中文
相关论文

相关论文: FineGym: A Hierarchical Video Dataset for Fine-gra…

200 篇论文

Sports video analysis is a widespread research topic. Its applications are very diverse, like events detection during a match, video summary, or fine-grained movement analysis of athletes. As part of the MediaEval 2022 benchmarking…

The key to action counting is accurately locating each video's repetitive actions. Instead of estimating the probability of each frame belonging to an action directly, we propose a dual-branch network, i.e., SkimFocusNet, working in a…

计算机视觉与模式识别 · 计算机科学 2024-06-14 Zhengqi Zhao , Xiaohu Huang , Hao Zhou , Kun Yao , Errui Ding , Jingdong Wang , Xinggang Wang , Wenyu Liu , Bin Feng

Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…

计算机视觉与模式识别 · 计算机科学 2022-04-26 Junfei Xiao , Longlong Jing , Lin Zhang , Ju He , Qi She , Zongwei Zhou , Alan Yuille , Yingwei Li

Human action recognition is a challenging problem, particularly when there is high variability in factors such as subject appearance, backgrounds and viewpoint. While deep neural networks (DNNs) have been shown to perform well on action…

计算机视觉与模式识别 · 计算机科学 2024-08-05 Arun V. Reddy , Ketul Shah , William Paul , Rohita Mocharla , Judy Hoffman , Kapil D. Katyal , Dinesh Manocha , Celso M. de Melo , Rama Chellappa

Sports video analysis is a prevalent research topic due to the variety of application areas, ranging from multimedia intelligent devices with user-tailored digests up to analysis of athletes' performance. The Sports Video task is part of…

计算机视觉与模式识别 · 计算机科学 2021-12-22 Pierre-Etienne Martin , Jordan Calandre , Boris Mansencal , Jenny Benois-Pineau , Renaud Péteri , Laurent Mascarilla , Julien Morlier

Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image…

计算机视觉与模式识别 · 计算机科学 2016-08-26 César Roberto de Souza , Adrien Gaidon , Eleonora Vig , Antonio Manuel López

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

计算机视觉与模式识别 · 计算机科学 2020-02-11 Wenhao Wu , Dongliang He , Xiao Tan , Shifeng Chen , Yi Yang , Shilei Wen

We have witnessed impressive advances in video action understanding. Increased dataset sizes, variability, and computation availability have enabled leaps in performance and task diversification. Current systems can provide coarse- and…

计算机视觉与模式识别 · 计算机科学 2025-05-07 Alexandros Stergiou , Ronald Poppe

The growing trend of sharing short videos on social media platforms, where users capture and share moments from their daily lives, has led to an increase in research efforts focused on micro-video recommendations. However, conventional…

信息检索 · 计算机科学 2025-04-07 Sanghyuck Lee , Sangkeun Park , Jaesung Lee

With the motivation of practical gait recognition applications, we propose to automatically create a large-scale synthetic gait dataset (called VersatileGait) by a game engine, which consists of around one million silhouette sequences of…

计算机视觉与模式识别 · 计算机科学 2021-01-06 Huanzhang Dou , Wenhu Zhang , Pengyi Zhang , Yuhan Zhao , Songyuan Li , Zequn Qin , Fei Wu , Lin Dong , Xi Li

Recognizing and categorizing human actions is an important task with applications in various fields such as human-robot interaction, video analysis, surveillance, video retrieval, health care system and entertainment industry. This thesis…

计算机视觉与模式识别 · 计算机科学 2021-05-03 Zahra Gharaee

We introduce a hierarchical architecture for video understanding that exploits the structure of real world actions by capturing targets at different levels of granularity. We design the model such that it first learns simpler coarse-grained…

计算机视觉与模式识别 · 计算机科学 2018-09-11 Farzaneh Mahdisoltani , Roland Memisevic , David Fleet

We propose a novel method for 3D point cloud action recognition. Understanding human actions in RGB videos has been widely studied in recent years, however, its 3D point cloud counterpart remains under-explored. This is mostly due to the…

计算机视觉与模式识别 · 计算机科学 2024-04-01 Yizhak Ben-Shabat , Oren Shrout , Stephen Gould

Our world is full of varied actions and moves across specialized domains that we, as humans, strive to identify and understand. Within any single domain, actions can often appear quite similar, making it challenging for deep models to…

计算机视觉与模式识别 · 计算机科学 2024-11-12 Mohammadreza Salehi , Jae Sung Park , Tanush Yadav , Aditya Kusupati , Ranjay Krishna , Yejin Choi , Hannaneh Hajishirzi , Ali Farhadi

We introduce Action Discovery, a novel setup within Temporal Action Segmentation that addresses the challenge of defining and annotating ambiguous actions and incomplete annotations in partially labeled datasets. In this setup, only a…

计算机视觉与模式识别 · 计算机科学 2025-08-08 Federico Spurio , Emad Bahrami , Olga Zatsarynna , Yazan Abu Farha , Gianpiero Francesca , Juergen Gall

Foggy conditions are commonly encountered in real-world applications; however, existing action recognition approaches typically assume favorable weather and high-quality video inputs. On foggy days, unpredictable visibility degradation and…

计算机视觉与模式识别 · 计算机科学 2026-05-21 Enqi Liu , Liyuan Pan , Zhi Gao , Lingzhi Li , Qing Li

Analyzing Fast, Frequent, and Fine-grained (F$^3$) events presents a significant challenge in video analytics and multi-modal LLMs. Current methods struggle to identify events that satisfy all the F$^3$ criteria with high accuracy due to…

计算机视觉与模式识别 · 计算机科学 2025-04-16 Zhaoyu Liu , Kan Jiang , Murong Ma , Zhe Hou , Yun Lin , Jin Song Dong

Daily activity recognition has gained prominence due to its applications in context-aware computing. Current methods primarily rely on supervised learning for detecting simple, repetitive activities. This paper introduces LayeredSense, a…

人机交互 · 计算机科学 2025-02-14 Chak Man Lam

Despite substantial progress in video understanding, most existing datasets are limited to Earth's gravitational conditions. However, microgravity alters human motion, interactions, and visual semantics, revealing a critical gap for…

计算机视觉与模式识别 · 计算机科学 2026-03-24 Di Wen , Lei Qi , Kunyu Peng , Kailun Yang , Fei Teng , Ao Luo , Jia Fu , Yufan Chen , Ruiping Liu , Yitian Shi , M. Saquib Sarfraz , Rainer Stiefelhagen

Fine-grained action recognition is a challenging task in computer vision. As fine-grained datasets have small inter-class variations in spatial and temporal space, fine-grained action recognition model requires good temporal reasoning and…

计算机视觉与模式识别 · 计算机科学 2022-08-04 Mei Chee Leong , Haosong Zhang , Hui Li Tan , Liyuan Li , Joo Hwee Lim