Motion is a salient cue to recognize actions in video. Modern action recognition models leverage motion information either explicitly by using optical flow as input or implicitly by means of 3D convolutional filters that simultaneously capture appearance and motion information. This paper proposes an alternative approach based on a learnable correlation operator that can be used to establish frame-toframe matches over convolutional feature maps in the different layers of the network. The proposed architecture enables the fusion of this explicit temporal matching information with traditional appearance cues captured by 2D convolution. Our correlation network compares favorably with widely-used 3D CNNs for video modeling, and achieves competitive results over the prominent two-stream network while being much faster to train. We empirically demonstrate that correlation networks produce strong results on a variety of video datasets, and outperform the state of the art on four popular benchmarks for action recognition: Kinetics, Something-Something, Diving48 and Sports1M.
A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to "imagify" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information tha…
Samsung AI Centre（三星人工智能中心）；University of Surrey（萨里大学）
Attentive video modeling is essential for action recognition in unconstrained videos due to their rich yet redundant information over space and time. However, introducing attention in a deep neural network for action recognition is challenging for two reasons. First, an effective attention module needs to learn what (objects and their local motion patterns), where (spatially), and when (temporally) to focus on. Second, a video attention module must be efficient because existing action recognition models already suffer from high computational cost. To address both challenges, a novel What-Where…
Nanjing University（南京大学）；Tencent AI Lab（腾讯人工智能实验室）；Fudan University（复旦大学）；Shanghai AI Lab（上海人工智能实验室）
The relation modeling between actors and scene context advances video action detection where the correlation of multiple actors makes their action recognition challenging. Existing studies model each actor and scene relation to improve action recognition. However, the scene variations and background interference limit the effectiveness of this relation modeling. In this paper, we propose to select actor-related scene context, rather than directly leverage raw video scenario, to improve relation modeling. We develop a Cycle Actor-Context Relation network (CycleACR) where there is a symmetric gr…
TRACE: Temporal Grounding Video LLM via Causal Event Modeling
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；Tencent PCG（腾讯平台与内容事业群）；Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS)（深圳市人工智能与机器人研究院）；Guangdong Provincial Key Laboratory of Future Networks of Intelligence（广东省未来智能网络重点实验室）
Visual data and text data are composed of information at multiple granularities. A video can describe a complex scene that is composed of multiple clips or shots, where each depicts a semantically coherent event or action. Similarly, a paragraph may contain sentences with different topics, which collectively conveys a coherent message or story. In this paper, we investigate the modeling techniques for such hierarchical sequential data where there are correspondences across multiple modalities. Specifically, we introduce hierarchical sequence embedding (HSE), a generic model for embedding seque…
Unified vision-language frameworks have greatly advanced in recent years, most of which adopt an encoder-decoder architecture to unify image-text tasks as sequence-to-sequence generation. However, existing video-language (VidL) models still require task-specific designs in model architecture and training objectives for each task. In this work, we explore a unified VidL framework LAVENDER, where Masked Language Modeling (MLM) is used as the common interface for all pre-training and downstream tasks. Such unification leads to a simplified model architecture, where only a lightweight MLM head, in…
University of Rochester（罗切斯特大学）；University of Michigan（密歇根大学）
Video action recognition, a critical problem in video understanding, has been gaining increasing attention. To identify actions induced by complex object-object interactions, we need to consider not only spatial relations among objects in a single frame, but also temporal relations among different or the same objects across multiple frames. However, existing approaches that model video representations and non-local features are either incapable of explicitly modeling relations at the object-object level or unable to handle streaming videos. In this paper, we propose a novel dynamic hidden grap…
National Taiwan University（台湾大学）；Mobile Drive Technology（Mobile Drive科技公司）
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of temporal modeling also suffer from weak and noisy alignment between modalities. To learn fine-grained visual understanding, we decouple spatial-temporal modeling and propose a hybrid pipeline, Decoupled Spatial-Temporal Encoders, integrating an image- and a video-language encoder. The former encodes spatial semantics from larger but sparsely sampled frames inde…
InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
Shanghai AI Laboratory（上海人工智能实验室）；Nanjing University（南京大学）；Shanghai Innovation Institute（上海创新研究院）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）
Peking University（北京大学）；The University of Hong Kong（香港大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks. However, the pre-training process is computationally expensive due to the requirement of millions of video-text pairs and the redundant data structure of each video. To mitigate these problems, we propose LiteVL, which adapts a pre-trained image-language model BLIP into a video-text model directly on downstream tasks, without heavy pre-training. To enhance the temporal modeling lacking in the image-language model, we propose to add temporal attention modules in the image encoder o…
Google Research（谷歌研究院）；The Ohio State University（俄亥俄州立大学）
We explore an efficient approach to establish a foundational video-text model. We present VideoCoCa that maximally reuses a pretrained image-text contrastive captioner (CoCa) model and adapt it to video-text tasks with minimal extra training. While previous works adapt image-text models with various cross-frame fusion modules, we find that the generative attentional pooling and contrastive attentional pooling layers in CoCa are instantly adaptable to flattened frame embeddings, yielding state-of-the-art results on zero-shot video classification and zero-shot text-to-video retrieval. Furthermor…
Response-G1: Explicit Scene Graph Modeling for Proactive Streaming Video Understanding
Northwestern Polytechnical University（北华大学）；Tsinghua University（清华大学）；The Hong Kong University of Science and Technology（香港科技大学）；Harbin Engineering University（哈尔滨工程大学）
VideoPCDNet: Video Parsing and Prediction with Phase Correlation Networks
Autonomous Intelligent Systems group, University of Bonn, Germany（bonn大学自主智能系统小组）；Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）；Center for Robotics, University of Bonn, Germany（bonn大学机器人中心）
Microsoft Dynamics 365 AI Research（微软Dynamics 365人工智能研究院）
We present HERO, a novel framework for large-scale video+language omni-representation learning. HERO encodes multimodal inputs in a hierarchical structure, where local context of a video frame is captured by a Cross-modal Transformer via multimodal fusion, and global video context is captured by a Temporal Transformer. In addition to standard Masked Language Modeling (MLM) and Masked Frame Modeling (MFM) objectives, we design two new pre-training tasks: (i) Video-Subtitle Matching (VSM), where the model predicts both global and local temporal alignment; and (ii) Frame Order Modeling (FOM), whe…
NAVER AI Lab（NAVER人工智能实验室）；KAIST AI（韩国科学技术院人工智能学院）；SNU AIIS（首尔国立大学人工智能研究所）
Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attention mechanism may not be ideal since its computational cost quadratically increases as the video length increases. Rather, previous studies have relied on offline feature extraction or frame sampling to represent the video efficiently, focusing on cross-modal modeling in short video clips. In this paper, we propose a semi-parametric video-grounded text generation model, SeViT, a novel perspective on scalable video-la…
Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of modeling long-range dependencies compared to CNN-based models. However, significant computation overheads, resulted from the quadratic complexity of self-attention on top of a tremendous number of tokens, limit the use of existing video transformers in applications with limited resources like mobile devices. In this paper, we extend Mobile-Former to Video Mobile-Former, which decouples the video architecture into a lig…
The goal of video summarization is to select keyframes that are visually diverse and can represent a whole story of an input video. State-of-the-art approaches for video summarization have mostly regarded the task as a frame-wise keyframe selection problem by aggregating all frames with equal weight. However, to find informative parts of the video, it is necessary to consider how all the frames of the video are related to each other. To this end, we cast video summarization as a graph modeling problem. We propose recursive graph modeling networks for video summarization, termed SumGraph, to re…
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 …
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Tencent AI Lab（腾讯人工智能实验室）
Video deblurring is still an unsolved problem due to the challenging spatio-temporal modeling process. While existing convolutional neural network-based methods show a limited capacity for effective spatial and temporal modeling for video deblurring. This paper presents VDTR, an effective Transformer-based model that makes the first attempt to adapt Transformer for video deblurring. VDTR exploits the superior long-range and relation modeling capabilities of Transformer for both spatial and temporal modeling. However, it is challenging to design an appropriate Transformer-based model for video …
Video-based person reID is an important task, which has received much attention in recent years due to the increasing demand in surveillance and camera networks. A typical video-based person reID system consists of three parts: an image-level feature extractor (e.g. CNN), a temporal modeling method to aggregate temporal features and a loss function. Although many methods on temporal modeling have been proposed, it is hard to directly compare these methods, because the choice of feature extractor and loss function also have a large impact on the final performance. We comprehensively study and c…
Boston University（波士顿大学）；University of California Berkeley（加州大学伯克利分校）
Video generation is an inherently challenging task, as it requires modeling realistic temporal dynamics as well as spatial content. Existing methods entangle the two intrinsically different tasks of motion and content creation in a single generator network, but this approach struggles to simultaneously generate plausible motion and content. To im-prove motion modeling in video generation tasks, we propose a two-stream model that disentangles motion generation from content generation, called a Two-Stream Variational Adversarial Network (TwoStreamVAN). Given an action label and a noise vector, o…
This paper focuses on task recognition and action segmentation in weakly-labeled instructional videos, where only the ordered sequence of video-level actions is available during training. We propose a two-stream framework, which exploits semantic and temporal hierarchies to recognize top-level tasks in instructional videos. Further, we present a novel top-down weakly-supervised action segmentation approach, where the predicted task is used to constrain the inference of fine-grained action sequences. Experimental results on the popular Breakfast and Cooking 2 datasets show that our two-stream h…
Outdoor videos sometimes contain unexpected rain streaks due to the rainy weather, which bring negative effects on subsequent computer vision applications, e.g., video surveillance, object recognition and tracking, etc. In this paper, we propose a directional regularized tensor-based video deraining model by taking into consideration the arbitrary direction of rain streaks. In particular, the sparsity of rain streaks in spatial and derivative domains, the spatiotemporal sparsity and low-rank property of video background are incorporated into the proposed method. Different from many previous me…
Shenzhen University（深圳大学）；Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University（中山大学孙逸仙纪念医院）
Breast cancer is one of the leading causes of cancer deaths in women. As the primary output of breast screening, breast ultrasound (US) video contains exclusive dynamic information for cancer diagnosis. However, training models for video analysis is non-trivial as it requires a voluminous dataset which is also expensive to annotate. Furthermore, the diagnosis of breast lesion faces unique challenges such as inter-class similarity and intra-class variation. In this paper, we propose a pioneering approach that directly utilizes US videos in computer-aided breast cancer diagnosis. It leverages ma…
VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling
Nanjing University（南京大学）；Institute of Artificial Intelligence, China Telecom (TeleAI)（中国电信人工智能研究院（TeleAI））；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
Object detection in video is crucial for many applications. Compared to images, video provides additional cues which can help to disambiguate the detection problem. Our goal in this paper is to learn discriminative models for the temporal evolution of object appearance and to use such models for object detection. To model temporal evolution, we introduce space-time tubes corresponding to temporal sequences of bounding boxes. We propose two CNN architectures for generating and classifying tubes, respectively. Our tube proposal network (TPN) first generates a large number of spatio-temporal tube…
