SOTAVerified

Human Interaction Recognition

Human Interaction Recognition (HIR) is a field of study that involves the development of computer algorithms to detect and recognize human interactions in videos, images, or other multimedia content. The goal of HIR is to automatically identify and analyze the social interactions between people, their body language, and facial expressions.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 22 papers

TitleStatusHype
Dynamic Scene Understanding from Vision-Language Representations—0
OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models—0
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action RecognitionCode1
Empathic Grounding: Explorations using Multimodal Interaction and Large Language Models with Conversational AgentsCode0
Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches—0
SkateFormer: Skeletal-Temporal Transformer for Human Action RecognitionCode2
Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction RecognitionCode0
A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition—0
Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action RecognitionCode1
Human-to-Human Interaction Detection—0
Show:102550
← PrevPage 1 of 3Next →
All datasetsNTU RGB+D 120NTU RGB+DUTBITEPIC-SOUNDSSBUSBU / SBU-RefineUT-Interaction

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SkateFormerAccuracy (Cross-Subject)97.1—Unverified
2CHASE(CTR-GCN)Accuracy (Cross-Subject)96.5—Unverified
3SkeleTRAccuracy (Cross-Subject)94.9—Unverified
4IGFormerAccuracy (Cross-Subject)93.6—Unverified
5LSTM-IRN'fc1inter+intraAccuracy (Cross-Subject)90.5—Unverified