Browse State-of-the-Art › Action Classification

Action Classification

251 papers with code · 28 benchmarks · 33 datasets archive 2025-07-28

Computer Vision

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

28 leaderboard tables shown for this task, 28 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 28 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): Kinetics-600 (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
Kinetics-400 (207 rows) OmniVec2 OmniVec2 - A Novel Transformer based Network for Large Scale... — — Compare
Kinetics-600 (65 rows) InternVideo2-6B InternVideo2: Scaling Foundation Models for Multimodal Video Understanding code — Compare
Charades (49 rows) TokenLearner TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? code Syntology official (archive's flag): 1 ran · 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Kinetics-700 (36 rows) InternVideo2-6B InternVideo2: Scaling Foundation Models for Multimodal Video Understanding code — Compare
MiT (29 rows) OmniVec2 OmniVec2 - A Novel Transformer based Network for Large Scale... — — Compare
Toyota Smarthome dataset (13 rows) π-ViT Just Add π! Pose Induced Video Transformers for Understanding... code — Compare
AViD (10 rows) TokenLearner TokenLearner: What Can 8 Learned Tokens Do for Images and Videos? code Syntology official (archive's flag): 1 ran · 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Kinetics-Sounds (4 rows) CA2ST(B/16) CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic... — — Compare
Moments in Time (4 rows) OmniVec2 OmniVec2 - A Novel Transformer based Network for Large Scale... — — Compare
ActivityNet-1.2 (3 rows) W-TALC W-TALC: Weakly-supervised Temporal Activity Localization and Classification code Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified Compare
Kinetics-700-2020 (3 rows) ALIP-ViT B/32 LAION30M ALIP: Adaptive Language-Image Pre-training with Synthetic Caption code Syntology official (archive's flag): 5 ran · 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) · 5 unverified Compare
THUMOS’14 (3 rows) 3C-Net 3C-Net: Category Count and Center Loss for Weakly-Supervised... code — Compare
WiGesture (3 rows) CSI-BERT2 Mining Limited Data Sufficiently: A BERT-inspired Approach for CSI... — — Compare
MIT (2 rows) InternVideo2-6B InternVideo2: Scaling Foundation Models for Multimodal Video Understanding code — Compare
TTStroke-21 ME22 (2 rows) RGB and PRGB Fine-Grained Action Detection with RGB and Pose Information using... code — Compare
ActivityNet (1 row) UniFormerV2-L UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with... code — Compare
BABEL (1 row) 2s-AGCN BABEL: Bodies, Action and Behavior with English Labels code — Compare
CelebV-HQ (1 row) MARLIN MARLIN: Masked Autoencoder for facial video Representation LearnINg code — Compare
Diving-48 (1 row) DualPath w/ ViT-B/16 Dual-path Adaptation from Image to Video Transformers code — Compare
HMDB51 (1 row) DualPath w/ ViT-B/16 MLPs. Dual-path Adaptation from Image to Video Transformers code — Compare
Jester test (1 row) C2F Towards Efficient Coarse-to-Fine Networks for Action and Gesture... — — Compare
MiniKinetics (1 row) MARS+RGB+Flow (16 frames) MARS: Motion-Augmented RGB Stream for Action Recognition code — Compare
Something-Something V2 (1 row) AdaMAE AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning... code Syntology official (archive's flag): 14 ran · 18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified Compare
THUMOS'14 (1 row) 3C-Net 3C-Net: Category Count and Center Loss for Weakly-Supervised... code — Compare
TTStroke-21 ME21 (1 row) STCNN Spatio-Temporal CNN baseline method for the Sports Video Task of... code — Compare
UCF101 (1 row) Ours SPAct: Self-supervised Privacy Preservation for Action Recognition code Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result Compare
WiFall (1 row) CSI-BERT2 Mining Limited Data Sufficiently: A BERT-inspired Approach for CSI... — — Compare
YouCook2 (1 row) VideoBERT (cross modal) VideoBERT: A Joint Model for Video and Language Representation Learning code Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 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

33 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 33 until expanded.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 457 · with a code link: 251 · where Syntology ran a sample: 83 (75 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (83 of 457 tagged: 75 with a run with no instrument failure, 8 where every run was a failure of Syntology's instrument)

Page 1 of 5: papers 1 to 100 of 457, 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 53 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