中文
相关论文

相关论文: FineVAU: A Novel Human-Aligned Benchmark for Fine-…

200 篇论文

Video anomaly understanding (VAU) aims to automatically comprehend unusual occurrences in videos, thereby enabling various applications such as traffic surveillance and industrial manufacturing. While existing VAU benchmarks primarily…

Video Anomaly Understanding (VAU) is essential for applications such as smart cities, security surveillance, and disaster alert systems, yet remains challenging due to its demand for fine-grained spatio-temporal perception and robust…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Liyun Zhu , Qixiang Chen , Xi Shen , Xiaodong Cun

Recent advancements in video anomaly understanding (VAU) have opened the door to groundbreaking applications in various fields, such as traffic monitoring and industrial automation. While the current benchmarks in VAU predominantly…

计算机视觉与模式识别 · 计算机科学 2024-12-11 Hang Du , Guoshun Nan , Jiawen Qian , Wangchenhui Wu , Wendi Deng , Hanqing Mu , Zhenyan Chen , Pengxuan Mao , Xiaofeng Tao , Jun Liu

Subtle abnormal events in videos often manifest as weak spatio-temporal cues that are easily overlooked by conventional anomaly detection systems. Existing video anomaly detection approaches typically provide coarse binary anomaly decisions…

计算机视觉与模式识别 · 计算机科学 2026-04-01 Jihao Gu , Kun Li , He Wang , Kaan Akşit

Video Anomaly Understanding (VAU) extends traditional Video Anomaly Detection (VAD) by not only localizing anomalies but also describing and reasoning about their context. Existing VAU approaches often rely on fine-tuned multimodal large…

计算机视觉与模式识别 · 计算机科学 2026-01-09 Iñaki Erregue , Kamal Nasrollahi , Sergio Escalera

Video anomaly understanding (VAU) aims to provide detailed interpretation and semantic comprehension of anomalous events within videos, addressing limitations of traditional methods that focus solely on detecting and localizing anomalies.…

计算机视觉与模式识别 · 计算机科学 2025-12-15 Ying Cheng , Yu-Ho Lin , Min-Hung Chen , Fu-En Yang , Shang-Hong Lai

How can we enable models to comprehend video anomalies occurring over varying temporal scales and contexts? Traditional Video Anomaly Understanding (VAU) methods focus on frame-level anomaly prediction, often missing the interpretability of…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Huaxin Zhang , Xiaohao Xu , Xiang Wang , Jialong Zuo , Xiaonan Huang , Changxin Gao , Shanjun Zhang , Li Yu , Nong Sang

How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or comprehending anomalous events with interpretable…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Yating Yu , Congqi Cao , Zhaoying Wang , Weihua Meng , Jie Li , Yuxin Li , Zihao Wei , Zhongpei Shen , Jiajun Zhang

Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies% at the frame level, which can be roughly interpreted as the binary or…

计算机视觉与模式识别 · 计算机科学 2024-02-29 Peng Wu , Jing Liu , Xiangteng He , Yuxin Peng , Peng Wang , Yanning Zhang

Video Anomaly Detection (VAD) aims to identify anomalous events in videos and accurately determine their time intervals. Current VAD methods mainly fall into two categories: traditional DNN-based approaches that focus on temporal…

计算机视觉与模式识别 · 计算机科学 2025-07-30 Shibo Gao , Peipei Yang , Yangyang Liu , Yi Chen , Han Zhu , Xuyao Zhang , Linlin Huang

The recent developments in Large Multi-modal Video Models (Video-LMMs) have significantly enhanced our ability to interpret and analyze video data. Despite their impressive capabilities, current Video-LMMs have not been evaluated for…

计算机视觉与模式识别 · 计算机科学 2025-03-26 Rohit Bharadwaj , Hanan Gani , Muzammal Naseer , Fahad Shahbaz Khan , Salman Khan

Automatically detecting abnormal events in videos is crucial for modern autonomous systems, yet existing Video Anomaly Detection (VAD) benchmarks lack the scene diversity, balanced anomaly coverage, and temporal complexity needed to…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Jie Li , Hongyi Cai , Mingkang Dong , Muxin Pu , Shan You , Fei Wang , Tao Huang

The evaluation of Long Video Understanding (LVU) performance poses an important but challenging research problem. Despite previous efforts, the existing video understanding benchmarks are severely constrained by several issues, especially…

计算机视觉与模式识别 · 计算机科学 2025-01-03 Junjie Zhou , Yan Shu , Bo Zhao , Boya Wu , Zhengyang Liang , Shitao Xiao , Minghao Qin , Xi Yang , Yongping Xiong , Bo Zhang , Tiejun Huang , Zheng Liu

Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of…

计算机视觉与模式识别 · 计算机科学 2026-05-26 Gueter Josmy Faure , Min-Hung Chen , Jia-Fong Yeh , Hung-Ting Su , Winston H. Hsu

Vision-Language Models (VLMs) have achieved strong results in video understanding, yet a key question remains: do they truly comprehend visual content or only learn shallow correlations between vision and language? Real visual…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Zongxia Li , Xiyang Wu , Guangyao Shi , Yubin Qin , Hongyang Du , Fuxiao Liu , Tianyi Zhou , Dinesh Manocha , Jordan Lee Boyd-Graber

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

Despite rapid progress in large vision-language models (LVLMs), existing video caption benchmarks remain limited in evaluating their alignment with human understanding. Most rely on a single annotation per video and lexical similarity-based…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Shiyu Hu , Xuchen Li , Xuzhao Li , Jing Zhang , Yipei Wang , Xin Zhao , Kang Hao Cheong

Multi-modal large language models (MLLMs) have demonstrated significant progress in reasoning capabilities and shown promising effectiveness in video anomaly understanding (VAU) tasks. However, existing MLLM-based approaches remain largely…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Zihao Zhao , Shengting Cao , Muchao Ye

Human action recognition in long-term videos, characterized by complex backgrounds and subtle action differences, poses significant challenges for traditional deep learning models due to computational overhead, difficulty in capturing…

计算机视觉与模式识别 · 计算机科学 2025-08-25 Kaining Li , Shuwei He , Zihan Xu

Recent progress in reasoning capabilities of Multimodal Large Language Models(MLLMs) has highlighted their potential for performing complex video understanding tasks. However, in the domain of Video Anomaly Detection and Understanding…

计算机视觉与模式识别 · 计算机科学 2026-01-16 Chao Huang , Benfeng Wang , Wei Wang , Jie Wen , Li Shen , Wenqi Ren , Yong Xu , Xiaochun Cao
‹ 上一页 1 2 3 10 下一页 ›