Browse State-of-the-Art › Action Recognition In Videos

Action Recognition In Videos

71 papers with code · 17 benchmarks · 17 datasets archive 2025-07-28

Computer Vision

Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

17 leaderboard tables shown for this task, 17 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 17 until expanded.

Syntology 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): PKU-MMD (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
Jester (Gesture Recognition) (9 rows) CPNet Res34, 5 CP Learning Video Representations from Correspondence Proposals code — Compare
PKU-MMD (5 rows) DSCNet (RGB + Pose) A Dense-Sparse Complementary Network for Human Action Recognition... code — Compare
UCF101 (5 rows) STM (ImageNet+Kinetics pretrain) STM: SpatioTemporal and Motion Encoding for Action Recognition — — Compare
Something-Something V2 (4 rows) STM (16 frames, ImageNet pretraining) STM: SpatioTemporal and Motion Encoding for Action Recognition — — Compare
Kinetics-400 (3 rows) Florence Florence: A New Foundation Model for Computer Vision code — Compare
Something-Something V1 (3 rows) STM (16 frames, ImageNet pretraining) STM: SpatioTemporal and Motion Encoding for Action Recognition — — Compare
AVA v2.2 (2 rows) YOWO+LFB* You Only Watch Once: A Unified CNN Architecture for Real-Time... code Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified Compare
FS-Something-Something V2-Small (2 rows) ITANet Learning Implicit Temporal Alignment for Few-shot Video Classification code — Compare
FS-Something-Something V2-Full (2 rows) ITANet Learning Implicit Temporal Alignment for Few-shot Video Classification code — Compare
Sports-1M (2 rows) G-Blend What Makes Training Multi-Modal Classification Networks Hard? code Syntology 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified Compare
THUMOS’14 (2 rows) Single-stream R-C3D (two-way buffer) R-C3D: Region Convolutional 3D Network for Temporal Activity Detection code Syntology official: harvested, nothing ran · 0 ran · 1 unverified Compare
ActivityNet (1 row) LSTM + Pretrained on YT-8M YouTube-8M: A Large-Scale Video Classification Benchmark code Syntology 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified Compare
AVA v2.1 (1 row) YOWO+LFB* You Only Watch Once: A Unified CNN Architecture for Real-Time... code Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified Compare
HMDB-51 (1 row) STM (ImageNet+Kinetics pretrain) STM: SpatioTemporal and Motion Encoding for Action Recognition — — Compare
Kinetics-600 (1 row) Florence Florence: A New Foundation Model for Computer Vision code — Compare
miniSports (1 row) G-Blend What Makes Training Multi-Modal Classification Networks Hard? code Syntology 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified Compare
NTU RGB+D (1 row) 2D-3D-Softargmax (RGB only) 2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning code Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 20 unverified 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

17 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: 124 · with a code link: 71 · where Syntology ran a sample: 23 (22 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (23 of 124 tagged: 22 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 124, 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 25 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