中文
相关论文

相关论文: In Defense of Clip-based Video Relation Detection

200 篇论文

Vision-Language Models (VLMs) are able to process increasingly longer videos. Yet, important visual information is easily lost throughout the entire context and missed by VLMs. Also, it is important to design tools that enable…

计算与语言 · 计算机科学 2026-01-09 Galann Pennec , Zhengyuan Liu , Nicholas Asher , Philippe Muller , Nancy F. Chen

Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as their spatial-temporal correlations from the redundant frames…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Chengpeng Dai , Fuhai Chen , Xiaoshuai Sun , Rongrong Ji , Qixiang Ye , Yongjian Wu

The success of CLIP has driven substantial progress in text-video retrieval. However, current methods often suffer from "blind" feature interaction, where the model struggles to discern key visual information from background noise due to…

计算机视觉与模式识别 · 计算机科学 2026-01-23 Zequn Xie , Xin Liu , Boyun Zhang , Yuxiao Lin , Sihang Cai , Tao Jin

Interpretation and understanding of video presents a challenging computer vision task in numerous fields - e.g. autonomous driving and sports analytics. Existing approaches to interpreting the actions taking place within a video clip are…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Salman Khan , Izzeddin Teeti , Andrew Bradley , Mohamed Elhoseiny , Fabio Cuzzolin

The rapid growth of online video resources has significantly promoted the development of video retrieval methods. As a standard evaluation metric for video retrieval, Average Precision (AP) assesses the overall rankings of relevant videos…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Yang Liu , Qianqian Xu , Peisong Wen , Siran Dai , Qingming Huang

Long-form video understanding presents significant challenges for interactive retrieval systems, as conventional methods struggle to process extensive video content efficiently. Existing approaches often rely on single models, inefficient…

Open-vocabulary video visual relationship detection aims to expand video visual relationship detection beyond annotated categories by detecting unseen relationships between both seen and unseen objects in videos. Existing methods usually…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Yongqi Wang , Xinxiao Wu , Shuo Yang , Jiebo Luo

Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently. In this work, we propose a novel visual relationship detection…

计算机视觉与模式识别 · 计算机科学 2019-11-05 Hao Zhou , Chongyang Zhang , Chuanping Hu

Seas of videos are uploaded daily with the popularity of social channels; thus, retrieving the most related video contents with user textual queries plays a more crucial role. Most methods consider only one joint embedding space between…

计算机视觉与模式识别 · 计算机科学 2022-06-28 Burak Satar , Hongyuan Zhu , Hanwang Zhang , Joo Hwee Lim

CLIP aligns image and text embeddings via contrastive learning and demonstrates strong zero-shot generalization. Its large-scale architecture requires substantial computational and memory resources, motivating the distillation of its…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Jeannie Chung , Hanna Jang , Ingyeong Yang , Uiwon Hwang , Jaehyeong Sim

Query-based video situation detection (as opposed to manual or customized algorithms) is critical for diverse applications such as traffic monitoring, surveillance1 , and other types of environmental/infrastructure monitoring. Video…

数据库 · 计算机科学 2022-11-29 Hafsa Billah , Mayur Arora , Sharma Chakravarthy

Micro-videos platforms such as TikTok are extremely popular nowadays. One important feature is that users no longer select interested videos from a set, instead they either watch the recommended video or skip to the next one. As a result,…

信息检索 · 计算机科学 2023-09-01 Yuhan Quan , Jingtao Ding , Chen Gao , Nian Li , Lingling Yi , Depeng Jin , Yong Li

Video Anomaly Detection (VAD) aims to localize abnormal events on the timeline of long-range surveillance videos. Anomaly-scoring-based methods have been prevailing for years but suffer from the high complexity of thresholding and low…

计算机视觉与模式识别 · 计算机科学 2024-01-12 Hui Lv , Qianru Sun

How do humans recognize the action "opening a book" ? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent…

计算机视觉与模式识别 · 计算机科学 2018-12-27 Xiaolong Wang , Abhinav Gupta

After a decade of prosperity, the development of video understanding has reached a critical juncture, where the sole reliance on massive data and complex architectures is no longer a one-size-fits-all solution to all situations. The…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Li Yicong

Referring video object segmentation (RVOS) aims to segment video objects with the guidance of natural language reference. Previous methods typically tackle RVOS through directly grounding linguistic reference over the image lattice. Such…

计算机视觉与模式识别 · 计算机科学 2024-01-22 Chen Liang , Yu Wu , Tianfei Zhou , Wenguan Wang , Zongxin Yang , Yunchao Wei , Yi Yang

Text-video retrieval is a challenging task that aims to identify relevant videos given textual queries. Compared to conventional textual retrieval, the main obstacle for text-video retrieval is the semantic gap between the textual nature of…

计算机视觉与模式识别 · 计算机科学 2024-01-09 Qian Li , Lixin Su , Jiashu Zhao , Long Xia , Hengyi Cai , Suqi Cheng , Hengzhu Tang , Junfeng Wang , Dawei Yin

We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct appearance alignment via frame-level feature matching to…

计算机视觉与模式识别 · 计算机科学 2022-07-25 Khoi D. Nguyen , Quoc-Huy Tran , Khoi Nguyen , Binh-Son Hua , Rang Nguyen

Video-Text Pre-training (VTP) aims to learn transferable representations for various downstream tasks from large-scale web videos. To date, almost all existing VTP methods are limited to retrieval-based downstream tasks, e.g., video…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Meng Cao , Tianyu Yang , Junwu Weng , Can Zhang , Jue Wang , Yuexian Zou

Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…

计算机视觉与模式识别 · 计算机科学 2020-08-06 Jinpeng Wang , Yiqi Lin , Andy J. Ma , Pong C. Yuen