Weakly-supervised Temporal Action Localization

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 41 papers with code (76 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization
  21 Dec 2021 5 repositories listed
  Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.
• Weakly Supervised Action Localization by Sparse Temporal Pooling Network
  14 Dec 2017 3 repositories listed
  We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks.
• Weakly-Supervised Temporal Action Localization by Progressive Complementary Learning
  22 Jun 2022 2 repositories listed
  Accordingly, we first exclude these surely non-existent categories by a complementary learning loss.
• Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
  27 Jul 2021 2 repositories listed
  In this work, we argue that the features extracted from the pretrained extractor, e.
• ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization
  7 Apr 2021 2 repositories listed
  Traditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence.
• Weakly-supervised Temporal Action Localization by Uncertainty Modeling
  12 Jun 2020 2 repositories listed
  Experimental results show that our uncertainty modeling is effective at alleviating the interference of background frames and brings a large performance gain without bells and whistles.
• Background Suppression Network for Weakly-supervised Temporal Action Localization
  22 Nov 2019 2 repositories listed
  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.
• Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization
  27 Dec 2024 1 repository listed
  Additionally, the proposed GUEF adaptively eliminates the interference of background noise by fusing snippet-level evidences to refine uncertainty measurement and select superior foreground feature information, which…
• Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localization
  24 Nov 2024 1 repository listed
  The AAL branch uses pseudo labels to learn class-agnostic action information.
• Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization
  12 Aug 2024 1 repository listed
  To address these problems, we propose a novel framework that aligns human action knowledge and VLP knowledge in a probabilistic embedding space.
• Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
  12 Jul 2024 1 repository listed
  However, the quality of pseudo labels in the framework, which is a key factor to the final result, is not carefully studied.
• Weakly supervised temporal action localization with actionness-guided false positive suppression
  15 Apr 2024 1 repository listed
  Our method seeks to suppress false positive backgrounds without introducing the background category.
• Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization
  1 Jan 2024 1 repository listed
  In CSL we design a novel center label generated by the point annotations for predicting aligned center scores.
• Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
  21 Dec 2023 1 repository listed
  It comprises two core components: a snippet clustering component that groups the snippets into multiple latent clusters and a cluster classification component that further classifies the cluster as foreground or…
• DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
  31 Jul 2023 1 repository listed
  Considering this phenomenon, we propose Discriminability-Driven Graph Network (DDG-Net), which explicitly models ambiguous snippets and discriminative snippets with well-designed connections, preventing the transmission…
• Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action Localization
  26 Jun 2023 1 repository listed
  In principle, the two branches are supposed to produce the same actionness activation.
• Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
  29 May 2023 1 repository listed
  Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training.
• Boosting Weakly-Supervised Temporal Action Localization with Text Information
  1 May 2023 1 repository listed
  For the discriminative objective, we propose a Text-Segment Mining (TSM) mechanism, which constructs a text description based on the action class label, and regards the text as the query to mine all class-related…
• Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint
  25 Apr 2023 1 repository listed
  The proposed Bi-SCC firstly adopts a temporal context augmentation to generate an augmented video that breaks the correlation between positive actions and their co-scene actions in the inter-video; Then, a semantic…
• Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels
  17 Apr 2023 1 repository listed
  Besides, the generated pseudo-labels can be fluctuating and inaccurate at the early stage of training.
• Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature
  22 Mar 2023 1 repository listed
  Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision.
• Consistency-based Self-supervised Learning for Temporal Anomaly Localization
  10 Aug 2022 1 repository listed
  This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training.
• Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization
  1 May 2022 1 repository listed
  C³BN consists of two key ingredients: a micro data augmentation strategy that increases the diversity in-between adjacent snippets by convex combination of adjacent snippets, and a macro-micro consistency regularization…
• Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
  31 Mar 2022 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training.
• ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization
  29 Mar 2022 1 repository listed
  Without the boundary information of action segments, existing methods mostly rely on multiple instance learning (MIL), where the predictions of unlabeled instances (i.
• Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation
  6 Mar 2022 1 repository listed Syntology ran 2 of 4 samples · 2 unverified
  Our method seeks to mine the representative snippets in each video for propagating information between video snippets to generate better pseudo labels.
• Background-Click Supervision for Temporal Action Localization
  24 Nov 2021 1 repository listed
  Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion.
• Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization
  14 Aug 2021 1 repository listed
  In this paper, we present a framework named FAC-Net based on the I3D backbone, on which three branches are appended, named class-wise foreground classification branch, class-agnostic attention branch and multiple…
• Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization
  11 Aug 2021 1 repository listed
  To learn completeness from the obtained sequence, we introduce two novel losses that contrast action instances with background ones in terms of action score and feature similarity, respectively.
• Cross-modal Consensus Network forWeakly Supervised Temporal Action Localization
  27 Jul 2021 1 repository listed
  In this work, we argue that the features extracted from the pretrained extractor, e.

Syntology lines on 2 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.