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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 22 papers

Title	Date	Tasks	Status
OV-HHIR: Open Vocabulary Human Interaction Recognition Using Cross-modal Integration of Large Language Models	Dec 31, 2024	Activity RecognitionHuman Interaction Recognition	—Unverified
SkeleTR: Towards Skeleton-based Action Recognition in the Wild	Jan 1, 2023	Action ClassificationAction Detection	—Unverified
WiFi-TCN: Temporal Convolution for Human Interaction Recognition based on WiFi signal	May 21, 2023	Activity RecognitionHuman Activity Recognition	—Unverified
Three-Stream Fusion Network for First-Person Interaction Recognition	Feb 19, 2020	Activity RecognitionHuman Interaction Recognition	—Unverified
IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition	Jul 25, 2022	Human Interaction Recognition	—Unverified
A Two-stream Hybrid CNN-Transformer Network for Skeleton-based Human Interaction Recognition	Dec 31, 2023	Human Interaction RecognitionSpecificity	—Unverified
Deep Convolutional Poses for Human Interaction Recognition in Monocular Videos	Dec 13, 2016	Human Interaction RecognitionPose Estimation	—Unverified
Dynamic Scene Understanding from Vision-Language Representations	Jan 20, 2025	Grounded Situation RecognitionHuman-Human Interaction Recognition	—Unverified
Exploring Vision Transformers for 3D Human Motion-Language Models with Motion Patches	May 8, 2024	Human Interaction RecognitionTransfer Learning	—Unverified
Facial Descriptors for Human Interaction Recognition In Still Images	Sep 17, 2015	Human Interaction Recognition	—Unverified

Show:10 25 50

← PrevPage 2 of 3Next →

All datasets NTU RGB+D 120 NTU RGB+D UT BIT EPIC-SOUNDS SBU SBU / SBU-Refine UT-Interaction

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SkateFormer	Accuracy (Cross-Setup)	93.2	—	Unverified
2	CHASE(CTR-GCN)	Accuracy (Cross-Setup)	92.3	—	Unverified
3	ISTA-Net	Accuracy (Cross-Setup)	91.7	—	Unverified
4	SkeleTR	Accuracy (Cross-Setup)	88.3	—	Unverified
5	IGFormer	Accuracy (Cross-Setup)	86.5	—	Unverified
6	LSTM-IRN	Accuracy (Cross-Setup)	79.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SkateFormer	Accuracy (Cross-Subject)	97.1	—	Unverified
2	CHASE(CTR-GCN)	Accuracy (Cross-Subject)	96.5	—	Unverified
3	SkeleTR	Accuracy (Cross-Subject)	94.9	—	Unverified
4	IGFormer	Accuracy (Cross-Subject)	93.6	—	Unverified
5	LSTM-IRN'fc1inter+intra	Accuracy (Cross-Subject)	90.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	H-LSTCM	Accuracy	98.33	—	Unverified
2	Co-LSTSM	Accuracy	95	—	Unverified
3	Raptis et al.	Accuracy	93.3	—	Unverified
4	Donahue et al.	Accuracy	85	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	H-LSTCM	Accuracy	94.03	—	Unverified
2	Co-LSTSM	Accuracy	92.88	—	Unverified
3	Donahue et al.	Accuracy	80.13	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Slow-Fast(Finetune by Fivewin team)	Top-1 accuracy %	55.11	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LSTM-IRN'fc1inter+intra	Accuracy	98.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	IGFormer	Accuracy	98.4	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LSTM-IRN'fc1inter+intra	Accuracy (Set 1)	98.3	—	Unverified