AI Paper Atlas

Research map / Benchmarks / Mini-Kinetics

Mini-Kinetics leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Mini-Kinetics. Best accuracy: 82.6 (OCSampler, CVPR 2022).

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.

Mini-Kinetics · accuracy

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

#accuracy ↑MethodPaperTopic
182.6OCSampler
SlowOnly-50
OCSampler: Compressing Videos to One Clip With Single-Step Sampling
CVPR 2022 · Table 1
Action recognition
280.7V4D ResNet50
ResNet50
V4D: 4D Convolutional Neural Networks for Video-level Representation Learning
ICLR 2020 · Table: Results on Mini-Kinetic
Action recognition
379.88ResNet-101 + 5 CGNL blocks
ResNet-101
Compact Generalized Non-local Network
NeurIPS 2018 · Main results table
Video segmentation and tracking
478.6SlowOnly-50 + RMS
SlowOnly-50
Regularization on Spatio-Temporally Smoothed Feature for Action Recognition
CVPR 2020 · Table 3
Action recognition
575.8Uni-AdaFocus (128^2) w/o sample-wise dynamic
MN2+RN
Uni-AdaFocus: Spatial-Temporal Dynamic Computation for Video Recognition
TPAMI 2024 · Table 1
Action recognition
675.4AdaFocusV2-MN2/RN (128²)
MobileNet-V2 + ResNet
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition
CVPR 2022 · Table 1
Video segmentation and tracking
775.4ResKD
ResNet-50
Rethinking Resolution in the Context of Efficient Video Recognition
NeurIPS 2022 · Table 1
Action recognition
875.3FrameExit (EfficientNet)
EfficientNet-b3
FrameExit: Conditional Early Exiting for Efficient Video Recognition
CVPR 2021 · Table 1
Action recognition
975.2Dynamic-STE
EfficientNet
Efficient Action Recognition via Dynamic Knowledge Propagation
ICCV 2021 · Table 2
Action recognition
1075AdaFocusV3 (matched to OCSampler GFLOPs)
MobileNet-V2 + ResNet-50
AdaFocusV3: On Unified Spatial-Temporal Dynamic Video Recognition
ECCV 2022 · Table 1
Action recognition
6 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.