Browse State-of-the-Art › Weakly-supervised Temporal Action Localization
Weakly-supervised Temporal Action Localization
41 papers with code · 3 benchmarks · 4 datasets archive 2025-07-28
Temporal Action Localization with weak supervision where only video-level labels are given for training
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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| THUMOS’14 (4 rows) | CO2-Net | Cross-modal Consensus Network for Weakly Supervised Temporal... | code | — | Compare |
| ActivityNet-1.3 (1 row) | ASM-Loc | ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised... | code | — | Compare |
| UCF101-24 (1 row) | Structured Keypoint Pooling | Unified Keypoint-based Action Recognition Framework via Structured... | — | — | Compare |
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 76 · with a code link: 41 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (1 of 76 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 76 of 76, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
21 Dec 2021 5 repositories listedWeakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.
-
14 Dec 2017 3 repositories listedWe propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks.
-
22 Jun 2022 2 repositories listedAccordingly, we first exclude these surely non-existent categories by a complementary learning loss.
-
27 Jul 2021 2 repositories listedIn this work, we argue that the features extracted from the pretrained extractor, e. g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant…
-
7 Apr 2021 2 repositories listedTraditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence.
-
12 Jun 2020 2 repositories listedExperimental 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.
-
22 Nov 2019 2 repositories listedThis 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.
-
27 Dec 2024 1 repository listedAdditionally, 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…
-
24 Nov 2024 1 repository listedThe AAL branch uses pseudo labels to learn class-agnostic action information.
-
12 Aug 2024 1 repository listedTo address these problems, we propose a novel framework that aligns human action knowledge and VLP knowledge in a probabilistic embedding space.
-
12 Jul 2024 1 repository listedHowever, the quality of pseudo labels in the framework, which is a key factor to the final result, is not carefully studied.
-
15 Apr 2024 1 repository listedOur method seeks to suppress false positive backgrounds without introducing the background category.
-
1 Jan 2024 1 repository listedIn CSL we design a novel center label generated by the point annotations for predicting aligned center scores.
-
21 Dec 2023 1 repository listedIt 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…
-
31 Jul 2023 1 repository listedConsidering 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…
-
26 Jun 2023 1 repository listedIn principle, the two branches are supposed to produce the same actionness activation.
-
29 May 2023 1 repository listedWeakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training.
-
1 May 2023 1 repository listedFor 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…
-
25 Apr 2023 1 repository listedThe 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 Labels17 Apr 2023 1 repository listedBesides, the generated pseudo-labels can be fluctuating and inaccurate at the early stage of training.
-
22 Mar 2023 1 repository listedWeakly-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.
-
10 Aug 2022 1 repository listedThis 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.
-
1 May 2022 1 repository listedC³BN 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…
-
31 Mar 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training.
-
29 Mar 2022 1 repository listedWithout the boundary information of action segments, existing methods mostly rely on multiple instance learning (MIL), where the predictions of unlabeled instances (i. e., video snippets) are supervised by classifying…
-
6 Mar 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)Our method seeks to mine the representative snippets in each video for propagating information between video snippets to generate better pseudo labels.
-
24 Nov 2021 1 repository listedWeakly 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.
-
14 Aug 2021 1 repository listedIn 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…
-
11 Aug 2021 1 repository listedTo 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.
-
27 Jul 2021 1 repository listedIn this work, we argue that the features extracted from the pretrained extractor, e. g., I3D, are not the WS-TALtask-specific features, thus the feature re-calibration is needed for reducing the task-irrelevant…
-
30 Mar 2021 1 repository listed
-
24 Mar 2021 1 repository listed
-
3 Jan 2021 1 repository listed
-
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations11 Dec 2020 1 repository listed
-
13 Jul 2020 1 repository listed
-
27 Mar 2020 1 repository listed
-
21 Jan 2020 1 repository listed
-
22 Aug 2019 1 repository listed
-
1 Jun 2019 1 repository listed
-
30 Mar 2019 1 repository listed
-
22 Jul 2018 1 repository listed
-
Bridge the Gap: From Weak to Full Supervision for Temporal Action Localization with PseudoFormer21 Apr 2025 0 repositories listed
-
Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction19 Jan 2025 0 repositories listed
-
Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models1 Jan 2025 0 repositories listed
-
Can MLLMs Guide Weakly-Supervised Temporal Action Localization Tasks?13 Nov 2024 0 repositories listed
-
STAT: Towards Generalizable Temporal Action Localization20 Apr 2024 0 repositories listed
-
Sub-action Prototype Learning for Point-level Weakly-supervised Temporal Action Localization16 Sep 2023 0 repositories listed
-
Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localization24 Aug 2023 0 repositories listed
-
Video-Specific Query-Key Attention Modeling for Weakly-Supervised Temporal Action Localization7 May 2023 0 repositories listed
-
JCDNet: Joint of Common and Definite phases Network for Weakly Supervised Temporal Action Localization30 Mar 2023 0 repositories listed
-
27 Mar 2023 0 repositories listed
-
Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization1 Jan 2023 0 repositories listed
-
1 Jan 2023 0 repositories listed
-
1 Jan 2023 0 repositories listed
-
Distilling Vision-Language Pre-training to Collaborate with Weakly-Supervised Temporal Action Localization19 Dec 2022 0 repositories listed
-
Slow Motion Matters: A Slow Motion Enhanced Network for Weakly Supervised Temporal Action Localization21 Nov 2022 0 repositories listed
-
Enabling Weakly-Supervised Temporal Action Localization from On-Device Learning of the Video Stream25 Aug 2022 0 repositories listed
-
Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization14 Jul 2022 0 repositories listed
-
Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization1 Jan 2022 0 repositories listed
-
Deep Motion Prior for Weakly-Supervised Temporal Action Localization12 Aug 2021 0 repositories listed
-
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 202127 Jul 2021 0 repositories listed
-
Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track21 Jun 2021 0 repositories listed
-
Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling20 Jun 2021 0 repositories listed
-
29 Apr 2021 0 repositories listed
-
6 Apr 2021 0 repositories listed
-
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context30 Mar 2021 0 repositories listed
-
28 Mar 2021 0 repositories listed
-
22 Oct 2020 0 repositories listed
-
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization18 Aug 2020 0 repositories listed
-
Weakly Supervised Temporal Action Localization with Segment-Level Labels3 Jul 2020 0 repositories listed
-
Towards Train-Test Consistency for Semi-supervised Temporal Action Localization24 Oct 2019 0 repositories listed
-
1 Oct 2019 0 repositories listed
-
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization7 Aug 2019 0 repositories listed
-
21 May 2019 0 repositories listed
-
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization28 Oct 2018 0 repositories listed
-
1 Sep 2018 0 repositories listed
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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections