Shiwei Zhang

Hangjie Yuan, Shiwei Zhang, Xiang Wang et al. · cambridge

Relational Language-Image Pre-training (RLIP) aims to align vision representations with relational texts, thereby advancing the capability of relational reasoning in computer vision tasks. However, hindered by the slow convergence of RLIPv1 architecture and the limited availability of existing scene graph data, scaling RLIPv1 is challenging. In this paper, we propose RLIPv2, a fast converging model that enables the scaling of relational pre-training to large-scale pseudo-labelled scene graph data. To enable fast scaling, RLIPv2 introduces Asymmetric Language-Image Fusion (ALIF), a mechanism that facilitates earlier and deeper gated cross-modal fusion with sparsified language encoding layers. ALIF leads to comparable or better performance than RLIPv1 in a fraction of the time for pre-training and fine-tuning. To obtain scene graph data at scale, we extend object detection datasets with free-form relation labels by introducing a captioner (e.g., BLIP) and a designed Relation Tagger. The Relation Tagger assigns BLIP-generated relation texts to region pairs, thus enabling larger-scale relational pre-training. Through extensive experiments conducted on Human-Object Interaction Detection and Scene Graph Generation, RLIPv2 shows state-of-the-art performance on three benchmarks under fully-finetuning, few-shot and zero-shot settings. Notably, the largest RLIPv2 achieves 23.29mAP on HICO-DET without any fine-tuning, yields 32.22mAP with just 1% data and yields 45.09mAP with 100% data. Code and models are publicly available at https://github.com/JacobYuan7/RLIPv2.

Xiang Wang, Shiwei Zhang, Jun Cen et al.

Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under-explored on the challenging few-shot action recognition (FSAR) task. In this work, we aim to transfer the powerful multimodal knowledge of CLIP to alleviate the inaccurate prototype estimation issue due to data scarcity, which is a critical problem in low-shot regimes. To this end, we present a CLIP-guided prototype modulating framework called CLIP-FSAR, which consists of two key components: a video-text contrastive objective and a prototype modulation. Specifically, the former bridges the task discrepancy between CLIP and the few-shot video task by contrasting videos and corresponding class text descriptions. The latter leverages the transferable textual concepts from CLIP to adaptively refine visual prototypes with a temporal Transformer. By this means, CLIP-FSAR can take full advantage of the rich semantic priors in CLIP to obtain reliable prototypes and achieve accurate few-shot classification. Extensive experiments on five commonly used benchmarks demonstrate the effectiveness of our proposed method, and CLIP-FSAR significantly outperforms existing state-of-the-art methods under various settings. The source code and models will be publicly available at https://github.com/alibaba-mmai-research/CLIP-FSAR.

Xiang Wang, Shiwei Zhang, Zhiwu Qing et al.

Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure between local frames tends to be inaccurate due to the lack of guidance to force long-range temporal perception; ii) explicit motion learning is usually ignored, leading to partial information loss. To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder. Specifically, the long-short contrastive objective is to endow local frame features with long-form temporal awareness by maximizing their agreement with the global token of videos belonging to the same class. The motion autodecoder is a lightweight architecture to reconstruct pixel motions from the differential features, which explicitly embeds the network with motion dynamics. By this means, MoLo can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching. To demonstrate the effectiveness, we evaluate MoLo on five standard benchmarks, and the results show that MoLo favorably outperforms recent advanced methods. The source code is available at https://github.com/alibaba-mmai-research/MoLo.

Jun Cen, Peng Yun, Shiwei Zhang et al. · gatech

Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e.g., autonomous driving, since it is closed-set and static. The closed-set assumption makes the network only able to output labels of trained classes, even for objects never seen before, while a static network cannot update its knowledge base according to what it has seen. Therefore, in this work, we propose the open-world semantic segmentation task for LIDAR point clouds, which aims to 1) identify both old and novel classes using open-set semantic segmentation, and 2) gradually incorporate novel objects into the existing knowledge base using incremental learning without forgetting old classes. For this purpose, we propose a REdundAncy cLassifier (REAL) framework to provide a general architecture for both the open-set semantic segmentation and incremental learning problems. The experimental results show that REAL can simultaneously achieves state-of-the-art performance in the open-set semantic segmentation task on the SemanticKITTI and nuScenes datasets, and alleviate the catastrophic forgetting problem with a large margin during incremental learning.

Xiang Wang, Shiwei Zhang, Zhiwu Qing et al.

Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they still suffer from two drawbacks: (i) learning individual features without considering the entire task may result in limited representation capability, and (ii) existing alignment strategies are sensitive to noises and misaligned instances. To handle the two limitations, we propose a novel Hybrid Relation guided temporal Set Matching (HyRSM++) approach for few-shot action recognition. The core idea of HyRSM++ is to integrate all videos within the task to learn discriminative representations and involve a robust matching technique. To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric. Given the basic representations from the feature extractor, the hybrid relation module is introduced to fully exploit associated relations within and cross videos in an episodic task and thus can learn task-specific embeddings. Subsequently, in the temporal set matching metric, we carry out the distance measure between query and support videos from a set matching perspective and design a Bi-MHM to improve the resilience to misaligned instances. In addition, we explicitly exploit the temporal coherence in videos to regularize the matching process. Furthermore, we extend the proposed HyRSM++ to deal with the more challenging semi-supervised few-shot action recognition and unsupervised few-shot action recognition tasks. Experimental results on multiple benchmarks demonstrate that our method achieves state-of-the-art performance under various few-shot settings. The source code is available at https://github.com/alibaba-mmai-research/HyRSMPlusPlus.

Zhiwu Qing, Shiwei Zhang, Ziyuan Huang et al.

Recently, large-scale pre-trained language-image models like CLIP have shown extraordinary capabilities for understanding spatial contents, but naively transferring such models to video recognition still suffers from unsatisfactory temporal modeling capabilities. Existing methods insert tunable structures into or in parallel with the pre-trained model, which either requires back-propagation through the whole pre-trained model and is thus resource-demanding, or is limited by the temporal reasoning capability of the pre-trained structure. In this work, we present DiST, which disentangles the learning of spatial and temporal aspects of videos. Specifically, DiST uses a dual-encoder structure, where a pre-trained foundation model acts as the spatial encoder, and a lightweight network is introduced as the temporal encoder. An integration branch is inserted between the encoders to fuse spatio-temporal information. The disentangled spatial and temporal learning in DiST is highly efficient because it avoids the back-propagation of massive pre-trained parameters. Meanwhile, we empirically show that disentangled learning with an extra network for integration benefits both spatial and temporal understanding. Extensive experiments on five benchmarks show that DiST delivers better performance than existing state-of-the-art methods by convincing gaps. When pre-training on the large-scale Kinetics-710, we achieve 89.7% on Kinetics-400 with a frozen ViT-L model, which verifies the scalability of DiST. Codes and models can be found in https://github.com/alibaba-mmai-research/DiST.

Jun Cen, Shiwei Zhang, Yixuan Pei et al.

2D RGB images and 3D LIDAR point clouds provide complementary knowledge for the perception system of autonomous vehicles. Several 2D and 3D fusion methods have been explored for the LIDAR semantic segmentation task, but they suffer from different problems. 2D-to-3D fusion methods require strictly paired data during inference, which may not be available in real-world scenarios, while 3D-to-2D fusion methods cannot explicitly make full use of the 2D information. Therefore, we propose a Bidirectional Fusion Network with Cross-Modality Knowledge Distillation (CMDFusion) in this work. Our method has two contributions. First, our bidirectional fusion scheme explicitly and implicitly enhances the 3D feature via 2D-to-3D fusion and 3D-to-2D fusion, respectively, which surpasses either one of the single fusion schemes. Second, we distillate the 2D knowledge from a 2D network (Camera branch) to a 3D network (2D knowledge branch) so that the 3D network can generate 2D information even for those points not in the FOV (field of view) of the camera. In this way, RGB images are not required during inference anymore since the 2D knowledge branch provides 2D information according to the 3D LIDAR input. We show that our CMDFusion achieves the best performance among all fusion-based methods on SemanticKITTI and nuScenes datasets. The code will be released at https://github.com/Jun-CEN/CMDFusion.

Xiang Wang, Hangjie Yuan, Shiwei Zhang et al.

The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation of temporal dynamics and the requirement of cross-frame temporal consistency. Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions. Specifically, considering the characteristic of video data, we introduce the motion vector from compressed videos as an explicit control signal to provide guidance regarding temporal dynamics. In addition, we develop a Spatio-Temporal Condition encoder (STC-encoder) that serves as a unified interface to effectively incorporate the spatial and temporal relations of sequential inputs, with which the model could make better use of temporal conditions and hence achieve higher inter-frame consistency. Extensive experimental results suggest that VideoComposer is able to control the spatial and temporal patterns simultaneously within a synthesized video in various forms, such as text description, sketch sequence, reference video, or even simply hand-crafted motions. The code and models will be publicly available at https://videocomposer.github.io.

Ziyuan Huang, Shiwei Zhang, Liang Pan et al.

Spatial convolutions are extensively used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions (TAdaConv) for video understanding, which shows that adaptive weight calibration along the temporal dimension is an efficient way to facilitate modeling complex temporal dynamics in videos. Specifically, TAdaConv empowers spatial convolutions with temporal modeling abilities by calibrating the convolution weights for each frame according to its local and global temporal context. Compared to existing operations for temporal modeling, TAdaConv is more efficient as it operates over the convolution kernels instead of the features, whose dimension is an order of magnitude smaller than the spatial resolutions. Further, kernel calibration brings an increased model capacity. Based on this readily plug-in operation TAdaConv as well as its extension, i.e., TAdaConvV2, we construct TAdaBlocks to empower ConvNeXt and Vision Transformer to have strong temporal modeling capabilities. Empirical results show TAdaConvNeXtV2 and TAdaFormer perform competitively against state-of-the-art convolutional and Transformer-based models in various video understanding benchmarks. Our codes and models are released at: https://github.com/alibaba-mmai-research/TAdaConv.

Haochun Wang, Chi Liu, Nuwa Xi et al. · tencent-ai

Prompt-based fine-tuning for pre-trained models has proven effective for many natural language processing tasks under few-shot settings in general domain. However, tuning with prompt in biomedical domain has not been investigated thoroughly. Biomedical words are often rare in general domain, but quite ubiquitous in biomedical contexts, which dramatically deteriorates the performance of pre-trained models on downstream biomedical applications even after fine-tuning, especially in low-resource scenarios. We propose a simple yet effective approach to helping models learn rare biomedical words during tuning with prompt. Experimental results show that our method can achieve up to 6% improvement in biomedical natural language inference task without any extra parameters or training steps using few-shot vanilla prompt settings.

Jun Cen, Shiwei Zhang, Xiang Wang et al.

Open-set action recognition is to reject unknown human action cases which are out of the distribution of the training set. Existing methods mainly focus on learning better uncertainty scores but dismiss the importance of feature representations. We find that features with richer semantic diversity can significantly improve the open-set performance under the same uncertainty scores. In this paper, we begin with analyzing the feature representation behavior in the open-set action recognition (OSAR) problem based on the information bottleneck (IB) theory, and propose to enlarge the instance-specific (IS) and class-specific (CS) information contained in the feature for better performance. To this end, a novel Prototypical Similarity Learning (PSL) framework is proposed to keep the instance variance within the same class to retain more IS information. Besides, we notice that unknown samples sharing similar appearances to known samples are easily misclassified as known classes. To alleviate this issue, video shuffling is further introduced in our PSL to learn distinct temporal information between original and shuffled samples, which we find enlarges the CS information. Extensive experiments demonstrate that the proposed PSL can significantly boost both the open-set and closed-set performance and achieves state-of-the-art results on multiple benchmarks. Code is available at https://github.com/Jun-CEN/PSL.

Ziang Cao, Ziyuan Huang, Liang Pan et al.

Temporal contexts among consecutive frames are far from being fully utilized in existing visual trackers. In this work, we present TCTrack, a comprehensive framework to fully exploit temporal contexts for aerial tracking. The temporal contexts are incorporated at \textbf{two levels}: the extraction of \textbf{features} and the refinement of \textbf{similarity maps}. Specifically, for feature extraction, an online temporally adaptive convolution is proposed to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights according to the previous frames. For similarity map refinement, we propose an adaptive temporal transformer, which first effectively encodes temporal knowledge in a memory-efficient way, before the temporal knowledge is decoded for accurate adjustment of the similarity map. TCTrack is effective and efficient: evaluation on four aerial tracking benchmarks shows its impressive performance; real-world UAV tests show its high speed of over 27 FPS on NVIDIA Jetson AGX Xavier.

Jiuniu Wang, Hangjie Yuan, Dayou Chen et al.

This paper introduces ModelScopeT2V, a text-to-video synthesis model that evolves from a text-to-image synthesis model (i.e., Stable Diffusion). ModelScopeT2V incorporates spatio-temporal blocks to ensure consistent frame generation and smooth movement transitions. The model could adapt to varying frame numbers during training and inference, rendering it suitable for both image-text and video-text datasets. ModelScopeT2V brings together three components (i.e., VQGAN, a text encoder, and a denoising UNet), totally comprising 1.7 billion parameters, in which 0.5 billion parameters are dedicated to temporal capabilities. The model demonstrates superior performance over state-of-the-art methods across three evaluation metrics. The code and an online demo are available at \url{https://modelscope.cn/models/damo/text-to-video-synthesis/summary}.

Xiang Wang, Shiwei Zhang, Zhiwu Qing et al.

Current few-shot action recognition methods reach impressive performance by learning discriminative features for each video via episodic training and designing various temporal alignment strategies. Nevertheless, they are limited in that (a) learning individual features without considering the entire task may lose the most relevant information in the current episode, and (b) these alignment strategies may fail in misaligned instances. To overcome the two limitations, we propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components: hybrid relation module and set matching metric. The purpose of the hybrid relation module is to learn task-specific embeddings by fully exploiting associated relations within and cross videos in an episode. Built upon the task-specific features, we reformulate distance measure between query and support videos as a set matching problem and further design a bidirectional Mean Hausdorff Metric to improve the resilience to misaligned instances. By this means, the proposed HyRSM can be highly informative and flexible to predict query categories under the few-shot settings. We evaluate HyRSM on six challenging benchmarks, and the experimental results show its superiority over the state-of-the-art methods by a convincing margin. Project page: https://hyrsm-cvpr2022.github.io/.

Zhiwu Qing, Shiwei Zhang, Ziyuan Huang et al.

Standard approaches for video recognition usually operate on the full input videos, which is inefficient due to the widely present spatio-temporal redundancy in videos. Recent progress in masked video modelling, i.e., VideoMAE, has shown the ability of vanilla Vision Transformers (ViT) to complement spatio-temporal contexts given only limited visual contents. Inspired by this, we propose propose Masked Action Recognition (MAR), which reduces the redundant computation by discarding a proportion of patches and operating only on a part of the videos. MAR contains the following two indispensable components: cell running masking and bridging classifier. Specifically, to enable the ViT to perceive the details beyond the visible patches easily, cell running masking is presented to preserve the spatio-temporal correlations in videos, which ensures the patches at the same spatial location can be observed in turn for easy reconstructions. Additionally, we notice that, although the partially observed features can reconstruct semantically explicit invisible patches, they fail to achieve accurate classification. To address this, a bridging classifier is proposed to bridge the semantic gap between the ViT encoded features for reconstruction and the features specialized for classification. Our proposed MAR reduces the computational cost of ViT by 53% and extensive experiments show that MAR consistently outperforms existing ViT models with a notable margin. Especially, we found a ViT-Large trained by MAR outperforms the ViT-Huge trained by a standard training scheme by convincing margins on both Kinetics-400 and Something-Something v2 datasets, while our computation overhead of ViT-Large is only 14.5% of ViT-Huge.

Ziang Cao, Ziyuan Huang, Liang Pan et al.

Visual tracking has made significant improvements in the past few decades. Most existing state-of-the-art trackers 1) merely aim for performance in ideal conditions while overlooking the real-world conditions; 2) adopt the tracking-by-detection paradigm, neglecting rich temporal contexts; 3) only integrate the temporal information into the template, where temporal contexts among consecutive frames are far from being fully utilized. To handle those problems, we propose a two-level framework (TCTrack) that can exploit temporal contexts efficiently. Based on it, we propose a stronger version for real-world visual tracking, i.e., TCTrack++. It boils down to two levels: features and similarity maps. Specifically, for feature extraction, we propose an attention-based temporally adaptive convolution to enhance the spatial features using temporal information, which is achieved by dynamically calibrating the convolution weights. For similarity map refinement, we introduce an adaptive temporal transformer to encode the temporal knowledge efficiently and decode it for the accurate refinement of the similarity map. To further improve the performance, we additionally introduce a curriculum learning strategy. Also, we adopt online evaluation to measure performance in real-world conditions. Exhaustive experiments on 8 wellknown benchmarks demonstrate the superiority of TCTrack++. Real-world tests directly verify that TCTrack++ can be readily used in real-world applications.

Jun Cen, Di Luan, Shiwei Zhang et al.

Open-set Recognition (OSR) aims to identify test samples whose classes are not seen during the training process. Recently, Unified Open-set Recognition (UOSR) has been proposed to reject not only unknown samples but also known but wrongly classified samples, which tends to be more practical in real-world applications. The UOSR draws little attention since it is proposed, but we find sometimes it is even more practical than OSR in the real world applications, as evaluation results of known but wrongly classified samples are also wrong like unknown samples. In this paper, we deeply analyze the UOSR task under different training and evaluation settings to shed light on this promising research direction. For this purpose, we first evaluate the UOSR performance of several OSR methods and show a significant finding that the UOSR performance consistently surpasses the OSR performance by a large margin for the same method. We show that the reason lies in the known but wrongly classified samples, as their uncertainty distribution is extremely close to unknown samples rather than known and correctly classified samples. Second, we analyze how the two training settings of OSR (i.e., pre-training and outlier exposure) influence the UOSR. We find although they are both beneficial for distinguishing known and correctly classified samples from unknown samples, pre-training is also helpful for identifying known but wrongly classified samples while outlier exposure is not. In addition to different training settings, we also formulate a new evaluation setting for UOSR which is called few-shot UOSR, where only one or five samples per unknown class are available during evaluation to help identify unknown samples. We propose FS-KNNS for the few-shot UOSR to achieve state-of-the-art performance under all settings.

Xiang Wang, Shiwei Zhang, Haonan Qiu et al.

The field of controllable human-centric video generation has witnessed remarkable progress, particularly with the advent of diffusion models. However, achieving precise and localized control over human motion in videos, such as replacing or inserting individuals while preserving desired motion patterns, still remains a formidable challenge. In this work, we present the ReplaceAnyone framework, which focuses on localized human replacement and insertion featuring intricate backgrounds. Specifically, we formulate this task as an image-conditioned video inpainting paradigm with pose guidance, utilizing a unified end-to-end video diffusion architecture that facilitates image-conditioned video inpainting within masked regions. To prevent shape leakage and enable granular local control, we introduce diverse mask forms involving both regular and irregular shapes. Furthermore, we implement an enriched visual guidance mechanism to enhance appearance alignment, a hybrid inpainting encoder to further preserve the detailed background information in the masked video, and a two-phase optimization methodology to simplify the training difficulty. ReplaceAnyone enables seamless replacement or insertion of characters while maintaining the desired pose motion and reference appearance within a single framework. Extensive experimental results demonstrate the effectiveness of our method in generating realistic and coherent video content. The proposed ReplaceAnyone can be seamlessly applied not only to traditional 3D-UNet base models but also to DiT-based video models such as Wan2.1. The code will be available at https://github.com/ali-vilab/UniAnimate-DiT.

Shiwei Zhang, Jiayu Wang, Yingya Zhang et al.

Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily arise from the scarcity of well-aligned text-video data and the complex inherent structure of videos, making it difficult for the model to simultaneously ensure semantic and qualitative excellence. In this report, we propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors and ensures the alignment of the input data by utilizing static images as a form of crucial guidance. I2VGen-XL consists of two stages: i) the base stage guarantees coherent semantics and preserves content from input images by using two hierarchical encoders, and ii) the refinement stage enhances the video's details by incorporating an additional brief text and improves the resolution to 1280$\times$720. To improve the diversity, we collect around 35 million single-shot text-video pairs and 6 billion text-image pairs to optimize the model. By this means, I2VGen-XL can simultaneously enhance the semantic accuracy, continuity of details and clarity of generated videos. Through extensive experiments, we have investigated the underlying principles of I2VGen-XL and compared it with current top methods, which can demonstrate its effectiveness on diverse data. The source code and models will be publicly available at \url{https://i2vgen-xl.github.io}.

Xianjie Wu, Jian Yang, Tongliang Li et al. · tsinghua

Incorporating external knowledge into dialogue generation (KIDG) is crucial for improving the correctness of response, where evidence fragments serve as knowledgeable snippets supporting the factual dialogue replies. However, introducing irrelevant content often adversely impacts reply quality and easily leads to hallucinated responses. Prior work on evidence retrieval and integration in dialogue systems falls short of fully leveraging existing evidence since the model fails to locate useful fragments accurately and overlooks hidden evidence labels within the KIDG dataset. To fully Unleash the potential of evidence, we propose a framework to effectively incorporate Evidence in knowledge-Intensive Dialogue Generation (u-EIDG). Specifically, we introduce an automatic evidence generation framework that harnesses the power of Large Language Models (LLMs) to mine reliable evidence veracity labels from unlabeled data. By utilizing these evidence labels, we train a reliable evidence indicator to effectively identify relevant evidence from retrieved passages. Furthermore, we propose an evidence-augmented generator with an evidence-focused attention mechanism, which allows the model to concentrate on evidenced segments. Experimental results on MultiDoc2Dial demonstrate the efficacy of evidential label augmentation and refined attention mechanisms in improving model performance. Further analysis confirms that the proposed method outperforms other baselines (+3~+5 points) regarding coherence and factual consistency.

Yixuan Pei, Zhiwu Qing, Jun Cen et al.

Recent incremental learning for action recognition usually stores representative videos to mitigate catastrophic forgetting. However, only a few bulky videos can be stored due to the limited memory. To address this problem, we propose FrameMaker, a memory-efficient video class-incremental learning approach that learns to produce a condensed frame for each selected video. Specifically, FrameMaker is mainly composed of two crucial components: Frame Condensing and Instance-Specific Prompt. The former is to reduce the memory cost by preserving only one condensed frame instead of the whole video, while the latter aims to compensate the lost spatio-temporal details in the Frame Condensing stage. By this means, FrameMaker enables a remarkable reduction in memory but keep enough information that can be applied to following incremental tasks. Experimental results on multiple challenging benchmarks, i.e., HMDB51, UCF101 and Something-Something V2, demonstrate that FrameMaker can achieve better performance to recent advanced methods while consuming only 20% memory. Additionally, under the same memory consumption conditions, FrameMaker significantly outperforms existing state-of-the-arts by a convincing margin.

Zhiwu Qing, Shiwei Zhang, Ziyuan Huang et al.

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited performance gain. In this work, we aim to learn representations by leveraging more abundant information in untrimmed videos. To this end, we propose to learn a hierarchy of consistencies in videos, i.e., visual consistency and topical consistency, corresponding respectively to clip pairs that tend to be visually similar when separated by a short time span and share similar topics when separated by a long time span. Specifically, a hierarchical consistency learning framework HiCo is presented, where the visually consistent pairs are encouraged to have the same representation through contrastive learning, while the topically consistent pairs are coupled through a topical classifier that distinguishes whether they are topic related. Further, we impose a gradual sampling algorithm for proposed hierarchical consistency learning, and demonstrate its theoretical superiority. Empirically, we show that not only HiCo can generate stronger representations on untrimmed videos, it also improves the representation quality when applied to trimmed videos. This is in contrast to standard contrastive learning that fails to learn appropriate representations from untrimmed videos.

Xiang Wang, Shiwei Zhang, Hangjie Yuan et al.

Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically generate associated captions for input videos. Then, we apply a text encoder to the synthetic captions to obtain representative text embeddings. Finally, a visual-text aggregation module based on Transformer is further designed to incorporate cross-modal spatio-temporal complementary information for reliable few-shot matching. In this way, CapFSAR can benefit from powerful multimodal knowledge of pretrained foundation models, yielding more comprehensive classification in the low-shot regime. Extensive experiments on multiple standard few-shot benchmarks demonstrate that the proposed CapFSAR performs favorably against existing methods and achieves state-of-the-art performance. The code will be made publicly available.

Yujie Wei, Yujin Han, Zhekai Chen et al.

Video generation is rapidly evolving from single-shot synthesis to complex multi-shot audio-video (MSAV) narratives to meet real-world demands. However, evaluating such frontier models remains a fundamental challenge. Existing benchmarks are limited in scope and data diversity, and rely on rigid evaluation pipelines, preventing systematic and reliable assessment of modern MSAV models. To bridge these gaps, we introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation. Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios. Our evaluation framework improves robustness through an adaptive self-correction mechanism for shot segmentation, instance-wise rubrics for subjective metrics, and tool-grounded evidence extraction for complex judgments. Furthermore, MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%. Our systematic evaluation of 19 state-of-the-art closed- and open-source models shows that current systems still struggle with director-level control and fine-grained audio-visual synchronization, while modular or agentic generation pipelines offer a promising path toward narrowing the gap between open- and closed-source models. We will release the benchmark data and evaluation code to facilitate future research.

Xiang Wang, Huaxin Zhang, Shiwei Zhang et al.

This technical report presents our first place winning solution for temporal action detection task in CVPR-2022 AcitivityNet Challenge. The task aims to localize temporal boundaries of action instances with specific classes in long untrimmed videos. Recent mainstream attempts are based on dense boundary matchings and enumerate all possible combinations to produce proposals. We argue that the generated proposals contain rich contextual information, which may benefits detection confidence prediction. To this end, our method mainly consists of the following three steps: 1) action classification and feature extraction by Slowfast, CSN, TimeSformer, TSP, I3D-flow, VGGish-audio, TPN and ViViT; 2) proposal generation. Our proposed Context-aware Proposal Network (CPN) builds on top of BMN, GTAD and PRN to aggregate contextual information by randomly masking some proposal features. 3) action detection. The final detection prediction is calculated by assigning the proposals with corresponding video-level classifcation results. Finally, we ensemble the results under different feature combination settings and achieve 45.8% performance on the test set, which improves the champion result in CVPR-2021 ActivityNet Challenge by 1.1% in terms of average mAP.

Team Wan, Ang Wang, Baole Ai et al.

This report presents Wan, a comprehensive and open suite of video foundation models designed to push the boundaries of video generation. Built upon the mainstream diffusion transformer paradigm, Wan achieves significant advancements in generative capabilities through a series of innovations, including our novel VAE, scalable pre-training strategies, large-scale data curation, and automated evaluation metrics. These contributions collectively enhance the model's performance and versatility. Specifically, Wan is characterized by four key features: Leading Performance: The 14B model of Wan, trained on a vast dataset comprising billions of images and videos, demonstrates the scaling laws of video generation with respect to both data and model size. It consistently outperforms the existing open-source models as well as state-of-the-art commercial solutions across multiple internal and external benchmarks, demonstrating a clear and significant performance superiority. Comprehensiveness: Wan offers two capable models, i.e., 1.3B and 14B parameters, for efficiency and effectiveness respectively. It also covers multiple downstream applications, including image-to-video, instruction-guided video editing, and personal video generation, encompassing up to eight tasks. Consumer-Grade Efficiency: The 1.3B model demonstrates exceptional resource efficiency, requiring only 8.19 GB VRAM, making it compatible with a wide range of consumer-grade GPUs. Openness: We open-source the entire series of Wan, including source code and all models, with the goal of fostering the growth of the video generation community. This openness seeks to significantly expand the creative possibilities of video production in the industry and provide academia with high-quality video foundation models. All the code and models are available at https://github.com/Wan-Video/Wan2.1.

Biao Gong, Siteng Huang, Yutong Feng et al.

Diffusion models have recently achieved remarkable progress in generating realistic images. However, challenges remain in accurately understanding and synthesizing the layout requirements in the textual prompts. To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time. Specifically, following a "check-locate-rectify" pipeline, the system first analyses the prompt to generate the target layout and compares it with the intermediate outputs to automatically detect errors. Then, by moving the located activations and making intra- and inter-map adjustments, the rectification process can be performed with negligible computational overhead. To evaluate SimM over a range of layout requirements, we present a benchmark SimMBench that compensates for the lack of superlative spatial relations in existing datasets. And both quantitative and qualitative results demonstrate the effectiveness of the proposed SimM in calibrating the layout inconsistencies. Our project page is at https://simm-t2i.github.io/SimM.

Shiwei Zhang, Xiaodong Yi, Lansong Diao et al.

This paper presents TAG, an automatic system to derive optimized DNN training graph and its deployment onto any device topology, for expedited training in device- and topology- heterogeneous ML clusters. We novelly combine both the DNN computation graph and the device topology graph as input to a graph neural network (GNN), and join the GNN with a search-based method to quickly identify optimized distributed training strategies. To reduce communication in a heterogeneous cluster, we further explore a lossless gradient compression technique and solve a combinatorial optimization problem to automatically apply the technique for training time minimization. We evaluate TAG with various representative DNN models and device topologies, showing that it can achieve up to 4.56x training speed-up as compared to existing schemes. TAG can produce efficient deployment strategies for both unseen DNN models and unseen device topologies, without heavy fine-tuning.

Shiwei Zhang, Lansong Diao, Siyu Wang et al.

We present Rhino, a system for accelerating tensor programs with automatic parallelization on AI platform for real production environment. It transforms a tensor program written for a single device into an equivalent distributed program that is capable of scaling up to thousands of devices with no user configuration. Rhino firstly works on a semantically independent intermediate representation of tensor programs, which facilitates its generalization to unprecedented applications. Additionally, it implements a task-oriented controller and a distributed runtime for optimal performance. Rhino explores on a complete and systematic parallelization strategy space that comprises all the paradigms commonly employed in deep learning (DL), in addition to strided partitioning and pipeline parallelism on non-linear models. Aiming to efficiently search for a near-optimal parallel execution plan, our analysis of production clusters reveals general heuristics to speed up the strategy search. On top of it, two optimization levels are designed to offer users flexible trade-offs between the search time and strategy quality. Our experiments demonstrate that Rhino can not only re-discover the expert-crafted strategies of classic, research and production DL models, but also identify novel parallelization strategies which surpass existing systems for novel models.

Yujie Wei, Xinyu Liu, Shiwei Zhang et al.

While large-scale diffusion models have revolutionized video synthesis, achieving precise control over both multi-subject identity and multi-granularity motion remains a significant challenge. Recent attempts to bridge this gap often suffer from limited motion granularity, control ambiguity, and identity degradation, leading to suboptimal performance on identity preservation and motion control. In this work, we present DreamVideo-Omni, a unified framework enabling harmonious multi-subject customization with omni-motion control via a progressive two-stage training paradigm. In the first stage, we integrate comprehensive control signals for joint training, encompassing subject appearances, global motion, local dynamics, and camera movements. To ensure robust and precise controllability, we introduce a condition-aware 3D rotary positional embedding to coordinate heterogeneous inputs and a hierarchical motion injection strategy to enhance global motion guidance. Furthermore, to resolve multi-subject ambiguity, we introduce group and role embeddings to explicitly anchor motion signals to specific identities, effectively disentangling complex scenes into independent controllable instances. In the second stage, to mitigate identity degradation, we design a latent identity reward feedback learning paradigm by training a latent identity reward model upon a pretrained video diffusion backbone. This provides motion-aware identity rewards in the latent space, prioritizing identity preservation aligned with human preferences. Supported by our curated large-scale dataset and the comprehensive DreamOmni Bench for multi-subject and omni-motion control evaluation, DreamVideo-Omni demonstrates superior performance in generating high-quality videos with precise controllability.

Lingling Cai, Kang Zhao, Hangjie Yuan et al.

Text-to-video diffusion models have made remarkable advancements. Driven by their ability to generate temporally coherent videos, research on zero-shot video editing using these fundamental models has expanded rapidly. To enhance editing quality, structural controls are frequently employed in video editing. Among these techniques, cross-attention mask control stands out for its effectiveness and efficiency. However, when cross-attention masks are naively applied to video editing, they can introduce artifacts such as blurring and flickering. Our experiments uncover a critical factor overlooked in previous video editing research: cross-attention masks are not consistently clear but vary with model structure and denoising timestep. To address this issue, we propose the metric Mask Matching Cost (MMC) that quantifies this variability and propose FreeMask, a method for selecting optimal masks tailored to specific video editing tasks. Using MMC-selected masks, we further improve the masked fusion mechanism within comprehensive attention features, e.g., temp, cross, and self-attention modules. Our approach can be seamlessly integrated into existing zero-shot video editing frameworks with better performance, requiring no control assistance or parameter fine-tuning but enabling adaptive decoupling of unedited semantic layouts with mask precision control. Extensive experiments demonstrate that FreeMask achieves superior semantic fidelity, temporal consistency, and editing quality compared to state-of-the-art methods.

Xinyu Liu, Hangjie Yuan, Yujie Wei et al.

Video unified models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vision-language models (VLMs). We attribute this gap to two factors: 1) existing datasets are inadequate for training and evaluating reasoning-aware video editing, and 2) an inherent disconnect between the models' reasoning and editing capabilities, which prevents the rich understanding from effectively instructing the editing process. Bridging this gap requires an integrated framework that connects reasoning with visual transformation. To address this gap, we introduce the Reason-Informed Video Editing (RVE) task, which requires reasoning about physical plausibility and causal dynamics during editing. To support systematic evaluation, we construct RVE-Bench, a comprehensive benchmark with two complementary subsets: Reasoning-Informed Video Editing and In-Context Video Generation. These subsets cover diverse reasoning dimensions and real-world editing scenarios. Building upon this foundation, we propose the ReViSE, a Self-Reflective Reasoning (SRF) framework that unifies generation and evaluation within a single architecture. The model's internal VLM provides intrinsic feedback by assessing whether the edited video logically satisfies the given instruction. The differential feedback that refines the generator's reasoning behavior during training. Extensive experiments on RVE-Bench demonstrate that ReViSE significantly enhances editing accuracy and visual fidelity, achieving a 32% improvement of the Overall score in the reasoning-informed video editing subset over state-of-the-art methods.

Ruihang Chu, Yefei He, Zhekai Chen et al.

We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse control granularity and limited scalability, leaving their outputs insufficient for practical use. We narrow this gap by achieving precise and high-quality motion control. Our core idea is to directly make the original condition features motion-aware for guiding video synthesis. To this end, we first represent object motions with dense point trajectories, allowing fine-grained control over the scene. We then project these trajectories into latent space and propagate the first frame's features along each trajectory, producing an aligned spatiotemporal feature map that tells how each scene element should move. This feature map serves as the updated latent condition, which is naturally integrated into the off-the-shelf image-to-video model, e.g., Wan-I2V-14B, as motion guidance without any architecture change. It removes the need for auxiliary motion encoders and makes fine-tuning base models easily scalable. Through scaled training, Wan-Move generates 5-second, 480p videos whose motion controllability rivals Kling 1.5 Pro's commercial Motion Brush, as indicated by user studies. To support comprehensive evaluation, we further design MoveBench, a rigorously curated benchmark featuring diverse content categories and hybrid-verified annotations. It is distinguished by larger data volume, longer video durations, and high-quality motion annotations. Extensive experiments on MoveBench and the public dataset consistently show Wan-Move's superior motion quality. Code, models, and benchmark data are made publicly available.

Zhaohe Liao, Kaixun Jiang, Zhihang Liu et al.

Although image generation has boosted various applications via its rapid evolution, whether the state-of-the-art models are able to produce ready-to-use academic illustrations for papers is still largely unexplored. Directly comparing or evaluating the illustration with VLM is native but requires oracle multi-modal understanding ability, which is unreliable for long and complex texts and illustrations. To address this, we propose AIBench, the first benchmark using VQA for evaluating logic correctness of the academic illustrations and VLMs for assessing aesthetics. In detail, we designed four levels of questions proposed from a logic diagram summarized from the method part of the paper, which query whether the generated illustration aligns with the paper on different scales. Our VQA-based approach raises more accurate and detailed evaluations on visual-logical consistency while relying less on the ability of the judger VLM. With our high-quality AIBench, we conduct extensive experiments and conclude that the performance gap between models on this task is significantly larger than general ones, reflecting their various complex reasoning and high-density generation ability. Further, the logic and aesthetics are hard to optimize simultaneously as in handcrafted illustrations. Additional experiments further state that test-time scaling on both abilities significantly boosts the performance on this task.

Shiwei Zhang, Mingfang Wu, Xiuzhen Zhang

In support of open and reproducible research, there has been a rapidly increasing number of datasets made available for research. As the availability of datasets increases, it becomes more important to have quality metadata for discovering and reusing them. Yet, it is a common issue that datasets often lack quality metadata due to limited resources for data curation. Meanwhile, technologies such as artificial intelligence and large language models (LLMs) are progressing rapidly. Recently, systems based on these technologies, such as ChatGPT, have demonstrated promising capabilities for certain data curation tasks. This paper proposes to leverage LLMs for cost-effective annotation of subject metadata through the LLM-based in-context learning. Our method employs GPT-3.5 with prompts designed for annotating subject metadata, demonstrating promising performance in automatic metadata annotation. However, models based on in-context learning cannot acquire discipline-specific rules, resulting in lower performance in several categories. This limitation arises from the limited contextual information available for subject inference. To the best of our knowledge, we are introducing, for the first time, an in-context learning method that harnesses large language models for automated subject metadata annotation.

Xiang Wang, Shiwei Zhang, Longxiang Tang et al.

This report presents UniAnimate-DiT, an advanced project that leverages the cutting-edge and powerful capabilities of the open-source Wan2.1 model for consistent human image animation. Specifically, to preserve the robust generative capabilities of the original Wan2.1 model, we implement Low-Rank Adaptation (LoRA) technique to fine-tune a minimal set of parameters, significantly reducing training memory overhead. A lightweight pose encoder consisting of multiple stacked 3D convolutional layers is designed to encode motion information of driving poses. Furthermore, we adopt a simple concatenation operation to integrate the reference appearance into the model and incorporate the pose information of the reference image for enhanced pose alignment. Experimental results show that our approach achieves visually appearing and temporally consistent high-fidelity animations. Trained on 480p (832x480) videos, UniAnimate-DiT demonstrates strong generalization capabilities to seamlessly upscale to 720P (1280x720) during inference. The training and inference code is publicly available at https://github.com/ali-vilab/UniAnimate-DiT.

Shiwei Zhang, Zhengzheng Wang, Qing Liu et al.

This paper presents a new annotation method called Sparse Annotation (SA) for crowd counting, which reduces human labeling efforts by sparsely labeling individuals in an image. We argue that sparse labeling can reduce the redundancy of full annotation and capture more diverse information from distant individuals that is not fully captured by Partial Annotation methods. Besides, we propose a point-based Progressive Point Matching network (PPM) to better explore the crowd from the whole image with sparse annotation, which includes a Proposal Matching Network (PMN) and a Performance Restoration Network (PRN). The PMN generates pseudo-point samples using a basic point classifier, while the PRN refines the point classifier with the pseudo points to maximize performance. Our experimental results show that PPM outperforms previous semi-supervised crowd counting methods with the same amount of annotation by a large margin and achieves competitive performance with state-of-the-art fully-supervised methods.

Yifeng Ma, Shiwei Zhang, Jiayu Wang et al.

Emotional talking head generation has attracted growing attention. Previous methods, which are mainly GAN-based, still struggle to consistently produce satisfactory results across diverse emotions and cannot conveniently specify personalized emotions. In this work, we leverage powerful diffusion models to address the issue and propose DreamTalk, a framework that employs meticulous design to unlock the potential of diffusion models in generating emotional talking heads. Specifically, DreamTalk consists of three crucial components: a denoising network, a style-aware lip expert, and a style predictor. The diffusion-based denoising network can consistently synthesize high-quality audio-driven face motions across diverse emotions. To enhance lip-motion accuracy and emotional fullness, we introduce a style-aware lip expert that can guide lip-sync while preserving emotion intensity. To more conveniently specify personalized emotions, a diffusion-based style predictor is utilized to predict the personalized emotion directly from the audio, eliminating the need for extra emotion reference. By this means, DreamTalk can consistently generate vivid talking faces across diverse emotions and conveniently specify personalized emotions. Extensive experiments validate DreamTalk's effectiveness and superiority. The code is available at https://github.com/ali-vilab/dreamtalk.

Quanhao Li, Junqiu Yu, Kaixun Jiang et al.

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint optimization suffers from cross-task interference and imbalance, while cascade RL is cumbersome and prone to catastrophic forgetting. We propose DiffusionOPD, a new multi-task training paradigm for diffusion models based on Online Policy Distillation (OPD). DiffusionOPD first trains task-specific teachers independently, then distills their capabilities into a unified student along the student own rollout trajectories. This decouples single-task exploration from multi-task integration and avoids the optimization burden of solving all tasks jointly from scratch. Theoretically, we lift the OPD framework from discrete tokens to continuous-state Markov processes, deriving a closed-form per-step KL objective that unifies both stochastic SDE and deterministic ODE refinement via mean-matching. We formally and empirically demonstrate that this analytic gradient provides lower variance and better generality compared to conventional PPO-style policy gradients. Extensive experiments show that DiffusionOPD consistently surpasses both multi-reward RL and cascade RL baselines in training efficiency and final performance, while achieving state-of-the-art results on all evaluated benchmarks.

Yujie Wei, Chenglong Ma, Jianxiong Gao et al.

Reconstructing dynamic visual experiences as videos from functional magnetic resonance imaging (fMRI) is pivotal for advancing the understanding of neural processes. However, current fMRI-to-video reconstruction methods are hindered by a semantic gap between noisy fMRI signals and the rich content of videos, stemming from a reliance on incomplete semantic embeddings that neither capture video-specific cues (e.g., actions) nor integrate prior knowledge. To this end, we draw inspiration from the dual-pathway processing mechanism in human brain and introduce CineNeuron, a novel hierarchical framework for semantically enhanced video reconstruction from fMRI signals with two synergistic stages. First, a bottom-up semantic enrichment stage maps fMRI signals to a rich embedding space that comprehensively captures textual semantics, image contents, action concepts, and object categories. Second, a top-down memory integration stage utilizes the proposed Mixture-of-Memories method to dynamically select relevant "memories" from previously seen data and fuse them with the fMRI embedding to refine the video reconstruction. Extensive experimental results on two fMRI-to-video benchmarks demonstrate that CineNeuron surpasses state-of-the-art methods across various metrics.

Zhekai Chen, Ruihang Chu, Yukang Chen et al.

Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and promising performance. In this work, we present TTS-VAR, the first general test-time scaling framework for visual auto-regressive (VAR) models, modeling the generation process as a path searching problem. To dynamically balance computational efficiency with exploration capacity, we first introduce an adaptive descending batch size schedule throughout the causal generation process. Besides, inspired by VAR's hierarchical coarse-to-fine multi-scale generation, our framework integrates two key components: (i) At coarse scales, we observe that generated tokens are hard for evaluation, possibly leading to erroneous acceptance of inferior samples or rejection of superior samples. Noticing that the coarse scales contain sufficient structural information, we propose clustering-based diversity search. It preserves structural variety through semantic feature clustering, enabling later selection on samples with higher potential. (ii) In fine scales, resampling-based potential selection prioritizes promising candidates using potential scores, which are defined as reward functions incorporating multi-scale generation history. Experiments on the powerful VAR model Infinity show a notable 8.7% GenEval score improvement (from 0.69 to 0.75). Key insights reveal that early-stage structural features effectively influence final quality, and resampling efficacy varies across generation scales. Code is available at https://github.com/ali-vilab/TTS-VAR.

Wenbo Pan, Shujie Liu, Xiangyang Zhou et al.

Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory design tailored to specific domains, such as semantic retrieval for conversations or skills reused for coding. However, a memory system optimized for one purpose frequently fails to transfer to others. To address this limitation, we introduce M$^\star$, a method that automatically discovers task-optimized memory harnesses through executable program evolution. Specifically, M$^\star$ models an agent memory system as a memory program written in Python. This program encapsulates the data Schema, the storage Logic, and the agent workflow Instructions. We optimize these components jointly using a reflective code evolution method; this approach employs a population-based search strategy and analyzes evaluation failures to iteratively refine the candidate programs. We evaluate M$^\star$ on four distinct benchmarks spanning conversation, embodied planning, and expert reasoning. Our results demonstrate that M$^\star$ improves performance over existing fixed-memory baselines robustly across all evaluated tasks. Furthermore, the evolved memory programs exhibit structurally distinct processing mechanisms for each domain. This finding indicates that specializing the memory mechanism for a given task explores a broad design space and provides a superior solution compared to general-purpose memory paradigms.

Yujie Wei, Shiwei Zhang, Zhiwu Qing et al.

Customized generation using diffusion models has made impressive progress in image generation, but remains unsatisfactory in the challenging video generation task, as it requires the controllability of both subjects and motions. To that end, we present DreamVideo, a novel approach to generating personalized videos from a few static images of the desired subject and a few videos of target motion. DreamVideo decouples this task into two stages, subject learning and motion learning, by leveraging a pre-trained video diffusion model. The subject learning aims to accurately capture the fine appearance of the subject from provided images, which is achieved by combining textual inversion and fine-tuning of our carefully designed identity adapter. In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern. Combining these two lightweight and efficient adapters allows for flexible customization of any subject with any motion. Extensive experimental results demonstrate the superior performance of our DreamVideo over the state-of-the-art methods for customized video generation. Our project page is at https://dreamvideo-t2v.github.io.

Xiang Wang, Shiwei Zhang, Zhiwu Qing et al.

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global interactions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://github.com/wangxiang1230/OadTR.

Xiaolong Liu, Qimeng Wang, Yao Hu et al.

Temporal action detection (TAD) aims to determine the semantic label and the temporal interval of every action instance in an untrimmed video. It is a fundamental and challenging task in video understanding. Previous methods tackle this task with complicated pipelines. They often need to train multiple networks and involve hand-designed operations, such as non-maximal suppression and anchor generation, which limit the flexibility and prevent end-to-end learning. In this paper, we propose an end-to-end Transformer-based method for TAD, termed TadTR. Given a small set of learnable embeddings called action queries, TadTR adaptively extracts temporal context information from the video for each query and directly predicts action instances with the context. To adapt Transformer to TAD, we propose three improvements to enhance its locality awareness. The core is a temporal deformable attention module that selectively attends to a sparse set of key snippets in a video. A segment refinement mechanism and an actionness regression head are designed to refine the boundaries and confidence of the predicted instances, respectively. With such a simple pipeline, TadTR requires lower computation cost than previous detectors, while preserving remarkable performance. As a self-contained detector, it achieves state-of-the-art performance on THUMOS14 (56.7% mAP) and HACS Segments (32.09% mAP). Combined with an extra action classifier, it obtains 36.75% mAP on ActivityNet-1.3. Code is available at https://github.com/xlliu7/TadTR.

Xiang Wang, Shiwei Zhang, Zhiwu Qing et al.

Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation. Particularly, we design an effective Self-supervised Semi-supervised Temporal Action Proposal (SSTAP) framework. The SSTAP contains two crucial branches, i.e., temporal-aware semi-supervised branch and relation-aware self-supervised branch. The semi-supervised branch improves the proposal model by introducing two temporal perturbations, i.e., temporal feature shift and temporal feature flip, in the mean teacher framework. The self-supervised branch defines two pretext tasks, including masked feature reconstruction and clip-order prediction, to learn the relation of temporal clues. By this means, SSTAP can better explore unlabeled videos, and improve the discriminative abilities of learned action features. We extensively evaluate the proposed SSTAP on THUMOS14 and ActivityNet v1.3 datasets. The experimental results demonstrate that SSTAP significantly outperforms state-of-the-art semi-supervised methods and even matches fully-supervised methods. Code is available at https://github.com/wangxiang1230/SSTAP.

Hangjie Yuan, Shiwei Zhang, Xiang Wang et al. · cambridge

Diffusion models have emerged as the de facto paradigm for video generation. However, their reliance on web-scale data of varied quality often yields results that are visually unappealing and misaligned with the textual prompts. To tackle this problem, we propose InstructVideo to instruct text-to-video diffusion models with human feedback by reward fine-tuning. InstructVideo has two key ingredients: 1) To ameliorate the cost of reward fine-tuning induced by generating through the full DDIM sampling chain, we recast reward fine-tuning as editing. By leveraging the diffusion process to corrupt a sampled video, InstructVideo requires only partial inference of the DDIM sampling chain, reducing fine-tuning cost while improving fine-tuning efficiency. 2) To mitigate the absence of a dedicated video reward model for human preferences, we repurpose established image reward models, e.g., HPSv2. To this end, we propose Segmental Video Reward, a mechanism to provide reward signals based on segmental sparse sampling, and Temporally Attenuated Reward, a method that mitigates temporal modeling degradation during fine-tuning. Extensive experiments, both qualitative and quantitative, validate the practicality and efficacy of using image reward models in InstructVideo, significantly enhancing the visual quality of generated videos without compromising generalization capabilities. Code and models will be made publicly available.

Xiang Wang, Shiwei Zhang, Han Zhang et al.

Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models. However, the consistency model in the more challenging and resource-consuming video generation is still less explored. In this report, we present the VideoLCM framework to fill this gap, which leverages the concept of consistency models from image generation to efficiently synthesize videos with minimal steps while maintaining high quality. VideoLCM builds upon existing latent video diffusion models and incorporates consistency distillation techniques for training the latent consistency model. Experimental results reveal the effectiveness of our VideoLCM in terms of computational efficiency, fidelity and temporal consistency. Notably, VideoLCM achieves high-fidelity and smooth video synthesis with only four sampling steps, showcasing the potential for real-time synthesis. We hope that VideoLCM can serve as a simple yet effective baseline for subsequent research. The source code and models will be publicly available.

Feng Liu, Shiwei Zhang, Xiaofeng Wang et al.

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly selected timesteps. However, such a strategy neglects the fact that differences among model outputs are not uniform across timesteps, which hinders selecting the appropriate model outputs to cache, leading to a poor balance between inference efficiency and visual quality. In this study, we introduce Timestep Embedding Aware Cache (TeaCache), a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps. Rather than directly using the time-consuming model outputs, TeaCache focuses on model inputs, which have a strong correlation with the modeloutputs while incurring negligible computational cost. TeaCache first modulates the noisy inputs using the timestep embeddings to ensure their differences better approximating those of model outputs. TeaCache then introduces a rescaling strategy to refine the estimated differences and utilizes them to indicate output caching. Experiments show that TeaCache achieves up to 4.41x acceleration over Open-Sora-Plan with negligible (-0.07% Vbench score) degradation of visual quality.

Zhiwu Qing, Shiwei Zhang, Jiayu Wang et al.

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial content and temporal dynamics together, leading to a notably increased complexity of text-to-video generation (T2V). In this work, we propose HiGen, a diffusion model-based method that improves performance by decoupling the spatial and temporal factors of videos from two perspectives, i.e., structure level and content level. At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser. Specifically, we generate spatially coherent priors using text during spatial reasoning and then generate temporally coherent motions from these priors during temporal reasoning. At the content level, we extract two subtle cues from the content of the input video that can express motion and appearance changes, respectively. These two cues then guide the model's training for generating videos, enabling flexible content variations and enhancing temporal stability. Through the decoupled paradigm, HiGen can effectively reduce the complexity of this task and generate realistic videos with semantics accuracy and motion stability. Extensive experiments demonstrate the superior performance of HiGen over the state-of-the-art T2V methods.