中文
相关论文

相关论文: The Blessings of Unlabeled Background in Untrimmed…

200 篇论文

Point-level supervised temporal action localization (PTAL) aims at recognizing and localizing actions in untrimmed videos where only a single point (frame) within every action instance is annotated in training data. Without temporal…

计算机视觉与模式识别 · 计算机科学 2023-10-10 Yuan Yin , Yifei Huang , Ryosuke Furuta , Yoichi Sato

Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest.…

计算机视觉与模式识别 · 计算机科学 2019-11-25 Pilhyeon Lee , Youngjung Uh , Hyeran Byun

Weakly supervised temporal action localization (WS-TAL) is a task of targeting at localizing complete action instances and categorizing them with video-level labels. Action-background ambiguity, primarily caused by background noise…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Yuanpeng He , Lijian Li , Tianxiang Zhan , Wenpin Jiao , Chi-Man Pun

Weakly Supervised Object Localization (WSOL) aims to localize objects with image-level supervision. Existing works mainly rely on Class Activation Mapping (CAM) derived from a classification model. However, CAM-based methods usually focus…

计算机视觉与模式识别 · 计算机科学 2022-05-30 Jilan Xu , Junlin Hou , Yuejie Zhang , Rui Feng , Rui-Wei Zhao , Tao Zhang , Xuequan Lu , Shang Gao

Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse…

计算机视觉与模式识别 · 计算机科学 2020-12-16 Chen Ju , Peisen Zhao , Ya Zhang , Yanfeng Wang , Qi Tian

Online Temporal Action Localization (On-TAL) aims to detect the occurrence time and category of actions in untrimmed streaming videos immediately upon their completion. Recent advancements in this field focus on developing more…

计算机视觉与模式识别 · 计算机科学 2026-05-12 Chaolei Han , Hongsong Wang , Xin Gong , Jie Gui

We describe a latent approach that learns to detect actions in long sequences given training videos with only whole-video class labels. Our approach makes use of two innovations to attention-modeling in weakly-supervised learning. First,…

计算机视觉与模式识别 · 计算机科学 2019-08-20 Phuc Xuan Nguyen , Deva Ramanan , Charless C. Fowlkes

Zero-Shot Temporal Action Localization (ZS-TAL) seeks to identify and locate actions in untrimmed videos unseen during training. Existing ZS-TAL methods involve fine-tuning a model on a large amount of annotated training data. While…

计算机视觉与模式识别 · 计算机科学 2024-04-12 Benedetta Liberatori , Alessandro Conti , Paolo Rota , Yiming Wang , Elisa Ricci

Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Both appearance and motion features are used in previous…

计算机视觉与模式识别 · 计算机科学 2021-07-28 Fa-Ting Hong , Jia-Chang Feng , Dan Xu , Ying Shan , Wei-Shi Zheng

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…

计算机视觉与模式识别 · 计算机科学 2023-09-27 Guiqin Wang , Peng Zhao , Cong Zhao , Shusen Yang , Jie Cheng , Luziwei Leng , Jianxing Liao , Qinghai Guo

Self-supervised vision transformers can generate accurate localization maps of the objects in an image. However, since they decompose the scene into multiple maps containing various objects, and they do not rely on any explicit supervisory…

计算机视觉与模式识别 · 计算机科学 2022-09-20 Shakeeb Murtaza , Soufiane Belharbi , Marco Pedersoli , Aydin Sarraf , Eric Granger

Point-supervised Temporal Action Localization (PTAL) adopts a lightly frame-annotated paradigm (\textit{i.e.}, labeling only a single frame per action instance) to train a model to effectively locate action instances within untrimmed…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Yunchuan Ma , Laiyun Qing , Guorong Li , Yuqing Liu , Yuankai Qi , Qingming Huang

Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation…

计算机视觉与模式识别 · 计算机科学 2021-02-19 Baifeng Shi , Qi Dai , Judy Hoffman , Kate Saenko , Trevor Darrell , Huijuan Xu

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…

计算机视觉与模式识别 · 计算机科学 2022-03-11 Wentao Bao , Qi Yu , Yu Kong

Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Yupeng Hu , Han Jiang , Hao Liu , Kun Wang , Haoyu Tang , Liqiang Nie

Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data. Under the supervision of category labels,…

计算机视觉与模式识别 · 计算机科学 2018-07-19 Jia-Xing Zhong , Nannan Li , Weijie Kong , Tao Zhang , Thomas H. Li , Ge Li

We present a meta-learning framework for weakly supervised anomaly detection in videos, where the detector learns to adapt to unseen types of abnormal activities effectively when only video-level annotations of binary labels are available.…

计算机视觉与模式识别 · 计算机科学 2022-03-28 Jaeyoo Park , Junha Kim , Bohyung Han

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…

计算机视觉与模式识别 · 计算机科学 2021-09-24 Ting-Ting Xie , Christos Tzelepis , Fan Fu , Ioannis Patras

Temporal action localization (TAL) is a task of identifying a set of actions in a video, which involves localizing the start and end frames and classifying each action instance. Existing methods have addressed this task by using predefined…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Tae-Kyung Kang , Gun-Hee Lee , Seong-Whan 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…

计算机视觉与模式识别 · 计算机科学 2021-03-30 Ankit Singh , Omprakash Chakraborty , Ashutosh Varshney , Rameswar Panda , Rogerio Feris , Kate Saenko , Abir Das