Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training, while offering limited insights into the direct impact of representations on the video generation process. In this paper, we initially investigate the characteristics of features in intermediate layers, finding substantial variations in attention maps across different layers. These variations lead to unstable semantic representations and contribute to cumulative differences between features, which ultimately reduce the similarity between adjacent frames and negatively affect temporal coherence. To address this, we propose RepVideo, an enhanced representation framework for text-to-video diffusion models. By accumulating features from neighboring layers to form enriched representations, this approach captures more stable semantic information. These enhanced representations are then used as inputs to the attention mechanism, thereby improving semantic expressiveness while ensuring feature consistency across adjacent frames. Extensive experiments demonstrate that our RepVideo not only significantly enhances the ability to generate accurate spatial appearances, such as capturing complex spatial relationships between multiple objects, but also improves temporal consistency in video generation.
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）科学与工程学院）；Future Network of Intelligence Institute, CUHK-Shenzhen, China（CUHK-深圳智能网络研究院）
Rethinking Reward Signals in Video GRPO: When Scores Become Targets
University of Science and Technology of China（中国科学技术大学）；Southeast University（东南大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）
Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation
Wuhan University（武汉大学）；University of Science and Technology of China（中国科学技术大学）；Hong Kong University of Science and Technology（香港科技大学）；Tsinghua University（清华大学）
RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-plane Networks
Max Planck Institute for intelligent Systems（马克斯·普朗克智能系统研究所）；Inria（法国国家信息与自动化研究所）；École normale supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；ELLIS Institute Tübingen（埃利斯研究所蒂宾根分所）
We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.
Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks
Peking University（北京大学）；Xiaomi EV（小米电动车）；Huazhong University of Science and Technology（华中科技大学）；Beijing Key Laboratory of Data Intelligence and Security (Peking University)（北京数据智能与安全重点实验室（北京大学））；Zhongguancun Academy（中关村学院）
State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content, leading to sub-optimal generalization performances. Recent data augmentation strategies have been reported to address the overfitting problems in static image classifiers. Despite the effectiveness on the static image classifiers, data augmentation has rarely been studied for videos. For the first time in the field, we systematically analyze the efficacy of various data augmentation strategies on the video classifica…
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
Nankai University（南开大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Linkoping University（林雪平大学）
Trained on large datasets, deep learning (DL) can accurately classify videos into hundreds of diverse classes. However, video data is expensive to annotate. Zero-shot learning (ZSL) proposes one solution to this problem. ZSL trains a model once, and generalizes to new tasks whose classes are not present in the training dataset. We propose the first end-to-end algorithm for ZSL in video classification. Our training procedure builds on insights from recent video classification literature and uses a trainable 3D CNN to learn the visual features. This is in contrast to previous video ZSL methods, …
Rethinking Representations for World-Action Modeling
Huazhong University of Science & Technology（华中科技大学）；D-Robotics（地瓜机器人）；Horizon Robotics（地平线机器人）；Fudan University（复旦大学）；Xi’an Jiaotong University（西安交通大学）
Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Model
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Shenzhen University（深圳大学）；Beijing University of Technology（北京工业大学）；JD Explore Academy（京东探索研究院）
Learning a good representation for space-time correspondence is the key for various computer vision tasks, including tracking object bounding boxes and performing video object pixel segmentation. To learn generalizable representation for correspondence in large-scale, a variety of self-supervised pretext tasks are proposed to explicitly perform object-level or patch-level similarity learning. Instead of following the previous literature, we propose to learn correspondence using Video Frame-level Similarity (VFS) learning, i.e, simply learning from comparing video frames. Our work is inspired b…
CyberAgent, Inc.（CyberAgent公司）；Osaka University（大阪大学）；Tampere University（坦佩雷大学）；University of Oulu（奥卢大学）
Video summarization is a technique to create a short skim of the original video while preserving the main stories/content. There exists a substantial interest in automatizing this process due to the rapid growth of the available material. The recent progress has been facilitated by public benchmark datasets, which enable easy and fair comparison of methods. Currently the established evaluation protocol is to compare the generated summary with respect to a set of reference summaries provided by the dataset. In this paper, we will provide in-depth assessment of this pipeline using two popular be…
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Horizon Robotics, Inc.（地平线机器人公司）；Xiamen University（厦门大学）
Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit fro…
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like raw pixel RGB values. In this paper, we propose masked video distillation (MVD), a simple yet effective two-stage masked feature modeling framework for video representation learning: firstly we pretrain an image (or video) model by recovering low-level features of masked patches, then we use the resulting features as targets for masked feature modeling. For …
Northwestern Polytechnical University（西北工业大学）；Ningbo Institute of Northwestern Polytechnical University（西北工业大学宁波研究院）；Nanchang University（南昌大学）；Shanghai Jiao Tong University（上海交通大学）
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain. By focusing on the benefits of joint auditory and visual information, most VSP methods are capable of exploiting semantic correlation between vision and audio modalities but ignoring the negative effects due to the temporal inconsistency of audio-visual intrinsics. Inspired by the biological inconsistency-correction within multi-sensory information, in this study, a consistency-aware audio-visual saliency prediction network (CASP-Net) is proposed, which takes a co…
Rethinking the Readout: Unlocking Video Backbones for AI-Generated Video Detection
Huazhong University of Science and Technology（华中科技大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Jilin University（吉林大学）；Vast Intelligence Lab（旷视智能实验室）
The University of Hong Kong（香港大学）；ByteDance Inc.（字节跳动公司）
In this paper, we empirically study how to make the most of low-resolution frames for efficient video recognition. Existing methods mainly focus on developing compact networks or alleviating temporal redundancy of video inputs to increase efficiency, whereas compressing frame resolution has rarely been considered a promising solution. A major concern is the poor recognition accuracy on low-resolution frames. We thus start by analyzing the underlying causes of performance degradation on low-resolution frames. Our key finding is that the major cause of degradation is not information loss in the …
Hefei University of Technology（合肥工业大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng National Laboratory（鹏城国家实验室）
With the rapid development of image restoration techniques, high-definition reconstruction of early videos has achieved impressive results. However, there are few studies about the interlacing artifacts that often appear in early videos and significantly affect visual perception. Traditional deinterlacing approaches are mainly focused on early interlacing scanning systems and thus cannot handle the complex and complicated artifacts in real-world early interlaced videos. Hence, this paper proposes a specific deinterlacing network (DIN), which is motivated by the traditional deinterlacing strate…
The Hong Kong University of Science and Technology（香港科技大学）
This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly efficient and robust framework. With the correspondences, every node in the current query frame is inferred by aggregating features from the past in an associative fashion. We cast the aggregation process as a voting problem and find that the existing inner-product affinity leads to poor use of memory…
Google Research（谷歌研究院）；University of California San Diego（加州大学圣地亚哥分校）
Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification. Three main challenges exist including spatial (image) feature representation, temporal information representation, and model/computation complexity. It was recently shown by Carreira and Zisserman that 3D CNNs, inflated from 2D networks and pretrained on ImageNet, could be a promising way for spatial and temporal representation learning. However, as for model/computation complexity, 3D CNNs are much …
