Background Suppression Network for Weakly-supervised Temporal Action Localization
Not on the map. Why?
Abstract (arXiv)
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. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-the-art methods on the most popular benchmarks - THUMOS'14 and ActivityNet. Our code and the trained model are available at https://github.com/Pilhyeon/BaSNet-pytorch.
Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Nov 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 21; 2022: 18; 2023: 21; 2024: 8; 2025: 3; 2026: 2.
73 papers.
Sort:
By area:
- 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 88
- 2021CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learningcited by 69
- 2021Temporal Action Segmentation from Timestamp Supervisioncited by 48
- 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
- 2021Learning Action Completeness from Points for Weakly-supervised Temporal Action Localizationcited by 42
- 2022ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localizationcited by 39
- 2021Cross-modal Consensus Network for Weakly Supervised Temporal Action Localizationcited by 34
- 2022Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localizationcited by 33
- 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
- 2022Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagationcited by 32
- 2021Action Unit Memory Network for Weakly Supervised Temporal Action Localizationcited by 26
- 2021Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localizationcited by 26
38 more
- 2022Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foregroundcited by 26
- 2021Weakly Supervised Action Selection Learning in Videocited by 21
- 2021Background-Click Supervision for Temporal Action Localizationcited by 21
- 2023Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Featurecited by 21
- 2021ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localizationcited by 20
- 2021ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localizationcited by 19
- 2023Multi-modal Prompting for Low-Shot Temporal Action Localizationcited by 19
- 2023Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localizationcited by 19
- 2021Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localizationcited by 18
- 2022Learning to Refactor Action and Co-occurrence Features for Temporal Action Localizationcited by 18
- 2021ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localizationcited by 17
- 2021The Blessings of Unlabeled Background in Untrimmed Videoscited by 16
- 2021Temporal Action Proposal Generation with Background Constraintcited by 16
- 2023HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagationcited by 16
- 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attentioncited by 15
- 2023Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labelscited by 14
- 2023Temporal Action Localization with Enhanced Instant Discriminabilitycited by 13
- 2021Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Contextcited by 12
- 2022Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localizationcited by 12
- 2023Decomposed Cross-modal Distillation for RGB-based Temporal Action Detectioncited by 12
- 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
- 2022Exploring Temporally Dynamic Data Augmentation for Video Recognitioncited by 9
- 2023Boosting Weakly-Supervised Temporal Action Localization with Text Informationcited by 8
- 2021Deep Motion Prior for Weakly-Supervised Temporal Action Localizationcited by 7
- 2023DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localizationcited by 7
- 2022Exploiting Shape Cues for Weakly Supervised Semantic Segmentationcited by 6
- 2022Weakly-Supervised Temporal Action Localization by Progressive Complementary Learningcited by 5
- 2022Contrastive Losses Are Natural Criteria for Unsupervised Video Summarizationcited by 5
- 2024Action-Agnostic Point-Level Supervision for Temporal Action Detectioncited by 5
- 2021Weakly-Supervised Temporal Action Localization Through Local-Global Background Modelingcited by 4
- 2022Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localizationcited by 4
- 2022Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localizationcited by 4
- 2023Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistencycited by 4
- 2023Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modelingcited by 4
- 2023Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localizationcited by 4
- 2024STAT: Towards Generalizable Temporal Action Localizationcited by 4
- 2023Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localizationcited by 3
- 2024Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localizationcited by 3
50 most cited of 73 All 73 (JSON)
- 2026WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?2 Feb 2026
- 2026Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment1 Feb 2026
- 2025Biomechanical-phase based Temporal Segmentation in Sports Videos: a Demonstration on Javelin-Throw29 Sep 2025
- 2025UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks27 Aug 2025
- 2025Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain23 Jun 2025
- 2024Action-Agnostic Point-Level Supervision for Temporal Action Detection30 Dec 2024
- 2024VARS: Vision-based Assessment of Risk in Security Systems25 Oct 2024
- 2024ViDAS: Vision-based Danger Assessment and Scoring1 Oct 2024
- 2024Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization12 Aug 2024
- 2024Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization12 Jul 2024
- 2024STAT: Towards Generalizable Temporal Action Localization20 Apr 2024
- 2024Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting21 Mar 2024
38 more
- 2024Computer Vision for Primate Behavior Analysis in the Wild29 Jan 2024
- 2023Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization12 Dec 2023
- 2023POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization20 Oct 2023
- 2023Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention28 Sep 2023
- 2023Sub-action Prototype Learning for Point-level Weakly-supervised Temporal Action Localization16 Sep 2023
- 2023Temporal Action Localization with Enhanced Instant Discriminability11 Sep 2023
- 2023Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization24 Aug 2023
- 2023HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation24 Aug 2023
- 2023Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling19 Aug 2023
- 2023Towards Imbalanced Motion: Part-Decoupling Network for Video Portrait Segmentation31 Jul 2023
- 2023DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization31 Jul 2023
- 2023Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization29 May 2023
- 2023Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization7 May 2023
- 2023Weakly-supervised Micro- and Macro-expression Spotting Based on Multi-level Consistency4 May 2023
- 2023Boosting Weakly-Supervised Temporal Action Localization with Text Information1 May 2023
- 2023Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint25 Apr 2023
- 2023Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels17 Apr 2023
- 2023JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization30 Mar 2023
- 2023Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection30 Mar 2023
- 2023Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature22 Mar 2023
- 2023Multi-modal Prompting for Low-Shot Temporal Action Localization21 Mar 2023
- 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection10 Feb 2023
- 2022Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization19 Dec 2022
- 2022Dilation-Erosion for Single-Frame Supervised Temporal Action Localization13 Dec 2022
- 2022Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground23 Nov 2022
- 2022Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization21 Nov 2022
- 2022Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization18 Nov 2022
- 2022Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering8 Sep 2022
- 2022Active Learning with Effective Scoring Functions for Semi-Supervised Temporal Action Localization31 Aug 2022
- 2022Exploiting Shape Cues for Weakly Supervised Semantic Segmentation8 Aug 2022
- 2022Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization14 Jul 2022
- 2022Exploring Temporally Dynamic Data Augmentation for Video Recognition30 Jun 2022
- 2022Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization23 Jun 2022
- 2022Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning22 Jun 2022
- 2022Scalable Temporal Localization of Sensitive Activities in Movies and TV Episodes16 Jun 2022
- 2022Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization1 May 2022
- 2022Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos28 Apr 2022
- 2022Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization31 Mar 2022
50 newest of 73 All 73 (JSON)
- 2023Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detectioncited by 88
- 2021CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learningcited by 69
- 2021Temporal Action Segmentation from Timestamp Supervisioncited by 48
- 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
- 2021Learning Action Completeness from Points for Weakly-supervised Temporal Action Localizationcited by 42
- 2022ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localizationcited by 39
- 2021Cross-modal Consensus Network for Weakly Supervised Temporal Action Localizationcited by 34
- 2022Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localizationcited by 33
- 2021Deep Learning-based Action Detection in Untrimmed Videos: A Surveycited by 32
- 2022Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagationcited by 32
- 2021Action Unit Memory Network for Weakly Supervised Temporal Action Localizationcited by 26
- 2021Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localizationcited by 26
12 most cited of 72 All 72 (JSON)
- 2026WS-IMUBench: Can Weakly Supervised Methods from Audio, Image, and Video Be Adapted for IMU-based Temporal Action Localization?2 Feb 2026
- 2026Boosting Point-supervised Temporal Action Localization via Text Refinement and Alignment1 Feb 2026
- 2025Biomechanical-phase based Temporal Segmentation in Sports Videos: a Demonstration on Javelin-Throw29 Sep 2025
- 2025UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks27 Aug 2025
- 2025Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain23 Jun 2025
- 2024Action-Agnostic Point-Level Supervision for Temporal Action Detection30 Dec 2024
- 2024VARS: Vision-based Assessment of Risk in Security Systems25 Oct 2024
- 2024ViDAS: Vision-based Danger Assessment and Scoring1 Oct 2024
- 2024Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization12 Aug 2024
- 2024Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization12 Jul 2024
- 2024STAT: Towards Generalizable Temporal Action Localization20 Apr 2024
- 2024Weak Supervision with Arbitrary Single Frame for Micro- and Macro-expression Spotting21 Mar 2024
12 newest of 72 All 72 (JSON)