SOTAVerified

Video Recognition

Video Recognition is a process of obtaining, processing, and analysing data that it receives from a visual source, specifically video.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 307 papers

TitleStatusHype
InternVideo2: Scaling Foundation Models for Multimodal Video UnderstandingCode7
Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal RepresentationsCode5
Expanding Language-Image Pretrained Models for General Video RecognitionCode3
Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video RecognitionCode2
TSM: Temporal Shift Module for Efficient and Scalable Video Understanding on Edge DeviceCode2
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT AdaptationCode2
X3D: Expanding Architectures for Efficient Video RecognitionCode2
Omni-sourced Webly-supervised Learning for Video RecognitionCode2
Video Swin TransformerCode2
AdaptFormer: Adapting Vision Transformers for Scalable Visual RecognitionCode2
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language ModelsCode2
Revisiting Classifier: Transferring Vision-Language Models for Video RecognitionCode2
DeMamba: AI-Generated Video Detection on Million-Scale GenVideo BenchmarkCode2
Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs?Code2
Adaptive Focus for Efficient Video RecognitionCode1
Depth Guided Adaptive Meta-Fusion Network for Few-shot Video RecognitionCode1
Adapting Short-Term Transformers for Action Detection in Untrimmed VideosCode1
Continual 3D Convolutional Neural Networks for Real-time Processing of VideosCode1
Deep Feature Flow for Video RecognitionCode1
DEVIAS: Learning Disentangled Video Representations of Action and SceneCode1
CatNet: Class Incremental 3D ConvNets for Lifelong Egocentric Gesture RecognitionCode1
AdaMML: Adaptive Multi-Modal Learning for Efficient Video RecognitionCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
Attacking Video Recognition Models with Bullet-Screen CommentsCode1
Building an Open-Vocabulary Video CLIP Model with Better Architectures, Optimization and DataCode1
Show:102550
← PrevPage 1 of 13Next →

No leaderboard results yet.