Browse › Computer Vision › Action Recognition › Something-Something V2

Action Recognition archive 2025-07-28

Something-Something V2 Benchmark (Action Recognition)

123 rows 103 with code listed 4 metrics Dataset page

Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.

In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.

Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.

The archive carries no text for this table; the description above is the archive's text for the task Action Recognition. archive 2025-07-28

Over time archive 2025-07-28

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: Top-1 Accuracy (higher is better), Top-5 Accuracy (higher is better). Not inferred (points only, no best-so-far line): Parameters, GFLOPs. Points are placed at the row's paper date; 123 of 123 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 MVD (Kinetics400 pretrain, ViT-H, 16 frame) 77.395.76331192x6 ✓ Paper Code 2022 linked, not harvested report
2 DejaVid 77.296.3 ✓ Paper Code 2025 linked, not harvested report
3 InternVideo 77.2 ✓ Paper Code 2022 3 of 3 ran · 0 unverified report
4 InternVideo2-1B 77.1 ✓ Paper Code 2024 linked, not harvested report
5 VideoMAE V2-g 77.095.910132544x6 ✓ Paper Code 2023 2 of 6 ran · 4 unverified report
6 MVD (Kinetics400 pretrain, ViT-L, 16 frame) 76.795.5305597x6 ✓ Paper Code 2022 linked, not harvested report
7 Hiera-L (no extra data) 76.5 – Paper Code 2023 0 of 6 ran · 6 unverified report
8 TubeViT-L 76.195.2 – Paper Code 2022 1 of 3 ran · 2 unverified report
9 VideoMAE (no extra data, ViT-L, 32x2) 75.495.23051436x3 – Paper Code 2022 9 of 13 ran · 4 unverified report
10 Side4Video (EVA ViT-E/14) 75.294.0 – Paper Code 2023 linked, not harvested report
11 MaskFeat (Kinetics600 pretrain, MViT-L) 75.095.02182828*3 ✓ Paper Code 2021 linked, not harvested report
12 MAR (50% mask, ViT-L, 16x4) 74.794.9311276x6 – Paper Code 2022 linked, not harvested report
13 ATM 74.694.4 – Paper Code 2023 3 of 6 ran · 3 unverified report
14 MAWS (ViT-L) 74.4 ✓ Paper Code 2023 linked, not harvested report
15 VideoMAE (no extra data, ViT-L, 16frame) 74.394.6305597x6 – Paper Code 2022 9 of 13 ran · 4 unverified report
16 MAR (75% mask, ViT-L, 16x4) 73.894.4311131x6 – Paper Code 2022 linked, not harvested report
17 MVD (Kinetics400 pretrain, ViT-B, 16 frame) 73.794.087180x6 ✓ Paper Code 2022 linked, not harvested report
18 ViC-MAE (ViT-L) 73.7 – Paper Code 2023 linked, not harvested report
19 TAdaFormer-L/14 73.6 ✓ Paper Code 2023 2 of 2 ran · 0 unverified report
20 TDS-CLIP-ViT-L/14(8frames) 73.493.8 – Paper Code 2024 linked, not harvested report
21 MViTv2-L (IN-21K + Kinetics400 pretrain) 73.394.1213.1 – Paper Code 2021 linked, not harvested report
22 AMD(ViT-B/16) 73.394.087180x6 – Paper – 2023 no code linked report
23 UniFormerV2-L 73.094.55154 ✓ Paper Code 2022 linked, not harvested report
24 ST-Adapter (ViT-L, CLIP) 72.393.98248 ✓ Paper Code 2022 4 of 10 ran · 6 unverified report
25 ZeroI2V ViT-L/14 72.293.0 ✓ Paper Code 2023 1 of 3 ran · 2 unverified report
26 MViT-B (IN-21K + Kinetics400 pretrain) 72.1225x3 ✓ Paper Code 2021 linked, not harvested report
27 CAST(ViT-B/16) 71.6 – Paper Code 2023 9 of 17 ran · 8 unverified report
28 StructVit-B-4-1 71.5 – Paper – 2024 no code linked report
29 OMNIVORE (Swin-B, IN-21K+ Kinetics400 pretrain) 71.493.5 ✓ Paper Code 2022 2 of 2 ran · 0 unverified report
30 BEVT (IN-1K + Kinetics400 pretrain) 71.4-89321x3 ✓ Paper Code 2021 linked, not harvested report
31 UniFormer-B (IN-1K + Kinetics400 pretrain) 71.292.850.1259x3 ✓ Paper Code 2021 linked, not harvested report
32 TAdaConvNeXtV2-B 71.1 ✓ Paper Code 2023 2 of 2 ran · 0 unverified report
33 MAR (50% mask, ViT-B, 16x4) 71.092.89486x6 – Paper Code 2022 linked, not harvested report
34 MVD (Kinetics400 pretrain, ViT-S, 16 frame) 70.992.82257x6 ✓ Paper Code 2022 linked, not harvested report
35 CoVeR(JFT-3B) 70.992.5 ✓ Paper – 2021 no code linked report
36 VideoMAE (no extra data, ViT-B, 16frame) 70.892.487180x6 – Paper Code 2022 9 of 13 ran · 4 unverified report
37 AMD(ViT-S/16) 70.292.52257x6 – Paper – 2023 no code linked report
38 ILA (ViT-L/14) 70.291.8 – Paper Code 2023 2 of 4 ran · 2 unverified report
39 MorphMLP-B (IN-1K) 70.192.868.5197x3 ✓ Paper Code 2021 2 of 2 ran · 0 unverified report
40 CoVeR(JFT-300M) 69.891.9 ✓ Paper – 2021 no code linked report
41 TPS 69.8 – Paper Code 2022 1 of 1 ran · 0 unverified report
42 SIFA 69.8 – Paper Code 2022 linked, not harvested report
43 Swin-B (IN-21K + Kinetics400 pretrain) 69.692.789321x3 ✓ Paper Code 2021 7 of 32 ran · 25 unverified report
44 TDN ResNet101 (one clip, three crop, 8+16 ensemble, ImageNet pretrained, RGB only) 69.692.2198x3 ✓ Paper Code 2020 2 of 4 ran · 2 unverified report
45 MAR (75% mask, ViT-B, 16x4) 69.591.99441x6 – Paper Code 2022 linked, not harvested report
46 ORViT Mformer-L (ORViT blocks) 69.591.5N/AN/A ✓ Paper Code 2021 1 of 7 ran · 6 unverified report
47 UniFormer-S (IN-1K + Kinetics600 pretrain) 69.492.121.441.8x3 ✓ Paper Code 2021 linked, not harvested report
48 MML (ensemble) 69.0292.70 ✓ Paper Code 2020 linked, not harvested report
49 MViT-B-24, 32x3 68.791.553.2M236x3 ✓ Paper Code 2021 13 of 26 ran · 13 unverified report
50 MTV-B 68.590.4 ✓ Paper Code 2022 linked, not harvested report
51 MLP-3D 68.5 – Paper – 2022 no code linked report
52 TDN ResNet101 (one clip, center crop, 8+16 ensemble, ImageNet pretrained, RGB only) 68.291.6198x1 ✓ Paper Code 2020 2 of 4 ran · 2 unverified report
53 MSMA (8+16frames) 68.2 – Paper – 2023 no code linked report
54 Mformer-L 68.191.2N/A1181x3 ✓ Paper Code 2021 1 of 2 ran · 1 unverified report
55 VIMPAC 68.1 ✓ Paper Code 2021 1 of 1 ran · 0 unverified report
56 ORViT Mformer (ORViT blocks) 67.990.5N/AN/A ✓ Paper Code 2021 1 of 7 ran · 6 unverified report
57 MViT-B, 32x3(Kinetics600 pretrain) 67.891.336.6170x3 ✓ Paper Code 2021 13 of 26 ran · 13 unverified report
58 GC-TDN Ensemble (R50,8+16) 67.891.227.4110.1 ✓ Paper Code 2022 5 of 5 ran · 0 unverified report
59 CT-Net Ensemble (R50, 8+12+16+24) 67.891.183.8280 ✓ Paper Code 2021 10 of 13 ran · 3 unverified report
60 TCM (Ensemble) 67.8 – Paper Code 2022 linked, not harvested report
61 SELFYNet-TSM-R50En (8+16 frames, ImageNet pretrained, 2 clips) 67.791.1 ✓ Paper Code 2021 3 of 4 ran · 1 unverified report
62 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips 67.791.1 ✓ Paper Code 2021 1 of 1 ran · 0 unverified report
63 GTDNet 67.6 – Paper – 2022 no code linked report
64 SELFYNet-TSM-R50En (8+16 frames, ImageNet pretrained, a single clip) 67.491 ✓ Paper Code 2021 3 of 4 ran · 1 unverified report
65 VoV3D-L (32frames, Kinetics pretrained, single) 67.3590.505.8M20.9x6 ✓ Paper Code 2020 linked, not harvested report
66 PLAR 67.391 – Paper – 2023 no code linked report
67 RSANet-R50 (8+16 frames, ImageNet pretrained, a single clip) 67.390.8 ✓ Paper Code 2021 1 of 1 ran · 0 unverified report
68 X-Vit (x16) 67.290.8N/A850x1 ✓ Paper Code 2021 1 of 1 ran · 0 unverified report
69 TAda2D-En (ResNet-50, 8+16 frames) 67.289.8 ✓ Paper Code 2021 0 of 1 ran · 1 unverified report
70 Mformer-HR 67.190.6N/A958.8x3 ✓ Paper Code 2021 1 of 2 ran · 1 unverified report
71 TAdaConvNeXt-T 67.190.4 ✓ Paper Code 2021 0 of 1 ran · 1 unverified report
72 MoDS (8+16frames) 67.1 – Paper – 2022 no code linked report
73 STPG (8+16frames) 67.0 – Paper – 2022 no code linked report
74 MML (single) 66.8391.30 ✓ Paper Code 2020 linked, not harvested report
75 ILA (ViT-B/16) 66.890.3 – Paper Code 2023 2 of 4 ran · 2 unverified report
76 TSM (RGB + Flow) 66.691.3 ✓ Paper Code 2018 6 of 16 ran · 10 unverified report
77 MSNet-R50En (8+16 ensemble, ImageNet pretrained) 66.690.6 ✓ Paper Code 2020 3 of 8 ran · 5 unverified report
78 PAN ResNet101 (RGB only, no Flow) 66.590.6 ✓ Paper Code 2020 linked, not harvested report
79 TSM+W3 (16 frames, RGB ResNet-50) 66.590.4 ✓ Paper – 2020 no code linked report
80 Mformer 66.590.1 ✓ Paper Code 2021 1 of 2 ran · 1 unverified report
81 MVFNet-ResNet50 (center crop, 8+16 ensemble, ImageNet pretrained, RGB only) 66.3 ✓ Paper Code 2020 linked, not harvested report
82 MViT-B, 16x4 66.290.2 ✓ Paper Code 2021 13 of 26 ran · 13 unverified report
83 RSANet-R50 (16 frames, ImageNet pretrained, a single clip) 6689.8 ✓ Paper Code 2021 1 of 1 ran · 0 unverified report
84 VoV3D-L (32frames, from scratch, single) 65.889.55.8M20.9x6 – Paper Code 2020 linked, not harvested report
85 E3D-L 65.789.818.3 – Paper Code 2023 linked, not harvested report
86 SELFYNet-TSM-R50 (16 frames, ImageNet pretrained) 65.789.8 ✓ Paper Code 2021 3 of 4 ran · 1 unverified report
87 TAda2D (ResNet-50, 16 frames) 65.689.2 ✓ Paper Code 2021 0 of 1 ran · 1 unverified report
88 ViViT-L/16x2 Fact. encoder 65.489.8 ✓ Paper Code 2021 14 of 21 ran · 7 unverified report
89 VoV3D-M (32frames, Kinetics pretrained, single) 65.2489.483.3M11.5x6 ✓ Paper Code 2020 linked, not harvested report
90 bLVNet 65.2 ✓ Paper Code 2019 0 of 6 ran · 6 unverified report
91 DirecFormer 64.9487.9 – Paper Code 2022 4 of 8 ran · 4 unverified report
92 RSANet-R50 (8 frames, ImageNet pretrained, a single clip) 64.889.1 ✓ Paper Code 2021 1 of 1 ran · 0 unverified report
93 MSNet-R50 (16 frames, ImageNet pretrained) 64.789.4 ✓ Paper Code 2020 3 of 8 ran · 5 unverified report
94 AK-Net 64.3 – Paper – 2022 no code linked report
95 VoV3D-M (32frames, from scratch, single) 64.288.83.3M11.5x6 – Paper Code 2020 linked, not harvested report
96 VoV3D-L (16frames, from scratch, single) 64.188.65.8M9.3x6 – Paper Code 2020 linked, not harvested report
97 TAda2D (ResNet-50, 8 frames) 64.088.0 ✓ Paper Code 2021 0 of 1 ran · 1 unverified report
98 MoViNet-A2 63.589.04.8M10.3x1 – Paper Code 2021 8 of 13 ran · 5 unverified report
99 VoV3D-M (16frames, from scratch, single) 63.288.23.3M5.7x6 – Paper Code 2020 linked, not harvested report
100 MSNet-R50 (8 frames, ImageNet pretrained) 6388.4 ✓ Paper Code 2020 3 of 8 ran · 5 unverified report
101 MoViNet-A1 62.789.04.6M6.0x1 – Paper Code 2021 8 of 13 ran · 5 unverified report
102 OmniVL 62.586.2 – Paper – 2022 no code linked report
103 TimeSformer-HR 62.5 ✓ Paper Code 2021 35 of 43 ran · 8 unverified report
104 TimeSformer-L 62.3 ✓ Paper Code 2021 35 of 43 ran · 8 unverified report
105 TRG (ResNet-50) 62.290.3 – Paper – 2019 no code linked report
106 TPN (TSM-50) 62.0 – Paper Code 2020 0 of 3 ran · 3 unverified report
107 Multigrid 61.7 ✓ Paper Code 2019 2 of 10 ran · 8 unverified report
108 SlowFast 61.7 ✓ Paper Code 2018 0 of 10 ran · 10 unverified report
109 TRG (Inception-V3) 61.391.4 – Paper – 2019 no code linked report
110 MoViNet-A0 61.388.23.1M2.7x1 – Paper Code 2021 8 of 13 ran · 5 unverified report
111 CCS + two-stream + TRN 61.289.3 – Paper – 2019 no code linked report
112 VidTr-L 60.2 – Paper – 2021 no code linked report
113 TimeSformer 59.5 ✓ Paper Code 2021 35 of 43 ran · 8 unverified report
114 SVT 59.2 – Paper Code 2021 0 of 1 ran · 1 unverified report
115 TAM (5-shot) 52.3 – Paper – 2019 no code linked report
116 model3D_1 with left-right augmentation and fps jitter 51.3380.46 – Paper Code 2017 linked, not harvested report
117 Prob-Distill 49.979.1 – Paper – 2019 no code linked report
118 STM + TRNMultiscale 47.73 – Paper Code 2019 linked, not harvested report
119 InternVideo2-6B 112213113321 ✓ Paper Code 2024 linked, not harvested report
120 MViTv2-B (IN-21K + Kinetics400 pretrain) 93.451.1 – Paper Code 2021 linked, not harvested report
121 RSANet-R50 (8+16 frames, ImageNet pretrained, 2 clips) 91.1 – Paper Code 2021 1 of 1 ran · 0 unverified report
122 MoViNet-A3 5.3M23.7x1 – Paper Code 2021 8 of 13 ran · 5 unverified report
123 MViT-L (IN-21K + Kinetics400 pretrain) 2828x3 ✓ Paper Code 2021 linked, not harvested report

All 123 rows shown. 123 link to a paper page on this site; 70 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 63 rows have a graph line, from 37 distinct papers; 54 rows (31 papers) have at least one sample that ran. Counting each paper once: Syntology ran 158 of 314 samples; 156 unverified. Separately, 84 of those 314 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

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