English
Related papers

Related papers: TALL: Temporal Activity Localization via Language …

200 papers

Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Yongxin Guo , Jingyu Liu , Mingda Li , Qingbin Liu , Xi Chen , Xiaoying Tang

Learning to localize actions in long, cluttered, and untrimmed videos is a hard task, that in the literature has typically been addressed assuming the availability of large amounts of annotated training samples for each class -- either in a…

Computer Vision and Pattern Recognition · Computer Science 2021-09-24 Ting-Ting Xie , Christos Tzelepis , Fan Fu , Ioannis Patras

Temporal Grounding is to identify specific moments or highlights from a video corresponding to textual descriptions. Typical approaches in temporal grounding treat all video clips equally during the encoding process regardless of their…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 WonJun Moon , Sangeek Hyun , SuBeen Lee , Jae-Pil Heo

Temporal action segmentation in untrimmed procedural videos aims to densely label frames into action classes. These videos inherently exhibit long-tailed distributions, where actions vary widely in frequency and duration. In temporal action…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Zhanzhong Pang , Fadime Sener , Shrinivas Ramasubramanian , Angela Yao

Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretability, and deviating from the human perception mechanism.…

Computer Vision and Pattern Recognition · Computer Science 2020-01-22 Jie Wu , Guanbin Li , Si Liu , Liang Lin

Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties. The task of temporal action segmentation, which aims at translating an…

Computer Vision and Pattern Recognition · Computer Science 2023-12-08 Dayoung Gong , Joonseok Lee , Deunsol Jung , Suha Kwak , Minsu Cho

Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features. While these methods have demonstrated remarkable performance on standard benchmarks, we are…

Computer Vision and Pattern Recognition · Computer Science 2020-05-21 Dian Shao , Yue Zhao , Bo Dai , Dahua Lin

Despite the recent progress in video understanding and the continuous rate of improvement in temporal action localization throughout the years, it is still unclear how far (or close?) we are to solving the problem. To this end, we introduce…

Computer Vision and Pattern Recognition · Computer Science 2018-07-30 Humam Alwassel , Fabian Caba Heilbron , Victor Escorcia , Bernard Ghanem

Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions,…

Computer Vision and Pattern Recognition · Computer Science 2017-05-04 Jiyang Gao , Zhenheng Yang , Ram Nevatia

Temporal language grounding in videos aims to localize the temporal span relevant to the given query sentence. Previous methods treat it either as a boundary regression task or a span extraction task. This paper will formulate temporal…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 Jialin Gao , Xin Sun , Mengmeng Xu , Xi Zhou , Bernard Ghanem

Prior work has primarily formulated CA-HAR as a multi-label classification problem, where model inputs are time-series sensor data and target labels are binary encodings representing whether a given activity or context occurs. These CA-HAR…

Machine Learning · Computer Science 2025-04-11 Wen Ge , Guanyi Mou , Emmanuel O. Agu , Kyumin Lee

Learning to recognize actions from only a handful of labeled videos is a challenging problem due to the scarcity of tediously collected activity labels. We approach this problem by learning a two-pathway temporal contrastive model using…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Ankit Singh , Omprakash Chakraborty , Ashutosh Varshney , Rameswar Panda , Rogerio Feris , Kate Saenko , Abir Das

Generating video descriptions automatically is a challenging task that involves a complex interplay between spatio-temporal visual features and language models. Given that videos consist of spatial (frame-level) features and their temporal…

Computer Vision and Pattern Recognition · Computer Science 2020-01-20 Anoop Cherian , Jue Wang , Chiori Hori , Tim K. Marks

Online Temporal Action Localization (On-TAL) aims to immediately provide action instances from untrimmed streaming videos. The model is not allowed to utilize future frames and any processing techniques to modify past predictions, making…

Computer Vision and Pattern Recognition · Computer Science 2022-11-10 Tuan N. Tang , Jungin Park , Kwonyoung Kim , Kwanghoon Sohn

Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multi-step action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies.…

Robotics · Computer Science 2025-11-07 Yueyang Weng , Xiaopeng Zhang , Yongjin Mu , Yingcong Zhu , Yanjie Li , Qi Liu

Long-term action recognition (LTAR) is challenging due to extended temporal spans with complex atomic action correlations and visual confounders. Although vision-language models (VLMs) have shown promise, they often rely on statistical…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Xu Shaowu , Jia Xibin , Gao Junyu , Sun Qianmei , Chang Jing , Fan Chao

Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are static, working with videos requires modeling their dynamic…

Machine Learning · Statistics 2015-10-02 Li Yao , Atousa Torabi , Kyunghyun Cho , Nicolas Ballas , Christopher Pal , Hugo Larochelle , Aaron Courville

Conventional representation learning methods learn a universal representation that primarily captures dominant semantics, which may not always align with customized downstream tasks. For instance, in animal habitat analysis, researchers…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Honglin Liu , Chao Sun , Peng Hu , Yunfan Li , Xi Peng

Few-shot temporal action localization (TAL) methods that adapt large models via single-prompt tuning often fail to produce precise temporal boundaries. This stems from the model learning a non-discriminative mean representation of an action…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Edward Fish , Andrew Gilbert

Procedural activity videos often exhibit a long-tailed action distribution due to varying action frequencies and durations. However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Zhanzhong Pang , Fadime Sener , Shrinivas Ramasubramanian , Angela Yao
‹ Prev 1 8 9 10 Next ›