Browse State-of-the-Art › Temporal Action Localization

Temporal Action Localization

493 papers with code · 14 benchmarks · 42 datasets archive 2025-07-28

Computer Vision

Temporal Action Localization aims to detect activities in the video stream and output beginning and end timestamps. It is closely related to Temporal Action Proposal Generation.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

14 leaderboard tables shown for this task, 14 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. 10 shown of 14 until expanded.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
THUMOS’14 (42 rows) AdaTAD (VideoMAEv2-giant) End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames code — Compare
ActivityNet-1.3 (33 rows) RDFA-S6 (InternVideo2-6B) Enhancing Temporal Action Localization: Advanced S6 Modeling with... code — Compare
HACS (12 rows) RDFA-S6 (InternVideo2-6B) Enhancing Temporal Action Localization: Advanced S6 Modeling with... code — Compare
FineAction (9 rows) RDFA-S6 (InternVideo2-6B) Enhancing Temporal Action Localization: Advanced S6 Modeling with... code — Compare
MultiTHUMOS (8 rows) TriDet (VideoMAEv2) Temporal Action Localization with Enhanced Instant Discriminability code — Compare
CrossTask (7 rows) VideoCLIP VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding code — Compare
EPIC-KITCHENS-100 (6 rows) AdaTAD (verb, VideoMAE-L) End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames code — Compare
MUSES (2 rows) TemporalMaxer TemporalMaxer: Maximize Temporal Context with only Max Pooling for... code — Compare
ActivityNet-1.2 (1 row) DeepMetricLearner Weakly Supervised Temporal Action Localization Using Deep Metric Learning code — Compare
Ego4D MQ test (1 row) ActionFormer (SlowFast+Omnivore+EgoVLP) Where a Strong Backbone Meets Strong Features -- ActionFormer for... code — Compare
Ego4D MQ val (1 row) ActionFormer (SlowFast+Omnivore+EgoVLP) Where a Strong Backbone Meets Strong Features -- ActionFormer for... code — Compare
MEXaction2 (1 row) S-CNN Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs code — Compare
THUMOS'14 (1 row) AVFusion Hear Me Out: Fusional Approaches for Audio Augmented Temporal... code — Compare
THUMOS14 (1 row) BasicTAD (R50-SlowOnly) BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection code — 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

42 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 42 until expanded.

Subtasks archive 2025-07-28

8 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 1,477 · with a code link: 493 · where Syntology ran a sample: 87 (66 with a run with no instrument failure, 21 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (87 of 1,477 tagged: 66 with a run with no instrument failure, 21 where every run was a failure of Syntology's instrument)

Page 1 of 15: papers 1 to 100 of 1,477, 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.

Syntology lines on 38 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