Kinetics
Canonical18papers using it
139HF downloads
1HF likes
2017first seen
π€ Hugging Faceβ cc-by-4.0
Papers using Kinetics (18)
- Few-shot Video Classification Via Temporal AlignmentTemporal-relational Crosstransformers For Few-shot Action RecognitionCo-training Transformer With Videos And Images Improves Action RecognitionMViTv2: Improved Multiscale Vision Transformers for Classification and
DetectionMvitv2: Improved Multiscale Vision Transformers For Classification And DetectionMotion-guided Masking For Spatiotemporal Representation LearningAttend And Interact: Higher-order Object Interactions For Video UnderstandingSample Less, Learn More: Efficient Action Recognition Via Frame Feature RestorationSkeleton-ood: An End-to-end Skeleton-based Model For Robust Out-of-distribution Human Action DetectionVideolightformer: Lightweight Action Recognition Using TransformersOn The Surprising Effectiveness Of Transformers In Low-labeled Video RecognitionTracking by Predicting 3-D Gaussians Over TimeInsights from Visual Cognition: Understanding Human Action Dynamics with Overall Glance and Refined Gaze TransformerSmooth Regularization For Efficient Video RecognitionSVT: Supertoken Video Transformer For Efficient Video UnderstandingVote&mix: Plug-and-play Token Reduction For Efficient Vision TransformerVideo Transformer NetworkViViT: A Video Vision Transformer