中文
相关论文

相关论文: Reversed in Time: A Novel Temporal-Emphasized Benc…

200 篇论文

Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while…

计算机视觉与模式识别 · 计算机科学 2025-12-09 Muhammad Maaz , Hanoona Rasheed , Fahad Shahbaz Khan , Salman Khan

Modern video-text retrieval (VTR) models excel on in-distribution benchmarks but are highly vulnerable to real-world query shifts, where the distribution of query data deviates from the training domain, leading to a sharp performance drop.…

信息检索 · 计算机科学 2026-04-24 Bingqing Zhang , Zhuo Cao , Heming Du , Yang Li , Xue Li , Jiajun Liu , Sen Wang

Modelling and understanding time remains a challenge in contemporary video understanding models. With language emerging as a key driver towards powerful generalization, it is imperative for foundational video-language models to have a sense…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Piyush Bagad , Makarand Tapaswi , Cees G. M. Snoek

We introduce TV show Retrieval (TVR), a new multimodal retrieval dataset. TVR requires systems to understand both videos and their associated subtitle (dialogue) texts, making it more realistic. The dataset contains 109K queries collected…

计算机视觉与模式识别 · 计算机科学 2020-08-19 Jie Lei , Licheng Yu , Tamara L. Berg , Mohit Bansal

Most existing text-video retrieval methods focus on cross-modal matching between the visual content of videos and textual query sentences. However, in real-world scenarios, online videos are often accompanied by relevant text information…

计算机视觉与模式识别 · 计算机科学 2023-03-29 Wenhao Wu , Haipeng Luo , Bo Fang , Jingdong Wang , Wanli Ouyang

Semantic retrieval of remote sensing (RS) images is a critical task fundamentally challenged by the \textquote{semantic gap}, the discrepancy between a model's low-level visual features and high-level human concepts. While large…

计算机视觉与模式识别 · 计算机科学 2025-12-12 J. Xiao , Y. Guo , X. Zi , K. Thiyagarajan , C. Moreira , M. Prasad

Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalization ability for various image tasks. However, how to…

计算机视觉与模式识别 · 计算机科学 2022-08-05 Bolin Ni , Houwen Peng , Minghao Chen , Songyang Zhang , Gaofeng Meng , Jianlong Fu , Shiming Xiang , Haibin Ling

Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Existing works attempt to progressively narrow the search…

计算机视觉与模式识别 · 计算机科学 2025-11-10 Junwen Pan , Qizhe Zhang , Rui Zhang , Ming Lu , Xin Wan , Yuan Zhang , Chang Liu , Qi She

Cross-modal video-text retrieval, a challenging task in the field of vision and language, aims at retrieving corresponding instance giving sample from either modality. Existing approaches for this task all focus on how to design encoding…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Rui Zhao , Kecheng Zheng , Zheng-Jun Zha , Hongtao Xie , Jiebo Luo

Efficiently understanding long-form videos remains a significant challenge in computer vision. In this work, we revisit temporal search paradigms for long-form video understanding and address a fundamental issue pertaining to all…

Retrieving events from videos using text queries has become increasingly challenging due to the rapid growth of multimedia content. Existing methods for text-based video event retrieval often focus heavily on object-level descriptions,…

计算与语言 · 计算机科学 2025-01-29 Long Nguyen , Huy Nguyen , Bao Khuu , Huy Luu , Huy Le , Tuan Nguyen , Tho Quan

The goal of text-to-video retrieval is to search large databases for relevant videos based on text queries. Existing methods have progressed to handling explicit queries where the visual content of interest is described explicitly; however,…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Yiqing Shen , Chenxiao Fan , Chenjia Li , Mathias Unberath

Research in the Vision and Language area encompasses challenging topics that seek to connect visual and textual information. When the visual information is related to videos, this takes us into Video-Text Research, which includes several…

计算机视觉与模式识别 · 计算机科学 2021-12-02 Jesus Perez-Martin , Benjamin Bustos , Silvio Jamil F. Guimarães , Ivan Sipiran , Jorge Pérez , Grethel Coello Said

Existing text-to-video retrieval benchmarks are dominated by real-world footage where much of the semantics can be inferred from a single frame, leaving temporal reasoning and explicit end-state grounding under-evaluated. We introduce…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Minghan Li , Tongna Chen , Tianrui Lv , Yishuai Zhang , Suchao An , Guodong Zhou

Video-text retrieval has witnessed remarkable progress driven by large-scale vision-language pretraining, yet most existing approaches inherit an implicit assumption from image-text retrieval: that visual semantics can be captured…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Zixu Li , Yupeng Hu , Zhiwei Chen , Zhiheng Fu , Xiaowei Zhu , Weili Guan , Liqiang Nie

Recent advancements in machine learning have fueled research on multimodal tasks, such as for instance text-to-video and text-to-audio retrieval. These tasks require models to understand the semantic content of video and audio data,…

信息检索 · 计算机科学 2024-09-04 Andreea-Maria Oncescu , João F. Henriques , A. Sophia Koepke

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a…

计算机视觉与模式识别 · 计算机科学 2024-04-12 Minkuk Kim , Hyeon Bae Kim , Jinyoung Moon , Jinwoo Choi , Seong Tae Kim

We address the problem of text-guided video temporal grounding, which aims to identify the time interval of a certain event based on a natural language description. Different from most existing methods that only consider RGB images as…

计算机视觉与模式识别 · 计算机科学 2021-11-01 Yi-Wen Chen , Yi-Hsuan Tsai , Ming-Hsuan Yang

The development of image time series retrieval (ITSR) methods is a growing research interest in remote sensing (RS). Given a user-defined image time series (i.e., the query time series), ITSR methods search and retrieve from large archives…

计算机视觉与模式识别 · 计算机科学 2025-07-16 Genc Hoxha , Olivér Angyal , Begüm Demir

A major challenge in text-video and text-audio retrieval is the lack of large-scale training data. This is unlike image-captioning, where datasets are in the order of millions of samples. To close this gap we propose a new video mining…

计算机视觉与模式识别 · 计算机科学 2022-04-05 Arsha Nagrani , Paul Hongsuck Seo , Bryan Seybold , Anja Hauth , Santiago Manen , Chen Sun , Cordelia Schmid