AI Paper Atlas

Research map / Benchmarks / Something-Something V1

Something-Something V1 leaderboard

45 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Something-Something V1. Best accuracy: 68.7 (VideoMAE V2-g, CVPR 2023).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Something-Something V1 · accuracy

35 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
168.7VideoMAE V2-g
ViT-g
VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking
CVPR 2023 · Table 5 (SSv1 table)
Video segmentation and tracking
265.6ATM ViT-L/14 Merged-2B 16x3x2
ViT-L/14
What Can Simple Arithmetic Operations Do for Temporal Modeling?
ICCV 2023 · Table 3
Action recognition
362.7UniFormerV2-L (32 frames)
CLIP-ViT-L
UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding
ICCV 2023 · Table 12
Video segmentation and tracking
461.3StructViT-B-4-1
UniFormer-B
Learning Correlation Structures for Vision Transformers
CVPR 2024 · Table 5a
Attention and transformers
561UniFormer-B (K600, 32 frames)UniFormer: Unifying Convolution and Self-Attention for Visual Recognition
TPAMI 2023 · Table SSV1&V2
Attention and transformers
661UniFormer-B, K600 pretraining, 32 framesUniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning
ICLR 2022 · Something-Something results ta
Video segmentation and tracking
758.3PST-B-dagger (K400, 3x1)
Swin
Spatiotemporal Self-Attention Modeling with Temporal Patch Shift for Action Recognition
ECCV 2022 · Table 2
Action recognition
857.9DTF-Transformer
Swin-B
Dynamic Temporal Filtering In Video Models
ECCV 2022 · Table 3
Video segmentation and tracking
957.4MorphMLP-B (32x3x1)MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning
ECCV 2022 · Table 3
Action recognition
1057.3SIFA-Transformer
Swin-B
Stand-Alone Inter-Frame Attention in Video Models
CVPR 2022 · Table: Performances on Somethi
Video segmentation and tracking
25 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Something-Something V1 · accuracy (val)

14 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
156.5MLP-3D-L
CycleMLP-B5
MLP-3D: A MLP-Like 3D Architecture With Grouped Time Mixing
CVPR 2022 · Table: Comparisons with the st
Attention and transformers
255.1SSA ensemble
ResNet-50
SSAN: Separable Self-Attention Network for Video Representation Learning
CVPR 2021 · Table: Something-Something-V1
Action recognition
352.6MVFNet
ResNet-50, 16 frames, 3 crops, 2 clips
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
AAAI 2021 · Table: Performance and FLOPs c
Action recognition
452.6TSM RGB+Flow
ResNet-50
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge Devices
TPAMI 2020 · Table 2
Action recognition
552.5MUSLE
ResNet-50
Representing Videos As Discriminative Sub-Graphs for Action Recognition
CVPR 2021 · Table: comparison on Something
Knowledge and temporal graphs
652.5TEINet-En-RGB 16f+8f
ResNet-50
TEINet: Towards an Efficient Architecture for Video Recognition
AAAI 2020 · Table: comparison on Something
Action recognition
751.6R(2+1)D-152; IG-Kinetics; SE
R(2+1)D-152
Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition
CVPR 2019 · Something-V1 comparison table
Action recognition
851.4Adaptive structures search (Ours)
I3D-ResNet
Adaptive Interaction Modeling via Graph Operations Search
CVPR 2020 · Table 5
Knowledge and temporal graphs
949.9TSM+DyReg
TSM-ResNet50
Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks
NeurIPS 2021 · Table 1
Video segmentation and tracking
1049.2I3D + RSTG
3D ResNet-50
Recurrent Space-time Graph Neural Networks
NeurIPS 2019 · Table: Comparison with state-o
Knowledge and temporal graphs
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.