitative experimental results on public benchmarks demonstrate that our method significantly outperforms the state-of-the-arts, especially under more challenging scenes.

Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and visual video signals. Although existing methods have demonstrated that the aligned visual input of lip movements can enhance the robustness of AVSR systems against noise, the paired videos are not always available during inference, leading to the problem of the missing visual modality, which restricts their practicality in real-world scenarios. To tackle this problem, we propose a Discrete Feature based Visual Generative Model (DFVGM) which exploits semantic correspondences between the audio and visual modalities during training, generating visual hallucinations in lieu of real videos during inference. To achieve that, the primary challenge is to generate the visual hallucination given the noisy audio while preserving semantic correspondences with the clean speech. To tackle this challenge, we start with training the audio encoder in the Audio-Only (AO) setting, which generates continuous semantic features closely associated with the linguistic information. Simultaneously, the visual encoder is trained in the Visual-Only (VO) setting, producing visual features that are phonetically related. Next, we employ K-means to discretize the continuous audio and visual feature spaces. The discretization step allows DFVGM to capture high-level semantic structures that are more resilient to noise and generate visual hallucinations with high quality. To evaluate the effectiveness and robustness of our approach, we conduct extensive experiments on two publicly available datasets. The results demonstrate that our method achieves a remarkable 53% relative reduction (30.5%->12.9%) in Word Error Rate (WER) on average compared to the current state-of-the-art Audio-Only (AO) baselines while maintaining comparable results (< 5% difference) under the Audio-Visual (AV) setting even without video as input.

Knowledge distillation (KD) has been widely adopted to compress large language models (LLMs). Existing KD methods investigate various divergence measures including the Kullback-Leibler (KL), reverse Kullback-Leibler (RKL), and Jensen-Shannon (JS) divergences. However, due to limitations inherent in their assumptions and definitions, these measures fail to deliver effective supervision when few distribution overlap exists between the teacher and the student. In this paper, we show that the aforementioned KL, RKL, and JS divergences respectively suffer from issues of mode-averaging, mode-collapsing, and mode-underestimation, which deteriorates logits-based KD for diverse NLP tasks. We propose the Sinkhorn Knowledge Distillation (SinKD) that exploits the Sinkhorn distance to ensure a nuanced and precise assessment of the disparity between teacher and student distributions. Besides, profit by properties of the Sinkhorn metric, we can get rid of sample-wise KD that restricts the perception of divergence in each teacher-student sample pair. Instead, we propose a batch-wise reformulation to capture geometric intricacies of distributions across samples in the high-dimensional space. Comprehensive evaluation on GLUE and SuperGLUE, in terms of comparability, validity, and generalizability, highlights our superiority over state-of-the-art methods on all kinds of LLMs with encoder-only, encoder-decoder, and decoder-only architectures.

The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost. Existing methods have attempted to accelerate the training of ViTs, yet typically disregard method universality with accuracy dropping. Meanwhile, they break the training consistency of the original transformers, including the consistency of hyperparameters, architecture, and strategy, which prevents them from being widely applied to different Transformer networks. In this paper, we propose a novel token growth scheme Token Expansion (termed ToE) to achieve consistent training acceleration for ViTs. We introduce an “initialization-expansion-merging” pipeline to maintain the integrity of the intermediate feature distribution of original transformers, preventing the loss of crucial learnable information in the training process. ToE can not only be seamlessly integrated into the training and fine-tuning process of transformers (e.g., DeiT and LV-ViT), but also effective for efficient training frameworks (e.g., EfficientTrain), without twisting the original training hyperparameters, architecture, and introducing additional training strategies. Extensive experiments demonstrate that ToE achieves about 1.3× faster for the training of ViTs in a lossless manner, or even with performance gains over the full-token training baselines. Code is available at https://github.com/Osilly/TokenExpansion.

Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (VDU). Different from conventional vision-language tasks, VDU is specifically concerned with text-rich scenarios containing abundant document elements. Nevertheless, the importance of fine-grained features remains largely unexplored within the community of LVLMs, leading to suboptimal performance in text-rich scenarios. In this paper, we abbreviate it as the fine-grained feature collapse issue. With the aim of filling this gap, we propose a contrastive learning framework, termed Document Object COntrastive learning (DoCo), specifically tailored for the downstream tasks of VDU. DoCo leverages an auxiliary multimodal encoder to obtain the features of document objects and align them to the visual features generated by the vision encoder of LVLM, which enhances visual representation in text-rich scenarios. It can represent that the contrastive learning between the visual holistic representations and the multimodal fine-grained features of document objects can assist the vision encoder in acquiring more effective visual cues, thereby enhancing the comprehension of text-rich documents in LVLMs. We also demonstrate that the proposed DoCo serves as a plug-and-play pre-training method, which can be employed in the pre-training of various LVLMs without inducing any increase in computational complexity during the inference process. Extensive experimental results on multiple benchmarks of VDU reveal that LVLMs equipped with our proposed DoCo can achieve superior performance and mitigate the gap between VDU and generic vision-language tasks.

Leveraging vast training data, multimodal large language models (MLLMs) have demonstrated formidable general visual comprehension capabilities and achieved remarkable performance across various tasks. However, their performance in visual document understanding still leaves much room for improvement. This discrepancy is primarily attributed to the fact that visual document understanding is a fine-grained prediction task. In natural scenes, MLLMs typically use low-resolution images, leading to a substantial loss of visual information. Furthermore, general-purpose MLLMs do not excel in handling document-oriented instructions. In this paper, we propose a High-Resolution Visual Document Assistant (HRVDA), which bridges the gap between MLLMs and visual document understanding. This model employs a content filtering mechanism and an instruction filtering module to separately filter out the content-agnostic visual tokens and instruction-agnostic visual tokens, thereby achieving efficient model training and inference for high-resolution images. In addition, we construct a document-oriented visual instruction tuning dataset and apply a multi-stage training strategy to enhance the model's document modeling capabilities. Extensive experiments demonstrate that our model achieves state-of-the-art performance across multiple document understanding datasets, while maintaining training efficiency and inference speed comparable to low-resolution models.

Vision foundation models have been explored recently to build general-purpose vision systems. However, predomi-nant paradigms, driven by casting instance-level tasks as an object-word alignment, bring heavy cross-modality in-teraction, which is not effective in prompting object detection and visual grounding. Another line of work that fo-cuses on pixel-level tasks often encounters a large annotation gap of things and stuff, and suffers from mutual inter-ference between foreground-object and background-class segmentation. In stark contrast to the prevailing methods, we present APE, a universal visual perception model for aligning and prompting everything all at once in an image to perform diverse tasks, i.e., detection, segmentation, and grounding, as an instance-level sentence-object matching paradigm. Specifically, APE advances the convergence of detection and grounding by reformulating language-guided grounding as open-vocabulary detection, which efficiently scales up model prompting to thousands of category vocab-ularies and region descriptions while maintaining the ef-fectiveness of cross-modality fusion. To bridge the granu-larity gap of different pixel-level tasks, APE equalizes se-mantic and panoptic segmentation to proxy instance learning by considering any isolated regions as individual in-stances. APE aligns vision and language representation on broad data with natural and challenging characteristics all at once without task-specific fine-tuning. The extensive ex-periments on over 160 datasets demonstrate that, with only one-suit of weights, APE outperforms (or is on par with) the state-of-the-art models, proving that an effective yet univer-sal perception for anything aligning and prompting is in-deed feasible. Codes and trained models are released at https://github.com/shenyunhang/APE.

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement Learning from Human Feedback (RLHF).Despite its promising efficacy, DPO faces a notable drawback: "verbosity", a common over-optimization phenomenon also observed in RLHF.While previous studies mainly attributed verbosity to biased labels within the data, we propose that the issue also stems from an inherent algorithmic length reliance in DPO.Specifically, we suggest that the discrepancy between sequencelevel Kullback-Leibler (KL) divergences between chosen and rejected sequences, used in DPO, results in overestimated or underestimated rewards due to varying token lengths.Empirically, we utilize datasets with different label lengths to demonstrate the presence of biased rewards.We then introduce an effective downsampling approach, named SamPO, to eliminate potential length reliance.Our experimental evaluations, conducted across three LLMs of varying scales and a diverse array of conditional and open-ended benchmarks, highlight the efficacy of SamPO in mitigating verbosity, achieving improvements of 5% to 12% over DPO through debaised rewards 1 .

With the advent of large language models(LLMs) enhanced by the chain-of-thought(CoT) methodology, the visual reasoning problem is usually decomposed into manageable sub-tasks and tackled sequentially with various external tools. However, such a paradigm faces the challenge of the potential "determining hallucinations" in decision generation due to insufficient visual information and the limitation of low-level perception tools that fail to provide abstract summaries necessary for comprehensive reasoning. We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. This paper delves into the realm of multimodal CoT to solve intricate visual reasoning tasks with multimodal large language models(MLLMs) and their cognitive capability. To this end, we propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Cantor first acts as a decision generator and integrates visual inputs to analyze the image and problem, ensuring a closer alignment with the actual context. Furthermore, Cantor leverages the advanced cognitive functions of MLLMs to perform as multifaceted experts for deriving higher-level information, enhancing the CoT generation process. Our extensive experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance across two complex visual reasoning datasets, without necessitating fine-tuning or ground-truth rationales. Project Page: https://ggg0919.github.io/cantor/.

The integration of large language models into open-world detection frameworks significantly improves versatility in new environments. Prompt representations derived from these models help establish classification boundaries for both base and novel categories within open-world detectors. However, we are the first to discover that directly fine-tuning language models in detection systems results in redundant attention patterns and leads to suboptimal prompt representations. In order to fully leverage the capabilities of large language models and augment prompt encoding for detection, this study introduces a redundancy assessment metric to identify uniform attention patterns. Furthermore, in areas with high redundancy, we incorporate multimodal inplace prompt tuning (MIPT) to enrich the text prompt with visual clues. Experimental results validate the efficacy of our MIPT framework, achieving a notable increase across benchmarks, e.g. elevating GLIP-L from 22.6% to 25.0% on ODinW-35, and 9.0% improvement on LVIS.

We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt generation, enabling offline computations and improving performance. FastTCM-CR50 offers several advantages: 1) It can enhance existing text detectors and spotters, improving performance by an average of 1.6% and 1.5%, respectively. 2) It outperforms the previous TCM-CR50 backbone, yielding an average improvement of 0.2% and 0.55% in text detection and spotting tasks, along with a 47.1% increase in inference speed. 3) It showcases robust few-shot training capabilities. Utilizing only 10% of the supervised data, FastTCM-CR50 improves performance by an average of 26.5% and 4.7% for text detection and spotting tasks, respectively. 4) It consistently enhances performance on out-of-distribution text detection and spotting datasets, particularly the NightTime-ArT subset from ICDAR2019-ArT and the DOTA dataset for oriented object detection.

In this paper, we propose a novel span-level model for Aspect-Based Sentiment Analysis (ABSA), which aims at identifying the sentiment polarity of the given aspect.In contrast to conventional ABSA models that focus on modeling the word-level dependencies between an aspect and its corresponding opinion expressions, in this paper, we propose Table Filling BERT (TF-BERT), which considers the consistency of multi-word opinion expressions at the span-level.Specially, we learn the span representations with a table filling method, by constructing an upper triangular table for each sentiment polarity, of which the elements represent the sentiment intensities of the specific sentiment polarity for all spans in the sentence.Two methods are then proposed, including tabledecoding and table-aggregation, to filter out target spans or aggregate each table for sentiment polarity classification.In addition, we design a sentiment consistency regularizer to guarantee the sentiment consistency of each span for different sentiment polarities.Experimental results on three benchmarks demonstrate the effectiveness of our proposed model.

Temporal sentence grounding (TSG) aims to locate a specific moment from an untrimmed video with a given natural language query. Recently, weakly supervised methods still have a large performance gap compared to fully supervised ones, while the latter requires laborious timestamp annotations. In this study, we aim to reduce the annotation cost yet keep competitive performance for TSG task compared to fully supervised ones. To achieve this goal, we investigate a recently proposed glance-supervised temporal sentence grounding task, which requires only single frame annotation (referred to as glance annotation) for each query. Under this setup, we propose a Dynamic Gaussian prior based Grounding framework with Glance annotation (D3G), which consists of a Semantic Alignment Group Contrastive Learning module (SA-GCL) and a Dynamic Gaussian prior Adjustment module (DGA). Specifically, SA-GCL samples reliable positive moments from a 2D temporal map via jointly leveraging Gaussian prior and semantic consistency, which contributes to aligning the positive sentence-moment pairs in the joint embedding space. Moreover, to alleviate the annotation bias resulting from glance annotation and model complex queries consisting of multiple events, we propose the DGA module, which adjusts the distribution dynamically to approximate the ground truth of target moments. Extensive experiments on three challenging benchmarks verify the effectiveness of the proposed D3G. It outperforms the state-of-the-art weakly supervised methods by a large margin and narrows the performance gap compared to fully supervised methods. Code is available at https://github.com/solicucu/D3G.

We propose a novel end-to-end document understanding model called SeRum (SElective Region Understanding Model) for extracting meaningful information from document images, including document analysis, retrieval, and office automation. Unlike state-of-the-art approaches that rely on multi-stage technical schemes and are computationally expensive, SeRum converts document image understanding and recognition tasks into a local decoding process of the visual tokens of interest, using a content-aware token merge module. This mechanism enables the model to pay more attention to regions of interest generated by the query decoder, improving the model’s effectiveness and speeding up the decoding speed of the generative scheme. We also designed several pre-training tasks to enhance the understanding and local awareness of the model. Experimental results demonstrate that SeRum achieves state-of-the-art performance on document understanding tasks and competitive results on text spotting tasks. SeRum represents a substantial advancement towards enabling efficient and effective end-to-end document understanding.

Image retrieval targets to find images from a database that are visually similar to the query image. Two-stage methods following retrieve-and-rerank paradigm have achieved excellent performance, but their separate local and global modules are inefficient to real-world applications. To better trade-off retrieval efficiency and accuracy, some approaches fuse global and local feature into a joint representation to perform single-stage image retrieval. However, they are still challenging due to various situations to tackle, e.g., background, occlusion and viewpoint. In this work, we design a Coarse-to-Fine framework to learn Compact Discriminative representation (CFCD) for end-to-end single-stage image retrieval-requiring only image-level labels. Specifically, we first design a novel adaptive softmax-based loss which dynamically tunes its scale and margin within each mini-batch and increases them progressively to strengthen supervision during training and intraclass compactness. Furthermore, we propose a mechanism which attentively selects prominent local descriptors and infuse fine-grained semantic relations into the global representation by a hard negative sampling strategy to optimize inter-class distinctiveness at a global scale. Extensive experimental results have demonstrated the effectiveness of our method, which achieves state-of-the-art single-stage image retrieval performance on benchmarks such as Revisited Oxford and Revisited Paris. Code is available at https://github.com/bassyess/CFCD.

Webly supervised learning has attracted increasing attention for its effectiveness in exploring publicly accessible data at scale without manual annotation. However, most existing methods of learning with web datasets are faced with challenges from label noise, and they have limited assumptions on clean samples under various noise. For instance, web images retrieved with queries of ”tiger cat“ (a cat species) and ”drumstick“ (a musical instrument) are almost dominated by images of tigers and chickens, which exacerbates the challenge of fine-grained visual concept learning. In this case, exploiting both web images and their associated texts is a requisite solution to combat real-world noise. In this paper, we propose Cross-modality Aligned Prototypes (CAPro), a unified prototypical contrastive learning framework to learn visual representations with correct semantics. For one thing, we leverage textual prototypes, which stem from the distinct concept definition of classes, to select clean images by text matching and thus disambiguate the formation of visual prototypes. For another, to handle missing and mismatched noisy texts, we resort to the visual feature space to complete and enhance individual texts and thereafter improve text matching. Such semantically aligned visual prototypes are further polished up with high-quality samples, and engaged in both cluster regularization and noise removal. Besides, we propose collective bootstrapping to encourage smoother and wiser label reference from appearance-similar instances in a manner of dictionary look-up. Extensive experiments on WebVision1k and NUS-WIDE (Web) demonstrate that CAPro well handles realistic noise under both single-label and multi-label scenarios. CAPro achieves new state-of-the-art performance and exhibits robustness to open-set recognition. Codes are available at https://github.com/yuleiqin/capro.

Existing deep learning approaches for person re-identification (Re-ID) mostly rely on large-scale and well-annotated training data. However, human-annotated labels are prone to label noise in real-world applications. Previous person Re-ID works mainly focus on random label noise, which doesn’t properly reflect the characteristic of label noise in practical human-annotated process. In this work, we find the visual ambiguity noise is more common and reasonable noise assumption in annotation of person Re-ID. To handle the kind of noise, we propose a simple and effective robust person Re-ID framework, namely Graph-Based Self-Learning (GBSL), to iteratively learn discriminative representation and rectify noisy labels with limited annotated samples for each identity. Meanwhile, considering the practical annotation process in person Re-ID, we further extend the visual ambiguity noise assumption and propose a type of more practical label noise in person Re-ID, namely the tracklet-level label noise (TLN). Without modifying network architecture or loss function, our approach significantly improves the robustness against label noise of the Re-ID system. Our model obtains competitive performance with training data corrupted by various types of label noise and outperforms the existing methods for robust Re-ID on public benchmarks.

Co-salient object detection (Co-SOD) aims at discovering the common objects in a group of relevant images. Mining a co-representation is essential for locating co-salient objects. Unfortunately, the current Co-SOD method does not pay enough attention that the information not related to the co-salient object is included in the co-representation. Such irrelevant information in the co-representation interferes with its locating of co-salient objects. In this paper, we propose a Co-Representation Purification (CoRP) method aiming at searching noise-free co-representation. We search a few pixel-wise embeddings probably belonging to co-salient regions. These embeddings constitute our co-representation and guide our prediction. For obtaining purer co-representation, we use the prediction to iteratively reduce irrelevant embeddings in our co-representation. Experiments on three datasets demonstrate that our CoRP achieves state-of-the-art performances on the benchmark datasets. Our source code is available at https://github.com/ZZY816/CoRP.

Vision transformers (ViTs) have recently received explosive popularity, but the huge computational cost is still a severe issue. Since the computation complexity of ViT is quadratic with respect to the input sequence length, a mainstream paradigm for computation reduction is to reduce the number of tokens. Existing designs include structured spatial compression that uses a progressive shrinking pyramid to reduce the computations of large feature maps, and unstructured token pruning that dynamically drops redundant tokens. However, the limitation of existing token pruning lies in two folds: 1) the incomplete spatial structure caused by pruning is not compatible with structured spatial compression that is commonly used in modern deep-narrow transformers; 2) it usually requires a time-consuming pre-training procedure. To tackle the limitations and expand the applicable scenario of token pruning, we present Evo-ViT, a self-motivated slow-fast token evolution approach for vision transformers. Specifically, we conduct unstructured instance-wise token selection by taking advantage of the simple and effective global class attention that is native to vision transformers. Then, we propose to update the selected informative tokens and uninformative tokens with different computation paths, namely, slow-fast updating. Since slow-fast updating mechanism maintains the spatial structure and information flow, Evo-ViT can accelerate vanilla transformers of both flat and deep-narrow structures from the very beginning of the training process. Experimental results demonstrate that our method significantly reduces the computational cost of vision transformers while maintaining comparable performance on image classification. For example, our method accelerates DeiT-S by over 60% throughput while only sacrificing 0.4% top-1 accuracy on ImageNet-1K, outperforming current token pruning methods on both accuracy and efficiency.

Current Image Captioning (IC) methods predict textual words sequentially based on the input visual information from the visual feature extractor and the partially generated sentence information. However, for most cases, the partially generated sentence may dominate the target word prediction due to the insufficiency of visual information, making the generated descriptions irrelevant to the content of the given image. In this paper, we propose a Dual Information Flow Network (DIFNet11Source code is available at: https://github.com/mrwu-mac/DIFNet) to address this issue, which takes segmentation feature as another visual information source to enhance the contribution of visual information for prediction. To maximize the use of two information flows, we also propose an effective feature fusion module termed Iterative Independent Layer Normalization (IILN) which can condense the most relevant inputs while retraining modality-specific information in each flow. Experiments show that our method is able to enhance the dependence of prediction on visual information, making word prediction more focused on the visual content, and thus achieves new state-of-the-art performance on the MSCOCO dataset, e.g., 136.2 CIDEr on COCO Karpathy test split.

Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks. The progresses are highly relevant to the architecture design, then it is worthwhile to propose Transformer Architecture Search (TAS) to search for better ViTs automatically. However, current TAS methods are time-consuming and existing zero-cost proxies in CNN do not generalize well to the ViT search space according to our experimental observations. In this paper, for the first time, we investigate how to conduct TAS in a training-free manner and devise an effective training-free TAS (TF-TAS) scheme. Firstly, we observe that the properties of multi-head self-attention (MSA) and multi-layer perceptron (MLP) in ViTs are quite different and that the synaptic diversity of MSA affects the performance notably. Secondly, based on the observation, we devise a modular strategy in TF-TAS that evaluates and ranks ViT architectures from two theoretical perspectives: synaptic diversity and synaptic saliency, termed as DSS-indicator. With DSS-indicator, evaluation results are strongly corre-lated with the test accuracies of ViT models. Experimental results demonstrate that our TF- TAS achieves a competitive performance against the state-of-the-art manually or automatically design ViT architectures, and it promotes the searching efficiency in ViT search space greatly: from about 24 GPU days to less than 0.5 GPU days. Moreover, the proposed DSS-indicator outperforms the existing cutting-edge zero-cost approaches (e.g., TE-score and NASWOT).

Transformers have shown remarkable progress on computer vision tasks in the past year. Compared to their CNN counterparts, transformers usually need the help of distillation to achieve comparable results on middle or small sized datasets. Meanwhile, recent researches discover that when transformers are trained with supervised and self-supervised manner respectively, the captured patterns are quite different both qualitatively and quantitatively. These findings motivate us to introduce an self-supervised teaching assistant (SSTA) besides the commonly used supervised teacher to improve the performance of transformers. Specifically, we propose a head-level knowledge distillation method that selects the most important head of the supervised teacher and self-supervised teaching assistant, and let the student mimic the attention distribution of these two heads, so as to make the student focus on the relationship between tokens deemed by the teacher and the teacher assistant. Extensive experiments verify the effectiveness of SSTA and demonstrate that the proposed SSTA is a good compensation to the supervised teacher. Meanwhile, some analytical experiments towards multiple perspectives (e.g. prediction, shape bias, robustness, and transferability to downstream tasks) with supervised teachers, self-supervised teaching assistants and students are inductive and may inspire future researches.

Text-based person search aims at retrieving the target person in an image gallery using a descriptive sentence of that person. The core of this task is to calculate a similarity score between the pedestrian image and description, which requires inferring the complex latent correspondence between image sub-regions and textual phrases at different scales. Transformer is an intuitive way to model the complex alignment by its self-attention mechanism. Most previous Transformer-based methods simply concatenate image region features and text features as input and learn a cross-modal representation in a brute force manner. Such weakly supervised learning approaches fail to explicitly build alignment between image region features and text features, causing an inferior feature distribution. In this paper, we present CFLT, Conditional Feature Learning based Transformer. It maps the sub-regions and phrases into a unified latent space and explicitly aligns them by constructing conditional embeddings where the feature of data from one modality is dynamically adjusted based on the data from the other modality. The output of our CFLT is a set of similarity scores for each sub-region or phrase rather than a cross-modal representation. Furthermore, we propose a simple and effective multi-modal re-ranking method named Re-ranking scheme by Visual Conditional Feature (RVCF). Benefit from the visual conditional feature and better feature distribution in our CFLT, the proposed RVCF achieves significant performance improvement. Experimental results show that our CFLT outperforms the state-of-the-art methods by 7.03% in terms of top-1 accuracy and 5.01% in terms of top-5 accuracy on the text-based person search dataset.

Although Person Re-Identification has made impressive progress, difficult cases like occlusion, change of view-point, and similar clothing still bring great challenges. In order to tackle these challenges, extracting discriminative feature representation is crucial. Most of the existing methods focus on extracting ReID features from individual images separately. However, when matching two images, we propose that the ReID features of a query image should be dynamically adjusted based on the contextual information from the gallery image it matches. We call this type of ReID features conditional feature embedding. In this paper, we propose a novel ReID framework that extracts conditional feature embedding based on the aligned visual clues between image pairs, called Clue Alignment based Conditional Embedding (CACE-Net). CACE-Net applies an attention module to build a detailed correspondence graph between crucial visual clues in image pairs and uses discrepancy-based GCN to embed the obtained complex correspondence information into the conditional features. The experiments show that CACE-Net achieves state-of-the-art performance on three public datasets.

One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action categories are highly related with the scene where the action happens, making the model tend to degrade to a solution where only the scene information is encoded. For example, a trained model may predict a video as playing football simply because it sees the field, neglecting that the subject is dancing as a cheerleader on the field. This is against our original intention towards the video representation learning and may bring scene bias on a different dataset that can not be ignored. In order to tackle this problem, we propose to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid. Specifically, we construct a positive clip and a negative clip for each video. Compared to the original video, the positive/negative is motion-untouched/broken but scene-broken/untouched by Spatial Local Disturbance and Temporal Local Disturbance. Our objective is to pull the positive closer while pushing the negative farther to the original clip in the latent space. In this way, the impact of the scene is weakened while the temporal sensitivity of the network is further enhanced. We conduct experiments on two tasks with various backbones and different pre-training datasets, and find that our method surpass the SOTA methods with a remarkable 8.1% and 8.8% improvement towards action recognition task on the UCF101 and HMDB51 datasets respectively using the same backbone.

Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch. It will inevitably cause the model to over-fit the data in the dominant position (e.g., head data in imbalanced class, easy samples or noisy samples). The latest resampling methods address the issue by designing specific criterion to select specific samples that trains the model generalize more on certain type of data (e.g., hard samples, tail data), which is not adaptive to the inconsistent real world ReID data distributions. Therefore, instead of simply presuming on what samples are generalizable, this paper proposes a one-for-more training objective that directly takes the generalization ability of selected samples as a loss function and learn a sampler to automatically select generalizable samples. More importantly, our proposed one-for-more based sampler can be seamlessly integrated into the ReID training framework which is able to simultaneously train ReID models and the sampler in an end-to-end fashion. The experimental results show that our method can effectively improve the ReID model training and boost the performance of ReID models.

It is well acknowledged that person re-identification (person ReID) highly relies on visual texture information like clothing. Despite significant progress has been made in recent years, texture-confusing situations like clothing changing and persons wearing the same clothes receive little attention from most existing ReID methods. In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person’s 3D shape. Existing shape learning schemas for person ReID either ignore the 3D information of a person, or require extra physical devices to collect 3D source data. Differently, we propose a novel ReID learning framework that directly extracts a texture-insensitive 3D shape embedding from a 2D image by adding 3D body reconstruction as an auxiliary task and regularization, called 3D Shape Learning (3DSL). The 3D reconstruction based regularization forces the ReID model to decouple the 3D shape information from the visual texture, and acquire discriminative 3D shape ReID features. To solve the problem of lacking 3D ground truth, we design an adversarial self-supervised projection (ASSP) model, performing 3D reconstruction without ground truth. Extensive experiments on common ReID datasets and texture-confusing datasets validate the effectiveness of our model.

Self-supervised learning has shown great potentials in improving the video representation ability of deep neural networks by getting supervision from the data itself. However, some of the current methods tend to cheat from the background, i.e., the prediction is highly dependent on the video background instead of the motion, making the model vulnerable to background changes. To mitigate the model reliance towards the background, we propose to remove the background impact by adding the background. That is, given a video, we randomly select a static frame and add it to every other frames to construct a distracting video sample. Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes. We term our method as Background Erasing (BE). It is worth noting that the implementation of our method is so simple and neat and can be added to most of the SOTA methods without much efforts. Specifically, BE brings 16.4% and 19.1% improvements with MoCo on the severely biased datasets UCF101 and HMDB51, and 14.5% improvement on the less biased dataset Diving48.

Space-time video super-resolution (STVSR) aims to increase the spatial and temporal resolutions of low-resolution and low-frame-rate videos. Recently, deformable convolution based methods have achieved promising STVSR performance, but they could only infer the intermediate frame pre-defined in the training stage. Besides, these methods undervalued the short-term motion cues among adjacent frames. In this paper, we propose a Temporal Modulation Network (TMNet) to interpolate arbitrary intermediate frame(s) with accurate high-resolution reconstruction. Specifically, we propose a Temporal Modulation Block (TMB) to modulate deformable convolution kernels for controllable feature interpolation. To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos. Experiments on three benchmark datasets demonstrate that our TMNet outperforms previous STVSR methods. The code is available at https://github.com/CS-GangXu/TMNet.

Text-based image retrieval has seen considerable progress in recent years. However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description. In this work, we introduce the partial-query problem and extensively analyze its influence on text-based image retrieval. Previous interactive methods tackle the problem by passively receiving users’ feedback to supplement the incomplete query iteratively, which is time-consuming and requires heavy user effort. Instead, we propose a novel retrieval framework that conducts the interactive process in an Ask-and-Confirm fashion, where AI actively searches for discriminative details missing in the current query, and users only need to confirm AI’s proposal. Specifically, we propose an object-based interaction to make the interactive retrieval more user-friendly and present a reinforcement-learning-based policy to search for discriminative objects. Furthermore, since fully-supervised training is often infeasible due to the difficulty of obtaining human-machine dialog data, we present a weakly-supervised training strategy that needs no human-annotated dialogs other than a text-image dataset. Experiments show that our framework significantly improves the performance of text-based image retrieval. Code is available at https://github.com/CuthbertCai/Ask-Confirm.

Personalized video highlight detection aims to shorten a long video to interesting moments according to a user’s preference, which has recently raised the community’s attention. Current methods regard the user’s history as holistic information to predict the user’s preference but negating the inherent diversity of the user’s interests, resulting in vague preference representation. In this paper, we propose a simple yet efficient preference reasoning framework (PR-Net) to explicitly take the diverse interests into account for frame-level highlight prediction. Specifically, distinct user-specific preferences for each input query frame are produced, presented as the similarity weighted sum of history highlights to the corresponding query frame. Next, distinct comprehensive preferences are formed by the user-specific preferences and a learnable generic preference for more overall highlight measurement. Lastly, the degree of highlight and non-highlight for each query frame is calculated as semantic similarity to its comprehensive and non-highlight preferences, respectively. Besides, to alleviate the ambiguity due to the incomplete annotation, a new bidirectional contrastive loss is proposed to ensure a compact and differentiable metric space. In this way, our method significantly outperforms state-of-the-art methods with a relative improvement of 12% in mean accuracy precision.

In this paper, we focus on recognizing 3D shapes from arbitrary views, i.e., arbitrary numbers and positions of viewpoints. It is a challenging and realistic setting for view-based 3D shape recognition. We propose a canonical view representation to tackle this challenge. We first transform the original features of arbitrary views to a fixed number of view features, dubbed canonical view representation, by aligning the arbitrary view features to a set of learnable reference view features using optimal transport. In this way, each 3D shape with arbitrary views is represented by a fixed number of canonical view features, which are further aggregated to generate a rich and robust 3D shape representation for shape recognition. We also propose a canonical view feature separation constraint to enforce that the view features in canonical view representation can be embedded into scattered points in a Euclidean space. Experiments on the ModelNet40, ScanObjectNN, and RGBD datasets show that our method achieves competitive results under the fixed viewpoint settings, and significantly outperforms the applicable methods under the arbitrary view setting.

Person re-identification (ReID) has gained an impressive progress in recent years. However, the occlusion is still a common and challenging problem for recent ReID methods. Several mainstream methods utilize extra cues (e.g., human pose information) to distinguish human parts from obstacles to alleviate the occlusion problem. Although achieving inspiring progress, these methods severely rely on the fine-grained extra cues, and are sensitive to the estimation error in the extra cues. In this paper, we show that existing methods may degrade if the extra information is sparse or noisy. Thus we propose a simple yet effective method that is robust to sparse and noisy pose information. This is achieved by discretizing pose information to the visibility label of body parts, so as to suppress the influence of occluded regions. We show in our experiments that leveraging pose information in this way is more effective and robust. Besides, our method can be embedded into most person ReID models easily. Extensive experiments validate the effectiveness of our model on common occluded person ReID datasets.

Multi-modal cues presented in videos are usually beneficial for the challenging video-text retrieval task on internet-scale datasets. Recent video retrieval methods take advantage of multi-modal cues by aggregating them to holistic high-level semantics for matching with text representations in a global view. In contrast to this global alignment, the local alignment of detailed semantics encoded within both multi-modal cues and distinct phrases is still not well conducted. Thus, in this paper, we leverage the hierarchical video-text alignment to fully explore the detailed diverse characteristics in multi-modal cues for fine-grained alignment with local semantics from phrases, as well as to capture a high-level semantic correspondence. Specifically, multi-step attention is learned for progressively comprehensive local alignment and a holistic transformer is utilized to summarize multi-modal cues for global alignment. With hierarchical alignment, our model outperforms state-of-the-art methods on three public video retrieval datasets.

The Deep Neural Networks are vulnerable to adversarial examples (Figure 1), making the DNNs-based systems collapsed by adding the inconspicuous perturbations to the images. Most of the existing works for adversarial attack are gradient-based and suffer from the latency efficiencies and the load on GPU memory. The generative-based adversarial attacks can get rid of this limitation, and some relative works propose the approaches based on GAN. However, suffering from the difficulty of the convergence of training a GAN, the adversarial examples have either bad attack ability or bad visual quality. In this work, we find that the discriminator could be not necessary for generative-based adversarial attack, and propose the Symmetric Saliency-based Auto-Encoder (SSAE) to generate the perturbations, which is composed of the saliency map module and the angle-norm disentanglement of the features module. The advantage of our proposed method lies in that it is not depending on discriminator, and uses the generative saliency map to pay more attention to label-relevant regions. The extensive experiments among the various tasks, datasets, and models demonstrate that the adversarial examples generated by SSAE not only make the widely-used models collapse, but also achieves good visual quality. The code is available at: https://github.com/BravoLu/SSAE.

We consider the problem of high-dimensional light field reconstruction and develop a learning-based framework for spatial and angular super-resolution. Many current approaches either require disparity clues or restore the spatial and angular details separately. Such methods have difficulties with non-Lambertian surfaces or occlusions. In contrast, we formulate light field super-resolution (LFSR) as tensor restoration and develop a learning framework based on a two-stage restoration with 4-dimensional (4D) convolution. This allows our model to learn the features capturing the geometry information encoded in multiple adjacent views. Such geometric features vary near the occlusion regions and indicate the foreground object border. To train a feasible network, we propose a novel normalization operation based on a group of views in the feature maps, design a stage-wise loss function, and develop the multi-range training strategy to further improve the performance. Evaluations are conducted on a number of light field datasets including real-world scenes, synthetic data, and microscope light fields. The proposed method achieves superior performance and less execution time comparing with other state-of-the-art schemes.

Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video. However, existing video-based ReID methods do not consider the semantic difference brought by the outputs of different network stages, which potentially compromises the information richness of the person features. Furthermore, traditional methods ignore important relationship among frames, which causes information redundancy in fusion along the time axis. To address these issues, we propose a novel general temporal fusion framework to aggregate frame features on both semantic aspect and time aspect. As for the semantic aspect, a multi-stage fusion network is explored to fuse richer frame features at multiple semantic levels, which can effectively reduce the information loss caused by the traditional single-stage fusion. While, for the time axis, the existing intra-frame attention method is improved by adding a novel inter-frame attention module, which effectively reduces the information redundancy in temporal fusion by taking the relationship among frames into consideration. The experimental results show that our approach can effectively improve the video-based re-identification accuracy, achieving the state-of-the-art performance.

Person re-identification (re-ID), is a challenging task due to the high variance within identity samples and imaging conditions. Although recent advances in deep learning have achieved remarkable accuracy in settled scenes, i.e., source domain, few works can generalize well on the unseen target domain. One popular solution is assigning unlabeled target images with pseudo labels by clustering, and then retraining the model. However, clustering methods tend to introduce noisy labels and discard low confidence samples as outliers, which may hinder the retraining process and thus limit the generalization ability. In this study, we argue that by explicitly adding a sample filtering procedure after the clustering, the mined examples can be much more efficiently used. To this end, we design an asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other. Meanwhile, one of the models receives samples as pure as possible, while the other takes in samples as diverse as possible. This procedure encourages that the selected training samples can be both clean and miscellaneous, and that the two models can promote each other iteratively. Extensive experiments show that the proposed framework can consistently benefit most clustering based methods, and boost the state-of-the-art adaptation accuracy. Our code is available at https://github.com/FlyingRoastDuck/ACT_AAAI20.

Although great progress in supervised person re-identification (Re-ID) has been made recently, due to the viewpoint variation of a person, Re-ID remains a massive visual challenge. Most existing viewpoint-based person Re-ID methods project images from each viewpoint into separated and unrelated sub-feature spaces. They only model the identity-level distribution inside an individual viewpoint but ignore the underlying relationship between different viewpoints. To address this problem, we propose a novel approach, called Viewpoint-Aware Loss with Angular Regularization (VA-reID). Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level. In addition, rather than modeling different viewpoints as hard labels used for conventional viewpoint classification, we introduce viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation. VALSR can effectively solve the ambiguity of the viewpoint cluster label assignment. Extensive experiments on the Market1501 and DukeMTMC-reID datasets demonstrated that our method outperforms the state-of-the-art supervised Re-ID methods.

This paper proposes a new learning paradigm called filter grafting, which aims to improve the representation capability of Deep Neural Networks (DNNs). The motivation is that DNNs have unimportant (invalid) filters (e.g., l1norm close to 0). These filters limit the potential of DNNs since they are identified as having little effect on the network. While filter pruning removes these invalid filters for efficiency consideration, filter grafting re-activates them from an accuracy boosting perspective. The activation is processed by grafting external information (weights) into invalid filters. To better perform the grafting process, we develop an entropy-based criterion to measure the information of filters and an adaptive weighting strategy for balancing the grafted information among networks. After the grafting operation, the network has very few invalid filters compared with its untouched state, empowering the model with more representation capacity. We also perform extensive experiments on the classification and recognition tasks to show the superiority of our method. For example, the grafted MobileNetV2 outperforms the non-grafted MobileNetV2 by about 7 percent on CIFAR-100 dataset.

Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will potentially lead to a lower recall rate and a higher threshold introduces more false positives. This problem is more severe in pedestrian detection because the instance density varies more intensively. However, previous works on NMS don't consider or vaguely consider the factor of the existent of nearby pedestrians. Thus, we propose \heatmapname (\heatmapnameshort ), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with \nmsname, which dynamically eases the suppression for the space that might contain other objects with a high likelihood. Compared to Greedy-NMS, our method, as the state-of-the-art, improves by $3.9%$ AP, $5.1%$ Recall, and $0.8%$ MR\textsuperscript-2 on CrowdHuman to $89.0%$ AP and $92.9%$ Recall, and $43.9%$ MR\textsuperscript-2 respectively.

Pruning has become a very powerful and effective technique to compress and accelerate modern neural networks. Existing pruning methods can be grouped into two categories: filter pruning (FP) and weight pruning (WP). FP wins at hardware compatibility but loses at the compression ratio compared with WP. To converge the strength of both methods, we propose to prune the filter in the filter. Specifically, we treat a filter F, whose size is CKK, as KK stripes, i.e., 11 filters, then by pruning the stripes instead of the whole filter, we can achieves finer granularity than traditional FP while being hardware friendly. We term our method as SWP (Stripe-Wise Pruning). SWP is implemented by introducing a novel learnable matrix called Filter Skeleton, whose values reflect the optimal shape of each filter. As some recent work has shown that the pruned architecture is more crucial than the inherited important weights, we argue that the architecture of a single filter, i.e., the Filter Skeleton, also matters. Through extensive experiments, we demonstrate that SWP is more effective compared to the previous FP-based methods and achieves the state-of-art pruning ratio on CIFAR-10 and ImageNet datasets without obvious accuracy drop.

Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other. However, due to the challenging practical scenarios, current detection models often produce inaccurate bounding boxes, which inevitably degenerate the performance of existing Re-ID algorithms. In this paper, we propose a novel coarse-to-fine pyramid model to relax the need of bounding boxes, which not only incorporates local and global information, but also integrates the gradual cues between them. The pyramid model is able to match at different scales and then search for the correct image of the same identity, even when the image pairs are not aligned. In addition, in order to learn discriminative identity representation, we explore a dynamic training scheme to seamlessly unify two losses and extract appropriate shared information between them. Experimental results clearly demonstrate that the proposed method achieves the state-of-the-art results on three datasets. Especially, our approach exceeds the current best method by 9.5% on the most challenging CUHK03 dataset.

The Dirichlet process (DP) prior is effective in modeling HSIs (HSI) and identifying land-cover classes. However, modeling a continuously varying intensity of these land covers elegantly and consistently is still a challenge. We propose a doubly stochastic DP (DSDP) as an efficient model of the global topic measurement space, which imposes a weaker assumption compared with the discrete Markov assumption, resulting in a lower computational cost than other DP-prior-based models. We also present a mixture model of DSDP, which is termed the marked sigmoidal Gaussian process (SGP) DSDP mixture model. It can be thinned from a DP mixture without massive auxiliary covariates, and the marked function prior makes the number of land-cover classes consistent, whereas the SGP function prior models the HSI land-cover variation globally. The consistency of the number of land covers is maintained for various HSIs with large-scale geographical areas. Experiments show that the model is robust and consistent on HSI identification with weak or even no supervision.

In this paper, we present a sparse hierarchical non-parametric Bayesian (SHNB) model, which is used to represent the data captured by the light field cameras. Specifically, a light field can be represented as a set of sub-aperture views. In order to capture the visual variations of these viewpoints, we propose the so-called “depth flow” features. Then based on the depth flow features, we model these views statistically with a sparse representation in a fully unsupervised manner. While local dictionaries are learned based on each sub-aperture view, all the views with different perspectives share one global dictionary. To show the effectiveness of the proposed model, we apply our model to denoise the light field data. In the experiments, we demonstrate that our method outperforms several state-of-the-art light field denoising approaches.

This paper presents a data-driven approach to estimate the object depths from light field data using Convolutional Neural Networks (CNN). By exploring the relationship between the epipolar-plane images (EPI) and the corresponding depth map, we propose an enhanced EPI feature that encodes the depth information of each physical point in the light field and obtains the disparity map of the whole scene in a supervised manner. This work covers two major contributions, namely the extraction of the enhanced EPI features and the light field depth estimation with CNN. The proposed features augment the depth information of the corresponding points in the light field, and then our CNN architecture differentiates them into different depth layers. Forward propagation step of the CNN model allows rapid recognition of the disparity map of the test light field data. In the experiments, we apply our method on the HCI (Heidelberg Col-laboratory for Image Processing) benchmark dataset and demonstrate that it is significantly faster than the state-of-the-art light field depth estimation approaches while achieving satisfactory performance.

We present an unsupervised tracking algorithm for human and car trajectory detection, using what is called the temporal doubly stochastic Dirichlet process (TDSDP) mixture model. The TDSDP captures the global dependence and the variation of human crowds and cars in temporal domains without the Markov assumption, making it particularly suitable for long-term tracking. Moreover, TDSDP prior can estimate the number of trajectories automatically. We first define the TDSDP based on the Cox process and then explain how to construct a TDSDP mixture model from thinning multiple Dirichlet process mixtures (DPMs) with conjugate priors. Next, a Markov chain Monte Carlo sampling inference is presented. Experimental results on synthetic and real-world data demonstrate that the proposed TDSDP mixture is superior to the DPM and the dependent Dirichlet process (DDP) in terms of topic variation modeling. PETS2001 data set experiments show that TDSDP has more robust object tracking capability over DDP based on generalized Polya urn. Low-quality fish data set experiments indicate that the TDSDP excels at solving tracking problems with insufficient features.

There are two main contributions in this paper: (1) A new hierarchical sparse coding algorithm is proposed, which combines hard and soft assignment coding in a fully unsupervised manner for image categorization. Hard coding assigns data into independent cluster globally to enable local dictionary learning to be learned by soft coding. The new coding algorithm is characterized by better fitting of data, more discriminative global clustering, low computational complexity and convergence speed up. (2) We utilize variational inference optimization on large data to solve regularized and optimization problem in the proposed hard soft sparse coding algorithm. Different from other convex optimization algorithm for sparse coding, the proposed algorithm has no limitation or preference on the data with proper prior estimation. In our experiments, we tested MIT 8 scene categories data-set and achieved a 10% improvement on the best existing algorithm with faster convergence rate.