AI Paper Atlas

Research map / Benchmarks / Kinetics-600 zero-shot

Kinetics-600 zero-shot leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Kinetics-600 zero-shot. Best accuracy: 92.2 (ViFi-CLIP, 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.

Kinetics-600 zero-shot · accuracy

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

#accuracy ↑MethodPaperTopic
192.2ViFi-CLIP
CLIP ViT-B/16
Fine-Tuned CLIP Models Are Efficient Video Learners
CVPR 2023 · Zero-shot results table
Video-language understanding
281.2Open-VCLIP++
ViT-L/14
Building an Open-Vocabulary Video CLIP Model With Better Architectures, Optimization and Data
TPAMI 2024 · Table 3
Action recognition
378.4MoTE
ViT-L/14
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
NeurIPS 2024 · Zero-shot video recognition ta
Video-language understanding
476.8IMP-MoE-LAlternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
NeurIPS 2023 · Table 1
Cross-modal learning
576.5XOV-ActionXOV-Action: Toward Generalizable Open-Vocabulary Action Recognition
TPAMI 2026 · Table 4
Action recognition
675.1OST (32 frames)
CLIP ViT-B/16
OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
CVPR 2024 · Table 1
Action recognition
774.9ALT-L/14
CLIP ViT-L/14
Align Before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
CVPR 2024 · Table 3
Action recognition
874.5+ MSTA + LCC
ViCLIP
Efficient Transfer Learning for Video-language Foundation Models
CVPR 2025 · Table 4
Video-language understanding
972.1ViCLIP + CONDA
ViCLIP ViT-B/16
Condensed Test-Time Adaptation of VLMs for Action Recognition
CVPR 2026 · Table 1
CLIP and zero-shot
1071.3LLaVA-Prime-ViT-g
ViT-g
Learning Beyond Still Frames: Scaling Vision-Language Models with Video
ICCV 2025 · Table 5
Video-language understanding
1 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.