SOTAVerified

Activity Recognition In Videos

Papers

Showing 110 of 18 papers

TitleStatusHype
Dual-path Adaptation from Image to Video TransformersCode1
TorMentor: Deterministic dynamic-path, data augmentations with fractalsCode1
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Very Deep Convolutional Networks for Large-Scale Image RecognitionCode1
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in VideosCode0
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition0
ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos0
Long Term Object Detection and Tracking in Collaborative Learning Environments0
Human Interaction Recognition Framework based on Interacting Body Part Attention0
Bubblenet: A Disperse Recurrent Structure To Recognize Activities0
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1VTFSAAccuracy98.55Unverified