English
Related papers

Related papers: Low-Fidelity End-to-End Video Encoder Pre-training…

200 papers

Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Rui Xia , Dan Jiang , Quan Zhang , Ke Zhang , Chun Yuan

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

Current vision language pretraining models are dominated by methods using region visual features extracted from object detectors. Given their good performance, the extract-then-process pipeline significantly restricts the inference speed…

Computer Vision and Pattern Recognition · Computer Science 2023-01-19 Xiaofeng Yang , Fayao Liu , Guosheng Lin

Weakly Supervised Temporal Action Localization (WTAL) aims to classify and localize temporal boundaries of actions for the video, given only video-level category labels in the training datasets. Due to the lack of boundary information…

Computer Vision and Pattern Recognition · Computer Science 2023-04-26 Guozhang Li , De Cheng , Xinpeng Ding , Nannan Wang , Jie Li , Xinbo Gao

Weakly Supervised Temporal Action Localization (WSTAL) aims to localize and classify action instances in long untrimmed videos with only video-level category labels. Due to the lack of snippet-level supervision for indicating action…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Jia-Run Du , Jia-Chang Feng , Kun-Yu Lin , Fa-Ting Hong , Xiao-Ming Wu , Zhongang Qi , Ying Shan , Wei-Shi Zheng

Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often result in imprecise predictions of action boundaries by…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Dingfeng Shi , Qiong Cao , Yujie Zhong , Shan An , Jian Cheng , Haogang Zhu , Dacheng Tao

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Minghao Chen , Renbo Tu , Chenxi Huang , Yuqi Lin , Boxi Wu , Deng Cai

Weakly-supervised Temporal Action Localization (WTAL) has achieved notable success but still suffers from a lack of temporal annotations, leading to a performance and framework gap compared with fully-supervised methods. While recent…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Ziyi Liu , Yangcen Liu

Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…

Computer Vision and Pattern Recognition · Computer Science 2018-08-02 Wei-Sheng Lai , Jia-Bin Huang , Oliver Wang , Eli Shechtman , Ersin Yumer , Ming-Hsuan Yang

Temporal action localization (TAL) aims to detect the boundary and identify the class of each action instance in a long untrimmed video. Current approaches treat video frames homogeneously, and tend to give background and key objects…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Yifan Liu , Youbao Tang , Ning Zhang , Ruei-Sung Lin , Haoqian Wang

Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems…

Machine Learning · Computer Science 2025-03-26 Uri Gadot , Assaf Shocher , Shie Mannor , Gal Chechik , Assaf Hallak

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.,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Junfei Xiao , Longlong Jing , Lin Zhang , Ju He , Qi She , Zongwei Zhou , Alan Yuille , Yingwei Li

Weakly-supervised temporal action localization aims to recognize and localize action segments in untrimmed videos given only video-level action labels for training. Without the boundary information of action segments, existing methods…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Bo He , Xitong Yang , Le Kang , Zhiyu Cheng , Xin Zhou , Abhinav Shrivastava

Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in…

Computer Vision and Pattern Recognition · Computer Science 2022-03-11 Wentao Bao , Qi Yu , Yu Kong

The vocabulary size in temporal action localization (TAL) is limited by the scarcity of large-scale annotated datasets. To overcome this, recent works integrate vision-language models (VLMs), such as CLIP, for open-vocabulary TAL (OV-TAL).…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Jeongseok Hyun , Su Ho Han , Hyolim Kang , Joon-Young Lee , Seon Joo Kim

Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Alejandro Pardo , Humam Alwassel , Fabian Caba Heilbron , Ali Thabet , Bernard Ghanem

The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning…

Computer Vision and Pattern Recognition · Computer Science 2018-11-26 Pascal Mettes , Cees G. M. Snoek

Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Svetlana Orlova , Niccolò Cavagnero , Gijs Dubbelman

Temporal human action detection aims to identify and localize action segments within untrimmed videos, serving as a pivotal task in video understanding. Despite the progress achieved by prior architectures like CNN and Transformer models,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-13 Yicheng Qiu , Keiji Yanai

Temporal Action Localization (TAL) aims to detect the start and end timestamps of actions in a video. However, the training of TAL models requires a substantial amount of manually annotated data. Data programming is an efficient method to…

Human-Computer Interaction · Computer Science 2025-05-26 Yuchen He , Jianbing Lv , Liqi Cheng , Lingyu Meng , Dazhen Deng , Yingcai Wu