中文
相关论文

相关论文: Building Scalable Video Understanding Benchmarks t…

200 篇论文

Long video understanding is heavily bottlenecked by a rigid one-shot paradigm: existing methods either densely encode videos at prohibitive memory and latency costs, or aggressively compress them into sparse frame sets that irreversibly…

计算机视觉与模式识别 · 计算机科学 2026-05-14 Xiao Yang , Yingzhe Ma , Haoxuan Yu , Zixin Li , Ning Qin

Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Hyungyu Choi , Young Kyun Jang , Chanho Eom

Recent progress in multimodal large language models has markedly enhanced the understanding of short videos (typically under one minute), and several evaluation datasets have emerged accordingly. However, these advancements fall short of…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Weihan Wang , Zehai He , Wenyi Hong , Yean Cheng , Xiaohan Zhang , Ji Qi , Xiaotao Gu , Shiyu Huang , Bin Xu , Yuxiao Dong , Ming Ding , Jie Tang

Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving…

计算机视觉与模式识别 · 计算机科学 2025-04-18 Lan Wang , Yujia Chen , Du Tran , Vishnu Naresh Boddeti , Wen-Sheng Chu

Ad-hoc Video Search (AVS) enables users to search for unlabeled video content using on-the-fly textual queries. Current deep learning-based models for AVS are trained to optimize holistic similarity between short videos and their associated…

多媒体 · 计算机科学 2024-01-17 Aozhu Chen , Fangming Zhou , Ziyuan Wang , Xirong Li

Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However, existing benchmarks suffer from limited video duration, low-quality captions, and coarse…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Qifeng Cai , Hao Liang , Zhaoyang Han , Hejun Dong , Meiyi Qiang , Ruichuan An , Quanqing Xu , Bin Cui , Wentao Zhang

Video summarization aims to produce a compact representation of a long video by selecting a subset of temporally important segments that best reflect human preferences. This task is inherently difficult due to strong annotation subjectivity…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Omer Tariq , Syed Muhammad Raza , Jeongbae Son

This paper presents a new large-scale dataset for recognition and temporal localization of human actions collected from Web videos. We refer to it as HACS (Human Action Clips and Segments). We leverage both consensus and disagreement among…

计算机视觉与模式识别 · 计算机科学 2019-09-05 Hang Zhao , Antonio Torralba , Lorenzo Torresani , Zhicheng Yan

Increasing the annotation efficiency of trajectory annotations from videos has the potential to enable the next generation of data-hungry tracking algorithms to thrive on large-scale datasets. Despite the importance of this task, there are…

计算机视觉与模式识别 · 计算机科学 2024-12-16 Orcun Cetintas , Tim Meinhardt , Guillem Brasó , Laura Leal-Taixé

Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception through irreversible information disposal or inhibit long-range…

计算机视觉与模式识别 · 计算机科学 2026-05-11 Handong Li , Zikang Liu , Longteng Guo , Tongtian Yue , Yepeng Tang , Xinxin Zhu , Chuanyang Zheng , Ziming Wang , Zhibin Wang , Jun Song , Cheng Yu , Bo Zheng , Jing Liu

While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long,…

计算机视觉与模式识别 · 计算机科学 2019-09-02 Bruno Korbar , Du Tran , Lorenzo Torresani

The canonical approach to video action recognition dictates a neural model to do a classic and standard 1-of-N majority vote task. They are trained to predict a fixed set of predefined categories, limiting their transferable ability on new…

计算机视觉与模式识别 · 计算机科学 2021-09-20 Mengmeng Wang , Jiazheng Xing , Yong Liu

Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast…

计算机视觉与模式识别 · 计算机科学 2024-09-10 Nina Shvetsova , Anna Kukleva , Xudong Hong , Christian Rupprecht , Bernt Schiele , Hilde Kuehne

Audio-Visual Video Parsing is a task to predict the events that occur in video segments for each modality. It often performs in a weakly supervised manner, where only video event labels are provided, i.e., the modalities and the timestamps…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Jinxing Zhou , Dan Guo , Yiran Zhong , Meng Wang

The development of video game streaming has grown rapidly, with major platforms such as YouTube and Twitch using different codecs. To support quality assessment models that work consistently across any codec, it is necessary to have access…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Rajesh Sureddi , Shreshth Saini , Avinab Saha , Alan C. Bovik

Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. This issue is…

计算与语言 · 计算机科学 2024-10-07 Jiapeng Wang , Chengyu Wang , Kunzhe Huang , Jun Huang , Lianwen Jin

The inherent complexity of video understanding makes it difficult to attribute whether performance gains stem from visual perception, linguistic reasoning, or knowledge priors. While many benchmarks have emerged to assess high-level…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Geuntaek Lim , Minho Shim , Sungjune Park , Jaeyun Lee , Inwoong Lee , Taeoh Kim , Dongyoon Wee , Yukyung Choi

Advertisers commonly need multiple versions of the same advertisement (ad) at varying durations for a single campaign. The traditional approach involves manually selecting and re-editing shots from longer video ads to create shorter…

计算机视觉与模式识别 · 计算机科学 2025-12-18 Wen Xie , Yanjun Zhu , Gijs Overgoor , Yakov Bart , Agata Lapedriza Garcia , Sarah Ostadabbas

Athlete performance measurement in sports videos requires modeling long sequences since the entire spatio-temporal progression contributes dominantly to the performance. It is crucial to comprehend local discriminative spatial dependencies…

计算机视觉与模式识别 · 计算机科学 2023-01-18 Sania Zahan , Ghulam Mubashar Hassan , Ajmal Mian

Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora, like HowTo100M, offer rich resources for model training, they present significant…

计算机视觉与模式识别 · 计算机科学 2026-04-30 Mingji Ge , Qirui Chen , Zeqian Li , Weidi Xie