中文
相关论文

相关论文: Knowing Where to Focus: Event-aware Transformer fo…

200 篇论文

Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as…

In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings. However, each learned embedding does not have an…

计算机视觉与模式识别 · 计算机科学 2022-01-05 Yingming Wang , Xiangyu Zhang , Tong Yang , Jian Sun

Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare…

计算机视觉与模式识别 · 计算机科学 2022-04-01 Jue Wang , Lorenzo Torresani

With the rapid development of deep learning, video deraining has experienced significant progress. However, existing video deraining pipelines cannot achieve satisfying performance for scenes with rain layers of complex spatio-temporal…

计算机视觉与模式识别 · 计算机科学 2023-10-02 Yueyi Zhang , Jin Wang , Wenming Weng , Xiaoyan Sun , Zhiwei Xiong

Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query. Given the prevalent use of platforms like YouTube for information retrieval, the demand for MR techniques is significantly growing.…

计算机视觉与模式识别 · 计算机科学 2026-02-27 Seojeong Park , Jiho Choi , Kyungjune Baek , Hyunjung Shim

Video understanding tasks take many forms, from action detection to visual query localization and spatio-temporal grounding of sentences. These tasks differ in the type of inputs (only video, or video-query pair where query is an image…

计算机视觉与模式识别 · 计算机科学 2023-03-21 Raghav Goyal , Effrosyni Mavroudi , Xitong Yang , Sainbayar Sukhbaatar , Leonid Sigal , Matt Feiszli , Lorenzo Torresani , Du Tran

In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage…

计算机视觉与模式识别 · 计算机科学 2022-03-15 Ye Du , Zehua Fu , Qingjie Liu , Yunhong Wang

Recognizing and comprehending human actions and gestures is a crucial perception requirement for robots to interact with humans and carry out tasks in diverse domains, including service robotics, healthcare, and manufacturing. Event…

计算机视觉与模式识别 · 计算机科学 2023-08-29 Tristan de Blegiers , Ishan Rajendrakumar Dave , Adeel Yousaf , Mubarak Shah

Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…

计算机视觉与模式识别 · 计算机科学 2025-12-30 L'ea Dubois , Klaus Schmidt , Chengyu Wang , Ji-Hoon Park , Lin Wang , Santiago Munoz

Video Moment Retrieval (VMR) aims to retrieve relevant moments of an untrimmed video corresponding to the query. While cross-modal interaction approaches have shown progress in filtering out query-irrelevant information in videos, they…

人工智能 · 计算机科学 2024-08-26 Chenghua Gao , Min Li , Jianshuo Liu , Junxing Ren , Lin Chen , Haoyu Liu , Bo Meng , Jitao Fu , Wenwen Su

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or…

计算机视觉与模式识别 · 计算机科学 2019-01-23 Dongliang He , Xiang Zhao , Jizhou Huang , Fu Li , Xiao Liu , Shilei Wen

In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame $t$ may be entirely…

计算机视觉与模式识别 · 计算机科学 2021-10-26 Mandela Patrick , Dylan Campbell , Yuki M. Asano , Ishan Misra , Florian Metze , Christoph Feichtenhofer , Andrea Vedaldi , João F. Henriques

Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation…

计算机视觉与模式识别 · 计算机科学 2024-01-04 Ziyi Bai , Ruiping Wang , Xilin Chen

In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Haojian Huang , Kaijing Ma , Jin Chen , Haodong Chen , Zhou Wu , Xianghao Zang , Han Fang , Chao Ban , Hao Sun , Mulin Chen , Zhongjiang He

Multimodal transformer exhibits high capacity and flexibility to align image and text for visual grounding. However, the existing encoder-only grounding framework (e.g., TransVG) suffers from heavy computation due to the self-attention…

计算机视觉与模式识别 · 计算机科学 2023-10-27 Fengyuan Shi , Ruopeng Gao , Weilin Huang , Limin Wang

In this paper, we study the problem of weakly-supervised temporal grounding of sentence in video. Specifically, given an untrimmed video and a query sentence, our goal is to localize a temporal segment in the video that semantically…

计算机视觉与模式识别 · 计算机科学 2020-01-28 Zhenfang Chen , Lin Ma , Wenhan Luo , Peng Tang , Kwan-Yee K. Wong

This paper tackles a recently proposed Video Corpus Moment Retrieval task. This task is essential because advanced video retrieval applications should enable users to retrieve a precise moment from a large video corpus. We propose a novel…

多媒体 · 计算机科学 2021-09-22 Zhijian Hou , Chong-Wah Ngo , Wing Kwong Chan

It is well known that most of the conventional video question answering (VideoQA) datasets consist of easy questions requiring simple reasoning processes. However, long videos inevitably contain complex and compositional semantic structures…

计算机视觉与模式识别 · 计算机科学 2022-10-20 Jihyeon Lee , Wooyoung Kang , Eun-Sol Kim

Currently successful methods for video description are based on encoder-decoder sentence generation using recur-rent neural networks (RNNs). Recent work has shown the advantage of integrating temporal and/or spatial attention mechanisms…

计算机视觉与模式识别 · 计算机科学 2017-03-13 Chiori Hori , Takaaki Hori , Teng-Yok Lee , Kazuhiro Sumi , John R. Hershey , Tim K. Marks

Understanding videos requires more than answering open ended questions, it demands the ability to pinpoint when events occur and how entities interact across time. While recent Video LLMs have achieved remarkable progress in holistic…

计算机视觉与模式识别 · 计算机科学 2025-08-22 Pengcheng Fang , Yuxia Chen , Rui Guo