Weiyao Lin

Tao Wang, Ning Xu, Kean Chen et al.

Video instance segmentation is a challenging task that extends image instance segmentation to the video domain. Existing methods either rely only on single-frame information for the detection and segmentation subproblems or handle tracking as a separate post-processing step, which limit their capability to fully leverage and share useful spatial-temporal information for all the subproblems. In this paper, we propose a novel graph-neural-network (GNN) based method to handle the aforementioned limitation. Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking. Both inter and intra-frame information is effectively propagated and shared via graph updates and all the subproblems (i.e. detection, segmentation and tracking) are jointly optimized in an unified framework. The performance of our method shows great improvement on the YoutubeVIS validation dataset compared to existing methods and achieves 35.2% AP with a ResNet-50 backbone, operating at 22 FPS. Code is available at http://github.com/lucaswithai/visgraph.git .

Huabin Liu, Weixian Lv, John See et al.

A primary challenge faced in few-shot action recognition is inadequate video data for training. To address this issue, current methods in this field mainly focus on devising algorithms at the feature level while little attention is paid to processing input video data. Moreover, existing frame sampling strategies may omit critical action information in temporal and spatial dimensions, which further impacts video utilization efficiency. In this paper, we propose a novel video frame sampler for few-shot action recognition to address this issue, where task-specific spatial-temporal frame sampling is achieved via a temporal selector (TS) and a spatial amplifier (SA). Specifically, our sampler first scans the whole video at a small computational cost to obtain a global perception of video frames. The TS plays its role in selecting top-T frames that contribute most significantly and subsequently. The SA emphasizes the discriminative information of each frame by amplifying critical regions with the guidance of saliency maps. We further adopt task-adaptive learning to dynamically adjust the sampling strategy according to the episode task at hand. Both the implementations of TS and SA are differentiable for end-to-end optimization, facilitating seamless integration of our proposed sampler with most few-shot action recognition methods. Extensive experiments show a significant boost in the performances on various benchmarks including long-term videos.The code is available at https://github.com/R00Kie-Liu/Sampler

Zelin Ni, Hang Yu, Shizhan Liu et al.

Bases have become an integral part of modern deep learning-based models for time series forecasting due to their ability to act as feature extractors or future references. To be effective, a basis must be tailored to the specific set of time series data and exhibit distinct correlation with each time series within the set. However, current state-of-the-art methods are limited in their ability to satisfy both of these requirements simultaneously. To address this challenge, we propose BasisFormer, an end-to-end time series forecasting architecture that leverages learnable and interpretable bases. This architecture comprises three components: First, we acquire bases through adaptive self-supervised learning, which treats the historical and future sections of the time series as two distinct views and employs contrastive learning. Next, we design a Coef module that calculates the similarity coefficients between the time series and bases in the historical view via bidirectional cross-attention. Finally, we present a Forecast module that selects and consolidates the bases in the future view based on the similarity coefficients, resulting in accurate future predictions. Through extensive experiments on six datasets, we demonstrate that BasisFormer outperforms previous state-of-the-art methods by 11.04\% and 15.78\% respectively for univariate and multivariate forecasting tasks. Code is available at: \url{https://github.com/nzl5116190/Basisformer}

Tao Wang, Kean Chen, Weiyao Lin et al.

Multiple Object Tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often hinder the final performance. Furthermore, most existing research are focusing on improving detection algorithms and association strategies. As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories. In particular, we formulate such "bad" detection results as a sequence of events and adopt the spatio-temporal point process}to model such events. Traditionally, the occurrence rate in a point process is characterized by an explicitly defined intensity function, which depends on the prior knowledge of some specific tasks. Thus, designing a proper model is expensive and time-consuming, with also limited ability to generalize well. To tackle this problem, we adopt the convolutional recurrent neural network (conv-RNN) to instantiate the point process, where its intensity function is automatically modeled by the training data. Furthermore, we show that our method captures both temporal and spatial evolution, which is essential in modeling events for MOT. Experimental results demonstrate notable improvements in addressing noisy and confusing detection results in MOT datasets. An improved state-of-the-art performance is achieved by incorporating our baseline MOT algorithm with the spatio-temporal point process model.

Jinlong Peng, Zekun Luo, Liang Liu et al.

Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image. Existing methods perform the same harmonization process for the whole foreground. However, the implanted foreground always contains different appearance patterns. All the existing solutions ignore the difference of each color block and losing some specific details. Therefore, we propose a novel global-local two stages framework for Fine-grained Region-aware Image Harmonization (FRIH), which is trained end-to-end. In the first stage, the whole input foreground mask is used to make a global coarse-grained harmonization. In the second stage, we adaptively cluster the input foreground mask into several submasks by the corresponding pixel RGB values in the composite image. Each submask and the coarsely adjusted image are concatenated respectively and fed into a lightweight cascaded module, adjusting the global harmonization performance according to the region-aware local feature. Moreover, we further designed a fusion prediction module by fusing features from all the cascaded decoder layers together to generate the final result, which could utilize the different degrees of harmonization results comprehensively. Without bells and whistles, our FRIH algorithm achieves the best performance on iHarmony4 dataset (PSNR is 38.19 dB) with a lightweight model. The parameters for our model are only 11.98 M, far below the existing methods.

Ziran Qin, Mingbao Lin, Weiyao Lin

This paper focuses on Winograd transformation in 3D convolutional neural networks (CNNs) that are more over-parameterized compared with the 2D version. The over-increasing Winograd parameters not only exacerbate training complexity but also barricade the practical speedups due simply to the volume of element-wise products in the Winograd domain. We attempt to reduce trainable parameters by introducing a low-rank Winograd transformation, a novel training paradigm that decouples the original large tensor into two less storage-required trainable tensors, leading to a significant complexity reduction. Built upon our low-rank Winograd transformation, we take one step ahead by proposing a low-rank oriented sparse granularity that measures column-wise parameter importance. By simply involving the non-zero columns in the element-wise product, our sparse granularity is empowered with the ability to produce a very regular sparse pattern to acquire effectual Winograd speedups. To better understand the efficacy of our method, we perform extensive experiments on 3D CNNs. Results manifest that our low-rank Winograd transformation well outperforms the vanilla Winograd transformation. We also show that our proposed low-rank oriented sparse granularity permits practical Winograd acceleration compared with the vanilla counterpart.

Yihang Chen, Qianyi Wu, Weiyao Lin et al.

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To address this, we make use of the relations between the unorganized anchors and the structured hash grid, leveraging their mutual information for context modeling, and propose a Hash-grid Assisted Context (HAC) framework for highly compact 3DGS representation. Our approach introduces a binary hash grid to establish continuous spatial consistencies, allowing us to unveil the inherent spatial relations of anchors through a carefully designed context model. To facilitate entropy coding, we utilize Gaussian distributions to accurately estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Additionally, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Importantly, our work is the pioneer to explore context-based compression for 3DGS representation, resulting in a remarkable size reduction of over $75\times$ compared to vanilla 3DGS, while simultaneously improving fidelity, and achieving over $11\times$ size reduction over SOTA 3DGS compression approach Scaffold-GS. Our code is available here: https://github.com/YihangChen-ee/HAC

Yuang Zhang, Tiancai Wang, Weiyao Lin et al.

We present our 1st place solution to the Group Dance Multiple People Tracking Challenge. Based on MOTR: End-to-End Multiple-Object Tracking with Transformer, we explore: 1) detect queries as anchors, 2) tracking as query denoising, 3) joint training on pseudo video clips generated from CrowdHuman dataset, and 4) using the YOLOX detection proposals for the anchor initialization of detect queries. Our method achieves 73.4% HOTA on the DanceTrack test set, surpassing the second-place solution by +6.8% HOTA.

Tieyuan Chen, Huabin Liu, Tianyao He et al.

Video causal reasoning aims to achieve a high-level understanding of video content from a causal perspective. However, current video reasoning tasks are limited in scope, primarily executed in a question-answering paradigm and focusing on short videos containing only a single event and simple causal relationships, lacking comprehensive and structured causality analysis for videos with multiple events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relationships between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD requires identifying the causal associations between these events to derive a comprehensive, structured event-level video causal diagram explaining why and how the final result event occurred. To address MECD, we devise a novel framework inspired by the Granger Causality method, using an efficient mask-based event prediction model to perform an Event Granger Test, which estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to address challenges in MECD like causality confounding and illusory causality. Experiments validate the effectiveness of our framework in providing causal relationships in multi-event videos, outperforming GPT-4o and VideoLLaVA by 5.7% and 4.1%, respectively.

Ziran Qin, Yuchen Cao, Mingbao Lin et al.

Large language models (LLMs) excel at processing long sequences, boosting demand for key-value (KV) caching. While recent efforts to evict KV cache have alleviated the inference burden, they often fail to allocate resources rationally across layers with different attention patterns. In this paper, we introduce Cascading and Adaptive KV cache Eviction (CAKE), a novel approach that frames KV cache eviction as a "cake-slicing problem." CAKE assesses layer-specific preferences by considering attention dynamics in both spatial and temporal dimensions, allocates rational cache size for layers accordingly, and manages memory constraints in a cascading manner. This approach enables a global view of cache allocation, adaptively distributing resources across diverse attention mechanisms while maintaining memory budgets. CAKE also employs a new eviction indicator that considers the shifting importance of tokens over time, addressing limitations in existing methods that overlook temporal dynamics. Comprehensive experiments on LongBench and NeedleBench show that CAKE maintains model performance with only 3.2% of the KV cache and consistently outperforms current baselines across various models and memory constraints, particularly in low-memory settings. Additionally, CAKE achieves over 10x speedup in decoding latency compared to full cache when processing contexts of 128K tokens with FlashAttention-2. Our code is available at https://github.com/antgroup/cakekv.

Zicheng Zhao, Chaofan Gan, Shijie Li et al.

While Video Large Language Models (Video-LLMs) excel in general understanding, they exhibit systematic deficits in fine-grained physical reasoning. Existing interventions not only suffer from limited generalization but fundamentally conflate generative artifacts with genuine physical fallacies. Furthermore, we find that models fail systematically not only in anti-physics anomalies but also in counter-intuitive scenarios where visual facts contradict statistical expectations. Accordingly, we propose the Unified Attribution Theory: this dual failure stems not from perception deficiency, but from Semantic Prior Dominance -- the reasoning mechanism is deeply hijacked by internal narrative scripts. To address this, we construct the Programmatic Adversarial Curriculum (PACC), the first high-fidelity adversarial video dataset synthesized based on physical laws, thoroughly decoupling visual artifacts from logical errors. Concurrently, we design the Visual-Anchored Reasoning Chain (VARC) to force models to explicitly ground their judgments in low-level visual facts prior to logical adjudication. Experiments demonstrate that without invasive architectural modifications, standard LoRA fine-tuning with the PACC curriculum effectively neutralizes prior interference in state-of-the-art (SOTA) models, yielding a substantial leap in physical reasoning capabilities.

Yihang Chen, Qianyi Wu, Weiyao Lin et al.

3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized nature of the point cloud of Gaussians (or anchors in our paper) presents challenges for compression. To achieve a compact size, we propose HAC++, which leverages the relationships between unorganized anchors and a structured hash grid, utilizing their mutual information for context modeling. Additionally, HAC++ captures intra-anchor contextual relationships to further enhance compression performance. To facilitate entropy coding, we utilize Gaussian distributions to precisely estimate the probability of each quantized attribute, where an adaptive quantization module is proposed to enable high-precision quantization of these attributes for improved fidelity restoration. Moreover, we incorporate an adaptive masking strategy to eliminate invalid Gaussians and anchors. Overall, HAC++ achieves a remarkable size reduction of over 100X compared to vanilla 3DGS when averaged on all datasets, while simultaneously improving fidelity. It also delivers more than 20X size reduction compared to Scaffold-GS. Our code is available at https://github.com/YihangChen-ee/HAC-plus.

Yihang Chen, Mengyao Li, Qianyi Wu et al.

3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practical applications. While many compression techniques have been proposed, they fail to efficiently utilize existing bitstreams in on-demand applications due to their lack of progressivity, leading to a waste of resource. To address this issue, we propose PCGS (Progressive Compression of 3D Gaussian Splatting), which adaptively controls both the quantity and quality of Gaussians (or anchors) to enable effective progressivity for on-demand applications. Specifically, for quantity, we introduce a progressive masking strategy that incrementally incorporates new anchors while refining existing ones to enhance fidelity. For quality, we propose a progressive quantization approach that gradually reduces quantization step sizes to achieve finer modeling of Gaussian attributes. Furthermore, to compact the incremental bitstreams, we leverage existing quantization results to refine probability prediction, improving entropy coding efficiency across progressive levels. Overall, PCGS achieves progressivity while maintaining compression performance comparable to SoTA non-progressive methods. Code available at: github.com/YihangChen-ee/PCGS.

Chaofan Gan, Yuanpeng Tu, Yuxi Li et al.

With the recent burst of 2D and 3D data, cross-modal retrieval has attracted increasing attention recently. However, manual labeling by non-experts will inevitably introduce corrupted annotations given ambiguous 2D/3D content. Though previous works have addressed this issue by designing a naive division strategy with hand-crafted thresholds, their performance generally exhibits great sensitivity to the threshold value. Besides, they fail to fully utilize the valuable supervisory signals within each divided subset. To tackle this problem, we propose a Divide-and-conquer 2D-3D cross-modal Alignment and Correction framework (DAC), which comprises Multimodal Dynamic Division (MDD) and Adaptive Alignment and Correction (AAC). Specifically, the former performs accurate sample division by adaptive credibility modeling for each sample based on the compensation information within multimodal loss distribution. Then in AAC, samples in distinct subsets are exploited with different alignment strategies to fully enhance the semantic compactness and meanwhile alleviate over-fitting to noisy labels, where a self-correction strategy is introduced to improve the quality of representation. Moreover. To evaluate the effectiveness in real-world scenarios, we introduce a challenging noisy benchmark, namely Objaverse-N200, which comprises 200k-level samples annotated with 1156 realistic noisy labels. Extensive experiments on both traditional and the newly proposed benchmarks demonstrate the generality and superiority of our DAC, where DAC outperforms state-of-the-art models by a large margin. (i.e., with +5.9% gain on ModelNet40 and +5.8% on Objaverse-N200).

Zhihao He, Tieyuan Chen, Kangyu Wang et al.

Standard Autoregressive Video LLMs inevitably suffer from causal masking biases that hinder global spatiotemporal modeling, leading to suboptimal understanding efficiency. We propose VidLaDA, a Video LLM based on Diffusion Language Model utilizing bidirectional attention to capture bidirectional dependencies. To further tackle the inference bottleneck of diffusion decoding on massive video tokens, we introduce MARS-Cache. This framework accelerates inference by combining asynchronous visual cache refreshing with frame-wise chunk attention, effectively pruning redundancy while preserving global connectivity via anchor tokens. Extensive experiments show VidLaDA outperforms diffusion baselines and rivals state-of-the-art autoregressive models (e.g., Qwen2.5-VL and LLaVA-Video), with MARS-Cache delivering over 12x speedup without compromising reasoning accuracy. Code and checkpoints are open-sourced at https://github.com/ziHoHe/VidLaDA.

Zhihao He, Tianyao He, Yun Xu et al.

Despite the prosperity of the video language model, the current pursuit of comprehensive video reasoning is thwarted by the inherent spatio-temporal incompleteness within individual videos, resulting in hallucinations and inaccuracies. A promising solution is to augment the reasoning performance with multiple related videos. However, video tokens are numerous and contain redundant information, so directly feeding the relevant video data into a large language model to enhance responses could be counterproductive. To address this challenge, we propose a multi-video collaborative framework for video language models. For efficient and flexible video representation, we establish a Video Structuring Module to represent the video's knowledge as a spatio-temporal graph. Based on the structured video representation, we design the Graph Fusion Module to fuse the structured knowledge and valuable information from related videos into the augmented graph node tokens. Finally, we construct an elaborate multi-video structured prompt to integrate the graph, visual, and textual tokens as the input to the large language model. Extensive experiments substantiate the effectiveness of our framework, showcasing its potential as a promising avenue for advancing video language models. Code will be open-sourced at https://github.com/ziHoHe/SMV-CR.

Zicheng Zhao, Kangyu Wang, Shijie Li et al.

Despite advancements in Video Large Language Models (Vid-LLMs) improving multimodal understanding, challenges persist in streaming video reasoning due to its reliance on contextual information. Existing paradigms feed all available historical contextual information into Vid-LLMs, resulting in a significant computational burden for visual data processing. Furthermore, the inclusion of irrelevant context distracts models from key details. This paper introduces a challenging task called Context-guided Streaming Video Reasoning (CogStream), which simulates real-world streaming video scenarios, requiring models to identify the most relevant historical contextual information to deduce answers for questions about the current stream. To support CogStream, we present a densely annotated dataset featuring extensive and hierarchical question-answer pairs, generated by a semi-automatic pipeline. Additionally, we present CogReasoner as a baseline model. It efficiently tackles this task by leveraging visual stream compression and historical dialogue retrieval. Extensive experiments prove the effectiveness of this method. The project is released on https://github.com/LiamZhao326/CogStream.

Tieyuan Chen, Huabin Liu, Yi Wang et al.

Video Question Answering (VideoQA) aims to answer natural language questions based on the given video, with prior work primarily focusing on identifying the duration of relevant segments, referred to as explicit visual evidence. However, explicit visual evidence is not always directly available, particularly when questions target symbolic meanings or deeper intentions, leading to significant performance degradation. To fill this gap, we introduce a novel task and dataset, $\textbf{I}$mplicit $\textbf{V}$ideo $\textbf{Q}$uestion $\textbf{A}$nswering (I-VQA), which focuses on answering questions in scenarios where explicit visual evidence is inaccessible. Given an implicit question and its corresponding video, I-VQA requires answering based on the contextual visual cues present within the video. To tackle I-VQA, we propose a novel reasoning framework, IRM (Implicit Reasoning Model), incorporating dual-stream modeling of contextual actions and intent clues as implicit reasoning chains. IRM comprises the Action-Intent Module (AIM) and the Visual Enhancement Module (VEM). AIM deduces and preserves question-related dual clues by generating clue candidates and performing relation deduction. VEM enhances contextual visual representation by leveraging key contextual clues. Extensive experiments validate the effectiveness of our IRM in I-VQA tasks, outperforming GPT-4o, OpenAI-o3, and fine-tuned VideoChat2 by $0.76\%$, $1.37\%$, and $4.87\%$, respectively. Additionally, IRM performs SOTA on similar implicit advertisement understanding and future prediction in traffic-VQA. Datasets and codes are available for double-blind review in anonymous repo: https://github.com/tychen-SJTU/Implicit-VideoQA.

Xian Liu, Rui Qian, Hang Zhou et al.

The task of audio-visual sound source localization has been well studied under constrained scenes, where the audio recordings are clean. However, in real-world scenarios, audios are usually contaminated by off-screen sound and background noise. They will interfere with the procedure of identifying desired sources and building visual-sound connections, making previous studies non-applicable. In this work, we propose the Interference Eraser (IEr) framework, which tackles the problem of audio-visual sound source localization in the wild. The key idea is to eliminate the interference by redefining and carving discriminative audio representations. Specifically, we observe that the previous practice of learning only a single audio representation is insufficient due to the additive nature of audio signals. We thus extend the audio representation with our Audio-Instance-Identifier module, which clearly distinguishes sounding instances when audio signals of different volumes are unevenly mixed. Then we erase the influence of the audible but off-screen sounds and the silent but visible objects by a Cross-modal Referrer module with cross-modality distillation. Quantitative and qualitative evaluations demonstrate that our proposed framework achieves superior results on sound localization tasks, especially under real-world scenarios. Code is available at https://github.com/alvinliu0/Visual-Sound-Localization-in-the-Wild.

Yuxi Li, Ning Xu, Wenjie Yang et al.

Modern video object segmentation (VOS) algorithms have achieved remarkably high performance in a sequential processing order, while most of currently prevailing pipelines still show some obvious inadequacy like accumulative error, unknown robustness or lack of proper interpretation tools. In this paper, we place the semi-supervised video object segmentation problem into a cyclic workflow and find the defects above can be collectively addressed via the inherent cyclic property of semi-supervised VOS systems. Firstly, a cyclic mechanism incorporated to the standard sequential flow can produce more consistent representations for pixel-wise correspondance. Relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, a simple gradient correction module, which naturally extends the offline cyclic pipeline to an online manner, can highlight the high-frequent and detailed part of results to further improve the segmentation quality while keeping feasible computation cost. Meanwhile such correction can protect the network from severe performance degration resulted from interference signals. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction process to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work. The code of this project can be found at https://github.com/lyxok1/STM-Training

Yuxi Li, Boshen Zhang, Jian Li et al.

In this paper, we place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporal reliance among video signals affect the action detection results. To do this, we decompose the action recognition pipeline into short-term and long-term reliance, in terms of the hypothesis that the two kinds of context are conditionally independent given the objective action instance. Within our design, a local aggregation branch is utilized to gather dense and informative short-term cues, while a high order long-term inference branch is designed to reason the objective action class from high-order interaction between actor and other person or person pairs. Both branches independently predict the context-specific actions and the results are merged in the end. We demonstrate that both temporal grains are beneficial to atomic action recognition. On the mainstream benchmarks of atomic action detection, our design can bring significant performance gain from the existing state-of-the-art pipeline. The code of this project can be found at [this url](https://github.com/TencentYoutuResearch/ActionDetection-LSTC)

Rui Qian, Yuxi Li, Huabin Liu et al.

The crux of self-supervised video representation learning is to build general features from unlabeled videos. However, most recent works have mainly focused on high-level semantics and neglected lower-level representations and their temporal relationship which are crucial for general video understanding. To address these challenges, this paper proposes a multi-level feature optimization framework to improve the generalization and temporal modeling ability of learned video representations. Concretely, high-level features obtained from naive and prototypical contrastive learning are utilized to build distribution graphs, guiding the process of low-level and mid-level feature learning. We also devise a simple temporal modeling module from multi-level features to enhance motion pattern learning. Experiments demonstrate that multi-level feature optimization with the graph constraint and temporal modeling can greatly improve the representation ability in video understanding. Code is available at https://github.com/shvdiwnkozbw/Video-Representation-via-Multi-level-Optimization.

Shuyuan Li, Huabin Liu, Rui Qian et al.

Few-shot action recognition aims to recognize novel action classes (query) using just a few samples (support). The majority of current approaches follow the metric learning paradigm, which learns to compare the similarity between videos. Recently, it has been observed that directly measuring this similarity is not ideal since different action instances may show distinctive temporal distribution, resulting in severe misalignment issues across query and support videos. In this paper, we arrest this problem from two distinct aspects -- action duration misalignment and action evolution misalignment. We address them sequentially through a Two-stage Action Alignment Network (TA2N). The first stage locates the action by learning a temporal affine transform, which warps each video feature to its action duration while dismissing the action-irrelevant feature (e.g. background). Next, the second stage coordinates query feature to match the spatial-temporal action evolution of support by performing temporally rearrange and spatially offset prediction. Extensive experiments on benchmark datasets show the potential of the proposed method in achieving state-of-the-art performance for few-shot action recognition.The code of this project can be found at https://github.com/R00Kie-Liu/TA2N

Di Hu, Rui Qian, Minyue Jiang et al.

Discriminatively localizing sounding objects in cocktail-party, i.e., mixed sound scenes, is commonplace for humans, but still challenging for machines. In this paper, we propose a two-stage learning framework to perform self-supervised class-aware sounding object localization. First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes. Then, class-aware object localization maps are generated in the cocktail-party scenarios by referring the pre-learned object knowledge, and the sounding objects are accordingly selected by matching audio and visual object category distributions, where the audiovisual consistency is viewed as the self-supervised signal. Experimental results in both realistic and synthesized cocktail-party videos demonstrate that our model is superior in filtering out silent objects and pointing out the location of sounding objects of different classes. Code is available at https://github.com/DTaoo/Discriminative-Sounding-Objects-Localization.

Kean Chen, Weiyao Lin, Jianguo Li et al.

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We provide in-depth analyses on the good convergence property and computational complexity of the proposed algorithm, both theoretically and empirically. Experimental results demonstrate notable improvement in addressing the imbalance issue in object detection over existing AP-based optimization algorithms. An improved state-of-the-art performance is achieved in one-stage detectors based on AP-loss over detectors using classification-losses on various standard benchmarks. The proposed framework is also highly versatile in accommodating different network architectures. Code is available at https://github.com/cccorn/AP-loss .

Rui Qian, Di Hu, Heinrich Dinkel et al.

How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations. To solve this problem, we develop a two-stage audiovisual learning framework that disentangles audio and visual representations of different categories from complex scenes, then performs cross-modal feature alignment in a coarse-to-fine manner. Our model achieves state-of-the-art results on public dataset of localization, as well as considerable performance on multi-source sound localization in complex scenes. We then employ the localization results for sound separation and obtain comparable performance to existing methods. These outcomes demonstrate our model's ability in effectively aligning sounds with specific visual sources. Code is available at https://github.com/shvdiwnkozbw/Multi-Source-Sound-Localization

Yuhui Xu, Yuxi Li, Shuai Zhang et al.

To accelerate DNNs inference, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple over a large prediction loss. Apparently, it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training process. We propose Trained Rank Pruning (TRP), which alternates between low rank approximation and training. TRP maintains the capacity of the original network while imposing low-rank constraints during training. A nuclear regularization optimized by stochastic sub-gradient descent is utilized to further promote low rank in TRP. Networks trained with TRP has a low-rank structure in nature, and is approximated with negligible performance loss, thus eliminating fine-tuning after low rank approximation. The proposed method is comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression counterparts using low rank approximation. Our code is available at: https://github.com/yuhuixu1993/Trained-Rank-Pruning.

Kean Chen, Jianguo Li, Weiyao Lin et al.

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the Average-Precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We verify good convergence property of the proposed algorithm theoretically and empirically. Experimental results demonstrate notable performance improvement in state-of-the-art one-stage detectors based on AP-loss over different kinds of classification-losses on various benchmarks, without changing the network architectures. Code is available at https://github.com/cccorn/AP-loss.

Yuhui Xu, Yuxi Li, Shuai Zhang et al.

The performance of Deep Neural Networks (DNNs) keeps elevating in recent years with increasing network depth and width. To enable DNNs on edge devices like mobile phones, researchers proposed several network compression methods including pruning, quantization and factorization. Among the factorization-based approaches, low-rank approximation has been widely adopted because of its solid theoretical rationale and efficient implementations. Several previous works attempted to directly approximate a pre-trained model by low-rank decomposition; however, small approximation errors in parameters can ripple a large prediction loss. As a result, performance usually drops significantly and a sophisticated fine-tuning is required to recover accuracy. We argue that it is not optimal to separate low-rank approximation from training. Unlike previous works, this paper integrates low rank approximation and regularization into the training. We propose Trained Rank Pruning (TRP), which iterates low rank approximation and training. TRP maintains the capacity of original network while imposes low-rank constraints during training. A stochastic sub-gradient descent optimized nuclear regularization is utilized to further encourage low rank in TRP. The TRP trained network has low-rank structure in nature, and can be approximated with negligible performance loss, eliminating fine-tuning after low rank approximation. The methods are comprehensively evaluated on CIFAR-10 and ImageNet, outperforming previous compression methods using low rank approximation. Code is available: https://github.com/yuhuixu1993/Trained-Rank-Pruning

Ziran Qin, Youru Lv, Mingbao Lin et al.

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the need to cache all previously generated visual tokens during decoding, leading to both high storage requirements and low throughput. In this paper, we introduce \textbf{LineAR}, a novel, training-free progressive key-value (KV) cache compression pipeline for autoregressive image generation. By fully exploiting the intrinsic characteristics of visual attention, LineAR manages the cache at the line level using a 2D view, preserving the visual dependency regions while progressively evicting less-informative tokens that are harmless for subsequent line generation, guided by inter-line attention. LineAR enables efficient autoregressive (AR) image generation by utilizing only a few lines of cache, achieving both memory savings and throughput speedup, while maintaining or even improving generation quality. Extensive experiments across six autoregressive image generation models, including class-conditional and text-to-image generation, validate its effectiveness and generality. LineAR improves ImageNet FID from 2.77 to 2.68 and COCO FID from 23.85 to 22.86 on LlamaGen-XL and Janus-Pro-1B, while retaining only 1/6 KV cache. It also improves DPG on Lumina-mGPT-768 with just 1/8 KV cache. Additionally, LineAR achieves significant memory and throughput gains, including up to 67.61% memory reduction and 7.57x speedup on LlamaGen-XL, and 39.66% memory reduction and 5.62x speedup on Janus-Pro-7B.

Conghui Li, Huanyu He, Xin Wang et al.

Real-time crack segmentation is vital for structural health monitoring but is plagued by aleatoric uncertainties arising from varying lighting, blur, and texture ambiguity. Current uncertainty-aware approaches typically treat uncertainty estimation as a passive endpoint for post-hoc analysis, failing to close the loop by feeding this information back to refine feature representations. We contend that independent pixel-wise heteroscedastic modeling is uniquely suited for crack segmentation, as cracks are defined by fine-grained local gradients rather than the global semantic coherence relied upon in general object segmentation. However, this approach suffers from a structural optimization pathology: high predicted variance attenuates loss gradients, effectively causing the model to ignore difficult samples and under-fit complex boundaries. To address these challenges, we propose UnGAP, a novel framework that establishes a closed-loop mechanism between uncertainty estimation and feature learning. Central to our approach is the Uncertainty-Prompted Feature Modulator (UPFM), which treats aleatoric uncertainty as an active visual prompt rather than a mere output. UPFM dynamically calibrates feature distributions through pixel-wise affine transformations. Crucially, this mechanism mitigates the heteroscedastic pathology by transforming high variance, which would otherwise indicate gradient suppression, into a constructive signal for stronger feature rectification in ambiguous regions. Additionally, a boundary-aware detection head is introduced to further constrain prediction precision. Extensive experiments demonstrate that UnGAP balances superior segmentation accuracy with real-time inference speed, effectively validating the benefit of transforming uncertainty from a passive metric into an active calibration tool.

Tianyao He, Huabin Liu, Yuxi Li et al.

Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to their intrinsic procedural temporal structure. Specifically, procedural knowledge is critical for accurate correlation analyses on instructional videos. Nevertheless, current procedure-learning methods heavily rely on step-level annotations, which are costly and not scalable. To address this problem, we introduce a weakly supervised framework called Collaborative Procedure Alignment (CPA) for procedure-aware correlation learning on instructional videos. Our framework comprises two core modules: collaborative step mining and frame-to-step alignment. The collaborative step mining module enables simultaneous and consistent step segmentation for paired videos, leveraging the semantic and temporal similarity between frames. Based on the identified steps, the frame-to-step alignment module performs alignment between the frames and steps across videos. The alignment result serves as a measurement of the correlation distance between two videos. We instantiate our framework in two distinct instructional video tasks: sequence verification and action quality assessment. Extensive experiments validate the effectiveness of our approach in providing accurate and interpretable correlation analyses for instructional videos.

Ziran Qin, Youru Lv, Mingbao Lin et al.

Visual Autoregressive (VAR) models have emerged as a powerful approach for multi-modal content creation, offering high efficiency and quality across diverse multimedia applications. However, they face significant memory bottlenecks due to extensive KV cache accumulation during inference. Existing KV cache compression techniques for large language models are suboptimal for VAR models due to, as we identify in this paper, two distinct categories of attention heads in VAR models: Structural Heads, which preserve spatial coherence through diagonal attention patterns, and Contextual Heads, which maintain semantic consistency through vertical attention patterns. These differences render single-strategy KV compression techniques ineffective for VAR models. To address this, we propose HACK, a training-free Head-Aware Compression method for KV cache. HACK allocates asymmetric cache budgets and employs pattern-specific compression strategies tailored to the essential characteristics of each head category. Experiments on Infinity-2B, Infinity-8B, and VAR-d30 demonstrate its effectiveness in text-to-image and class-conditional generation tasks. HACK can hack down up to 50\% and 70\% of cache with minimal performance degradation for VAR-d30 and Infinity-8B, respectively. Even with 70\% and 90\% KV cache compression in VAR-d30 and Infinity-8B, HACK still maintains high-quality generation while reducing memory usage by 44.2\% and 58.9\%, respectively.

Chaofan Gan, Yuanpeng Tu, Xi Chen et al.

Pre-trained stable diffusion models (SD) have shown great advances in visual correspondence. In this paper, we investigate the capabilities of Diffusion Transformers (DiTs) for accurate dense correspondence. Distinct from SD, DiTs exhibit a critical phenomenon in which very few feature activations exhibit significantly larger values than others, known as \textit{massive activations}, leading to uninformative representations and significant performance degradation for DiTs. The massive activations consistently concentrate at very few fixed dimensions across all image patch tokens, holding little local information. We analyze these dimension-concentrated massive activations and uncover that their concentration is inherently linked to the Adaptive Layer Normalization (AdaLN) in DiTs. Building on these findings, we propose the \textbf{Di}ffusion \textbf{T}ransformer \textbf{F}eature (DiTF), a training-free AdaLN-based framework that extracts semantically discriminative features from DiTs. Specifically, DiTF leverages AdaLN to adaptively localize and normalize massive activations through channel-wise modulation. Furthermore, a channel discard strategy is introduced to mitigate the adverse effects of massive activations. Experimental results demonstrate that our DiTF outperforms both DINO and SD-based models and establishes a new state-of-the-art performance for DiTs in different visual correspondence tasks (\eg, with +9.4\% on Spair-71k and +4.4\% on AP-10K-C.S.).

Tieyuan Chen, Huabin Liu, Yi Wang et al.

Video causal reasoning aims to achieve a high-level understanding of videos from a causal perspective. However, it exhibits limitations in its scope, primarily executed in a question-answering paradigm and focusing on brief video segments containing isolated events and basic causal relations, lacking comprehensive and structured causality analysis for videos with multiple interconnected events. To fill this gap, we introduce a new task and dataset, Multi-Event Causal Discovery (MECD). It aims to uncover the causal relations between events distributed chronologically across long videos. Given visual segments and textual descriptions of events, MECD identifies the causal associations between these events to derive a comprehensive and structured event-level video causal graph explaining why and how the result event occurred. To address the challenges of MECD, we devise a novel framework inspired by the Granger Causality method, incorporating an efficient mask-based event prediction model to perform an Event Granger Test. It estimates causality by comparing the predicted result event when premise events are masked versus unmasked. Furthermore, we integrate causal inference techniques such as front-door adjustment and counterfactual inference to mitigate challenges in MECD like causality confounding and illusory causality. Additionally, context chain reasoning is introduced to conduct more robust and generalized reasoning. Experiments validate the effectiveness of our framework in reasoning complete causal relations, outperforming GPT-4o and VideoChat2 by 5.77% and 2.70%, respectively. Further experiments demonstrate that causal relation graphs can also contribute to downstream video understanding tasks such as video question answering and video event prediction.

Tieyuan Chen, Huabin Liu, Chern Hong Lim et al.

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex than image data because it requires learning and preserving both spatial appearance and temporal action involvement. To address this challenge, we propose a novel exemplar-free framework that equips separate spatiotemporal adapters to learn new class patterns, accommodating the incremental information representation requirements unique to each class. While separate adapters are proven to mitigate forgetting and fit unique requirements, naively applying them hinders the intrinsic connection between spatial and temporal information increments, affecting the efficiency of representing newly learned class information. Motivated by this, we introduce two key innovations from a causal perspective. First, a causal distillation module is devised to maintain the relation between spatial-temporal knowledge for a more efficient representation. Second, a causal compensation mechanism is proposed to reduce the conflicts during increment and memorization between different types of information. Extensive experiments conducted on benchmark datasets demonstrate that our framework can achieve new state-of-the-art results, surpassing current example-based methods by 4.2% in accuracy on average.

Kangyu Wang, Zhiyun Jiang, Haibo Feng et al.

Diffusion large language models (dLLMs) generate text through iterative denoising steps, achieving parallel decoding by denoising only high-confidence positions at each step. However, existing approaches often repetitively remask tokens due to initially low confidence scores, leading to redundant iterations and limiting overall acceleration. Through the analysis of dLLM decoding traces, we observe that the model often determines the final prediction for a token several steps before the decoding step. To leverage this historical information and avoid redundant steps, we introduce the concept of Trace Credit, which quantifies each token's convergence potential by accumulating historical logits. Furthermore, we propose CreditDecoding, a training-free parallel decoding algorithm that accelerates the confidence convergence of correct but underconfident tokens by fusing current logits with Trace Credit. This process significantly reduces redundant iterations and enhances decoding robustness. On eight benchmarks, CreditDecoding achieves a 5.48 times speedup and a 0.48 performance improvement over LLaDA-8B-Instruct, and a 4.11 times speedup with a 0.15 performance improvement over LLaDA-MoE-Instruct. Importantly, CreditDecoding scales effectively to long sequences and is orthogonal to mainstream inference optimizations, making it a readily integrable and versatile solution.

Chaofan Gan, Zicheng Zhao, Yuanpeng Tu et al.

Diffusion Transformers (DiTs) have recently emerged as a powerful backbone for visual generation. Recent observations reveal \emph{Massive Activations} (MAs) in their internal feature maps, yet their function remains poorly understood. In this work, we systematically investigate these activations to elucidate their role in visual generation. We found that these massive activations occur across all spatial tokens, and their distribution is modulated by the input timestep embeddings. Importantly, our investigations further demonstrate that these massive activations play a key role in local detail synthesis, while having minimal impact on the overall semantic content of output. Building on these insights, we propose \textbf{D}etail \textbf{G}uidance (\textbf{DG}), a MAs-driven, training-free self-guidance strategy to explicitly enhance local detail fidelity for DiTs. Specifically, DG constructs a degraded ``detail-deficient'' model by disrupting MAs and leverages it to guide the original network toward higher-quality detail synthesis. Our DG can seamlessly integrate with Classifier-Free Guidance (CFG), enabling further refinements of fine-grained details. Extensive experiments demonstrate that our DG consistently improves fine-grained detail quality across various pre-trained DiTs (\eg, SD3, SD3.5, and Flux).

Tieyuan Chen, Xiaodong Chen, Haoxing Chen et al.

We introduce Dynamic Nested Depth (DND), a novel method that improves performance for off-the-shelf LLMs by selecting critical tokens to reprocess in a nested depth manner. Specifically, at the end of the given transformer layer, DND identifies more critical tokens with a router and feeds them back for an extra round of processing, effectively ``reviewing" difficult tokens while avoiding redundant computation for easier ones. The dynamic selection mechanism is tailored for precise control via two novel strategies: a router controlling loss to enhance token selection distinguishability, and a threshold control scheme to ensure selection stability. We demonstrate the effectiveness of DND by directly integrating it into pre-trained dense and MoE models during a post-training phase. On diverse benchmarks, this approach boosts the performances of the dense Qwen3-1.7B by 1.88% and the MoE Qwen3-30B-A3B by 0.87%, all with a minimal parameter and computing increase.

Xing Gao, Zherui Huang, Weiyao Lin et al.

Accurate motion prediction of surrounding agents is crucial for the safe planning of autonomous vehicles. Recent advancements have extended prediction techniques from individual agents to joint predictions of multiple interacting agents, with various strategies to address complex interactions within future motions of agents. However, these methods overlook the evolving nature of these interactions. To address this limitation, we propose a novel progressive multi-scale decoding strategy, termed ProgD, with the help of dynamic heterogeneous graph-based scenario modeling. In particular, to explicitly and comprehensively capture the evolving social interactions in future scenarios, given their inherent uncertainty, we design a progressive modeling of scenarios with dynamic heterogeneous graphs. With the unfolding of such dynamic heterogeneous graphs, a factorized architecture is designed to process the spatio-temporal dependencies within future scenarios and progressively eliminate uncertainty in future motions of multiple agents. Furthermore, a multi-scale decoding procedure is incorporated to improve on the future scenario modeling and consistent prediction of agents' future motion. The proposed ProgD achieves state-of-the-art performance on the INTERACTION multi-agent prediction benchmark, ranking $1^{st}$, and the Argoverse 2 multi-world forecasting benchmark.

Gui Zou, Chaofan Gan, Chern Hong Lim et al.

With the increasing availability of 2D and 3D data, significant advancements have been made in the field of cross-modal retrieval. Nevertheless, the existence of imperfect annotations presents considerable challenges, demanding robust solutions for 2D-3D cross-modal retrieval in the presence of noisy label conditions. Existing methods generally address the issue of noise by dividing samples independently within each modality, making them susceptible to overfitting on corrupted labels. To address these issues, we propose a robust 2D-3D \textbf{M}ulti-level cross-modal adaptive \textbf{C}orrection and \textbf{A}lignment framework (MCA). Specifically, we introduce a Multimodal Joint label Correction (MJC) mechanism that leverages multimodal historical self-predictions to jointly model the modality prediction consistency, enabling reliable label refinement. Additionally, we propose a Multi-level Adaptive Alignment (MAA) strategy to effectively enhance cross-modal feature semantics and discrimination across different levels. Extensive experiments demonstrate the superiority of our method, MCA, which achieves state-of-the-art performance on both conventional and realistic noisy 3D benchmarks, highlighting its generality and effectiveness.

Shizhan Liu, Zhengkai Jiang, Yuxi Li et al.

Active domain adaptation has emerged as a solution to balance the expensive annotation cost and the performance of trained models in semantic segmentation. However, existing works usually ignore the correlation between selected samples and its local context in feature space, which leads to inferior usage of annotation budgets. In this work, we revisit the theoretical bound of the classical Core-set method and identify that the performance is closely related to the local sample distribution around selected samples. To estimate the density of local samples efficiently, we introduce a local proxy estimator with Dynamic Masked Convolution and develop a Density-aware Greedy algorithm to optimize the bound. Extensive experiments demonstrate the superiority of our approach. Moreover, with very few labels, our scheme achieves comparable performance to the fully supervised counterpart.

Huabin Liu, Weiyao Lin, Tieyuan Chen et al.

Current few-shot action recognition involves two primary sources of information for classification:(1) intra-video information, determined by frame content within a single video clip, and (2) inter-video information, measured by relationships (e.g., feature similarity) among videos. However, existing methods inadequately exploit these two information sources. In terms of intra-video information, current sampling operations for input videos may omit critical action information, reducing the utilization efficiency of video data. For the inter-video information, the action misalignment among videos makes it challenging to calculate precise relationships. Moreover, how to jointly consider both inter- and intra-video information remains under-explored for few-shot action recognition. To this end, we propose a novel framework, Video Information Maximization (VIM), for few-shot video action recognition. VIM is equipped with an adaptive spatial-temporal video sampler and a spatiotemporal action alignment model to maximize intra- and inter-video information, respectively. The video sampler adaptively selects important frames and amplifies critical spatial regions for each input video based on the task at hand. This preserves and emphasizes informative parts of video clips while eliminating interference at the data level. The alignment model performs temporal and spatial action alignment sequentially at the feature level, leading to more precise measurements of inter-video similarity. Finally, These goals are facilitated by incorporating additional loss terms based on mutual information measurement. Consequently, VIM acts to maximize the distinctiveness of video information from limited video data. Extensive experimental results on public datasets for few-shot action recognition demonstrate the effectiveness and benefits of our framework.

Rui Qian, Weiyao Lin, John See et al.

This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to bias to static background and have difficulty establishing global temporal structures. The major reason is that the positive pairs, i.e., different clips sampled from the same video, have limited temporal receptive field, and usually share similar background but differ in motions. To address these problems, we propose a framework to jointly utilize local clips and global videos to learn from detailed region-level correspondence as well as general long-term temporal relations. Based on a set of controllable augmentations, we achieve accurate appearance and motion pattern alignment through soft spatio-temporal region contrast. Our formulation is able to avoid the low-level redundancy shortcut by mutual information minimization to improve the generalization. We also introduce local-global temporal order dependency to further bridge the gap between clip-level and video-level representations for robust temporal modeling. Extensive experiments demonstrate that our framework is superior on three video benchmarks in action recognition and video retrieval, capturing more accurate temporal dynamics.

Yehao Li, Jiahao Fan, Yingwei Pan et al.

Vision-language pre-training has been an emerging and fast-developing research topic, which transfers multi-modal knowledge from rich-resource pre-training task to limited-resource downstream tasks. Unlike existing works that predominantly learn a single generic encoder, we present a pre-trainable Universal Encoder-DEcoder Network (Uni-EDEN) to facilitate both vision-language perception (e.g., visual question answering) and generation (e.g., image captioning). Uni-EDEN is a two-stream Transformer based structure, consisting of three modules: object and sentence encoders that separately learns the representations of each modality, and sentence decoder that enables both multi-modal reasoning and sentence generation via inter-modal interaction. Considering that the linguistic representations of each image can span different granularities in this hierarchy including, from simple to comprehensive, individual label, a phrase, and a natural sentence, we pre-train Uni-EDEN through multi-granular vision-language proxy tasks: Masked Object Classification (MOC), Masked Region Phrase Generation (MRPG), Image-Sentence Matching (ISM), and Masked Sentence Generation (MSG). In this way, Uni-EDEN is endowed with the power of both multi-modal representation extraction and language modeling. Extensive experiments demonstrate the compelling generalizability of Uni-EDEN by fine-tuning it to four vision-language perception and generation downstream tasks.

Di Hu, Yake Wei, Rui Qian et al.

Audiovisual scenes are pervasive in our daily life. It is commonplace for humans to discriminatively localize different sounding objects but quite challenging for machines to achieve class-aware sounding objects localization without category annotations, i.e., localizing the sounding object and recognizing its category. To address this problem, we propose a two-stage step-by-step learning framework to localize and recognize sounding objects in complex audiovisual scenarios using only the correspondence between audio and vision. First, we propose to determine the sounding area via coarse-grained audiovisual correspondence in the single source cases. Then visual features in the sounding area are leveraged as candidate object representations to establish a category-representation object dictionary for expressive visual character extraction. We generate class-aware object localization maps in cocktail-party scenarios and use audiovisual correspondence to suppress silent areas by referring to this dictionary. Finally, we employ category-level audiovisual consistency as the supervision to achieve fine-grained audio and sounding object distribution alignment. Experiments on both realistic and synthesized videos show that our model is superior in localizing and recognizing objects as well as filtering out silent ones. We also transfer the learned audiovisual network into the unsupervised object detection task, obtaining reasonable performance.

Jinlong Peng, Zhengkai Jiang, Yueyang Gu et al.

Recently, most siamese network based trackers locate targets via object classification and bounding-box regression. Generally, they select the bounding-box with maximum classification confidence as the final prediction. This strategy may miss the right result due to the accuracy misalignment between classification and regression. In this paper, we propose a novel siamese tracking algorithm called SiamRCR, addressing this problem with a simple, light and effective solution. It builds reciprocal links between classification and regression branches, which can dynamically re-weight their losses for each positive sample. In addition, we add a localization branch to predict the localization accuracy, so that it can work as the replacement of the regression assistance link during inference. This branch makes the training and inference more consistent. Extensive experimental results demonstrate the effectiveness of SiamRCR and its superiority over the state-of-the-art competitors on GOT-10k, LaSOT, TrackingNet, OTB-2015, VOT-2018 and VOT-2019. Moreover, our SiamRCR runs at 65 FPS, far above the real-time requirement.

Yuang Zhang, Huanyu He, Jianguo Li et al.

Pedestrian detection in a crowd is a challenging task due to a high number of mutually-occluding human instances, which brings ambiguity and optimization difficulties to the current IoU-based ground truth assignment procedure in classical object detection methods. In this paper, we develop a unique perspective of pedestrian detection as a variational inference problem. We formulate a novel and efficient algorithm for pedestrian detection by modeling the dense proposals as a latent variable while proposing a customized Auto Encoding Variational Bayes (AEVB) algorithm. Through the optimization of our proposed algorithm, a classical detector can be fashioned into a variational pedestrian detector. Experiments conducted on CrowdHuman and CityPersons datasets show that the proposed algorithm serves as an efficient solution to handle the dense pedestrian detection problem for the case of single-stage detectors. Our method can also be flexibly applied to two-stage detectors, achieving notable performance enhancement.

Yuxi Li, Ning Xu, Jinlong Peng et al.

In this paper, we address several inadequacies of current video object segmentation pipelines. Firstly, a cyclic mechanism is incorporated to the standard semi-supervised process to produce more robust representations. By relying on the accurate reference mask in the starting frame, we show that the error propagation problem can be mitigated. Next, we introduce a simple gradient correction module, which extends the offline pipeline to an online method while maintaining the efficiency of the former. Finally we develop cycle effective receptive field (cycle-ERF) based on gradient correction to provide a new perspective into analyzing object-specific regions of interests. We conduct comprehensive experiments on challenging benchmarks of DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is beneficial to segmentation quality.

Weiyao Lin, Xiaoyi He, Wenrui Dai et al.

Feature coding has been recently considered to facilitate intelligent video analysis for urban computing. Instead of raw videos, extracted features in the front-end are encoded and transmitted to the back-end for further processing. In this article, we present a lossless key-point sequence compression approach for efficient feature coding. The essence of this predict-and-encode strategy is to eliminate the spatial and temporal redundancies of key points in videos. Multiple prediction modes with an adaptive mode selection method are proposed to handle key-point sequences with various structures and motion. Experimental results validate the effectiveness of the proposed scheme on four types of widely used key-point sequences in video analysis.