paper-with-me

Papers Weakly Supervised Action Localization

“Weakly Supervised Action Localization” 태그가 달린 논문 55편 · 필터 해제

Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization

2024-11-24 · Neural Networks 2024 11 · Zhilin Li, Zilei Wang, Cerui Dong

Weakly supervised temporal action localization aims to identify and localize action instances in untrimmed videos with only video-level labels. Typically, most methods are based on a multiple instance learning framework …

Action ClassificationAction LocalizationMultiple Instance LearningTemporal Action Localization+2

Weakly supervised temporal action localization with actionness-guided false positive suppression

2024-04-15 · Neural Networks 2024 4 · Zhilin Li, Zilei Wang

Weakly supervised temporal action localization aims to locate the temporal boundaries of action instances in untrimmed videos using video-level labels and assign them the corresponding action category. Generally, it is s…

Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action Localization

Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach

2023-12-21 · ICCV 2023 1 · Qinying Liu, Zilei Wang, Shenghai Rong, Junjie Li 외

Weakly-supervised temporal action localization aims to localize action instances in videos with only video-level action labels. Existing methods mainly embrace a localization-by-classification pipeline that optimizes the…

Action LocalizationClassificationClusteringTemporal Action Localization+3

Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning

2023-10-22 · IROS 2023 2023 10 · Fan YangShigeyuki OdashimaShoichi MasuiShan Jiang

Action segmentation plays an important role in enabling robots to automatically understand human activities. To train the action recognition model, while obtaining action labels for all frames is costly, annotating times…

Action RecognitionAction SegmentationSegmentationWeakly Supervised Action Localization+1

POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization

2023-10-20 · Elahe Vahdani, YingLi Tian

This paper tackles the challenge of point-supervised temporal action detection, wherein only a single frame is annotated for each action instance in the training set. Most of the current methods, hindered by the sparse n…

Action DetectionAction LocalizationPseudo LabelTemporal Action Localization+1

HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation

2023-08-24 · Huaxin Zhang, Xiang Wang, Xiaohao Xu, Zhiwu Qing 외

Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the ins…

Action LocalizationTemporal Action LocalizationWeakly Supervised Action Localization

Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling

2023-08-19 · ICCV 2023 1 · Guiqin Wang, Peng Zhao, Cong Zhao, Shusen Yang 외

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…

Action LocalizationMultiple Instance LearningWeakly Supervised Action Localization

Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization

2023-06-26 · AAAI 2023 6 · Zhilin Li, Zilei Wang, Qinying Liu

Weakly-supervised temporal action localization (WTAL) aims to detect action instances given only video-level labels. To address the challenge, recent methods commonly employ a two-branch framework, consisting of a class-…

Action LocalizationContrastive LearningRepresentation LearningTemporal Action Localization+2

Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization

2023-05-29 · CVPR 2023 1 · Huan Ren, Wenfei Yang, Tianzhu Zhang, Yongdong Zhang

Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods f…

Action LocalizationMultiple Instance LearningTemporal Action LocalizationWeakly Supervised Action Localization+1

PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization

2023-01-01 · CVPR 2023 1 · Mamshad Nayeem Rizve, Gaurav Mittal, Ye Yu, Matthew Hall 외

Weakly-supervised Temporal Action Localization (WTAL) attempts to localize the actions in untrimmed videos using only video-level supervision. Most recent works approach WTAL from a localization-by-classification per…

Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action Localization

Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms

2023-01-01 · CVPR 2023 1 · Yu Wang, Yadong Li, Hongbin Wang

Weakly-supervised temporal action localization aims to detect action boundaries in untrimmed videos with only video-level annotations. Most existing schemes detect temporal regions that are most responsive to video-l…

Action LocalizationMultiple Instance LearningTemporal Action LocalizationWeakly Supervised Action Localization+1

Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions

2022-07-24 · Zhi Li, Lu He, Huijuan Xu

Action understanding has evolved into the era of fine granularity, as most human behaviors in real life have only minor differences. To detect these fine-grained actions accurately in a label-efficient way, we tackle the…

Action DetectionAction UnderstandingFine-Grained Action DetectionWeakly Supervised Action Localization

Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning

2022-06-22 · Jia-Run Du, Jia-Chang Feng, Kun-Yu Lin, Fa-Ting Hong 외

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 indic…

Action LocalizationMultiple Instance LearningRepresentation LearningTemporal Action Localization+2

0/1 Deep Neural Networks via Block Coordinate Descent

2022-06-19 · HUI ZHANG, Shenglong Zhou, Geoffrey Ye Li, Naihua Xiu

The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsic characteristics (e.g., discontinuity a…

10-shot image generation16k2D Object Detection+92

Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization

2022-05-01 · Qinying Liu, Zilei Wang, Ruoxi Chen, Zhilin Li

Weakly-supervised temporal action localization (WTAL) intends to detect action instances with only weak supervision, e.g., video-level labels. The current~\textit{de facto} pipeline locates action instances by thresholdi…

Action LocalizationData AugmentationTemporal Action LocalizationVideo Classification+2

Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization

2022-03-31 · CVPR 2022 1 · Junyu Gao, Mengyuan Chen, Changsheng Xu

We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly embrace a localization…

Action LocalizationClassificationContrastive LearningInductive Bias+3

Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization

2021-08-11 · ICCV 2021 10 · Pilhyeon Lee, Hyeran Byun

We tackle the problem of localizing temporal intervals of actions with only a single frame label for each action instance for training. Owing to label sparsity, existing work fails to learn action completeness, resulting…

Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action Localization

Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization

2021-07-27 · Fa-Ting Hong, Jia-Chang Feng, Dan Xu, Ying Shan 외

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 us…

Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action Localization

FineAction: A Fine-Grained Video Dataset for Temporal Action Localization

2021-05-24 · Yi Liu, LiMin Wang, Yali Wang, Xiao Ma 외

Temporal action localization (TAL) is an important and challenging problem in video understanding. However, most existing TAL benchmarks are built upon the coarse granularity of action classes, which exhibits two major l…

Action DetectionAction LocalizationFine-Grained Action DetectionTemporal Action Localization+3

Action Shuffling for Weakly Supervised Temporal Localization

2021-05-10 · Xiao-Yu Zhang, Haichao Shi, Changsheng Li, Xinchu Shi

Weakly supervised action localization is a challenging task with extensive applications, which aims to identify actions and the corresponding temporal intervals with only video-level annotations available. This paper ana…

Action LocalizationTemporal LocalizationWeakly Supervised Action Localization
1–20 / 55 다음 →