AI Paper Atlas

Research map / Benchmarks / Kinetics-700

Kinetics-700 leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Kinetics-700. Best accuracy: 91.6 (MiCo (ViT-g), ICCV 2025).

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.

Kinetics-700 · accuracy

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

#accuracy ↑MethodPaperTopic
191.6MiCo (ViT-g)
ViT-g
Scaling Omni-modal Pretraining with Multimodal Context: Advancing Universal Representation Learning Across Modalities
ICCV 2025 · Table 3
Cross-modal learning
283.8TubeViT-L
ViT-L
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
CVPR 2023 · Table 3
Video segmentation and tracking
382.9EVA
ViT giant
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
CVPR 2023 · Video action recognition table
Open-set and few-shot detection
482.7UniFormerV2-L 336 (64 frames)
CLIP-ViT-L + K710
UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding
ICCV 2023 · Table 9
Video segmentation and tracking
582.2MTV-H (WTS)Multiview Transformers for Video Recognition
CVPR 2022 · Table 2(d)
Action recognition
680.4MaskFeat MViT-L↑312, 40×3
MViT-L
Masked Feature Prediction for Self-Supervised Visual Pre-Training
CVPR 2022 · Table: Comparison with previou
Video segmentation and tracking
779.4MViTv2-L, 312², 40×3MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
CVPR 2022 · Table 8
CNN features
876.3MultiTrain (312p)
MViTv2
Multi-dataset Training of Transformers for Robust Action Recognition
NeurIPS 2022 · Table 2
Action recognition
972.7VATTVATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
NeurIPS 2021 · text
Action recognition
1072.4Collaborative Memory (SlowFast-101+NL 8×8)
SlowFast-101+NL 8×8
Beyond Short Clips: End-to-End Video-Level Learning With Collaborative Memories
CVPR 2021 · Table: Comparison with the sta
Action recognition
3 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.