SOTAVerified

Activity Recognition In Videos

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–18 of 18 papers

TitleStatusHype
ActNetFormer: Transformer-ResNet Hybrid Method for Semi-Supervised Action Recognition in VideosCode0
Dual-path Adaptation from Image to Video TransformersCode1
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition—0
ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos—0
TorMentor: Deterministic dynamic-path, data augmentations with fractalsCode1
Long Term Object Detection and Tracking in Collaborative Learning Environments—0
Human Interaction Recognition Framework based on Interacting Body Part Attention—0
Bubblenet: A Disperse Recurrent Structure To Recognize Activities—0
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction—0
Large-scale weakly-supervised pre-training for video action recognitionCode0
Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos—0
Representation Flow for Action RecognitionCode0
Learning Latent Sub-events in Activity Videos Using Temporal Attention FiltersCode0
Action Recognition with Trajectory-Pooled Deep-Convolutional DescriptorsCode0
A new network-based algorithm for human activity recognition in video—0
Pooled Motion Features for First-Person VideosCode0
Very Deep Convolutional Networks for Large-Scale Image RecognitionCode1
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1VTFSAAccuracy98.55—Unverified