Human-Object Interaction Detection

Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i.e., humans) and target (i.e., objects) of interaction, and ii) the classification of the interaction labels.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 141–150 of 449 papers

Title	Date	Tasks	Status
Generating Human Interaction Motions in Scenes with Text Control	Apr 16, 2024	DenoisingHuman-Object Interaction Detection	—Unverified
Effective Actor-centric Human-object Interaction Detection	Feb 24, 2022	Human-Object Interaction DetectionObject	—Unverified
Beyond Holistic Object Recognition: Enriching Image Understanding with Part States	Dec 15, 2016	Human-Object Interaction DetectionImage Captioning	—Unverified
Dynamic Scene Understanding from Vision-Language Representations	Jan 20, 2025	Grounded Situation RecognitionHuman-Human Interaction Recognition	—Unverified
Compositional Learning in Transformer-Based Human-Object Interaction Detection	Aug 11, 2023	Human-Object Interaction DetectionObject	—Unverified
An analysis of HOI: using a training-free method with multimodal visual foundation models when only the test set is available, without the training set	Aug 11, 2024	Human-Object Interaction Detection	—Unverified
Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videos	Jun 3, 2025	Graph LearningGraph Neural Network	—Unverified
DropKey for Vision Transformer	Jan 1, 2023	Human-Object Interaction Detectionimage-classification	—Unverified
DropKey	Aug 4, 2022	Human-Object Interaction Detectionimage-classification	—Unverified
Compositional Learning for Human Object Interaction	Sep 1, 2018	Human-Object Interaction DetectionObject	—Unverified

Show:10 25 50

← PrevPage 15 of 45Next →

All datasets HICO-DET V-COCO HICO VidHOI Ambiguious-HOI MECCANO

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Ours (PViC+)	mAP	46.49	—	Unverified
2	RLIPv2 (Swin-L)	mAP	45.09	—	Unverified
3	PViC-SwinL	mAP	44.32	—	Unverified
4	SOV-STG (Swin-L)	mAP	43.35	—	Unverified
5	DiffHOI	mAP	41.5	—	Unverified
6	ViPLO	mAP	37.22	—	Unverified
7	FGAHOI	mAP	37.18	—	Unverified
8	ERNet	mAP	36.89	—	Unverified
9	CQL+GEN-VLKT-L	mAP	36.03	—	Unverified
10	QAHOI (Swin-L)	mAP	35.78	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RLIPv2	AP(S1)	72.1	—	Unverified
2	MUREN	AP(S1)	68.8	—	Unverified
3	STIP	AP(S1)	66	—	Unverified
4	DiffHOI	AP(S1)	65.7	—	Unverified
5	OCN (ResNet101)	AP(S1)	65.3	—	Unverified
6	OCN (ResNet50)	AP(S1)	64.2	—	Unverified
7	CDN (ResNet101)	AP(S1)	63.91	—	Unverified
8	HOICLIP	AP(S1)	63.5	—	Unverified
9	QPIC + CPC	MAP	63.1	—	Unverified
10	Body Part Interactiveness	AP(S1)	63	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DEFR	mAP	65.6	—	Unverified
2	HAKE	mAP	47.1	—	Unverified
3	PaStaNet	mAP	46.3	—	Unverified
4	RelViT	mAP	43.98	—	Unverified
5	Pairwise-Part	mAP	39.9	—	Unverified
6	Mallya & Lazebnik	mAP	36.1	—	Unverified
7	Girdhar & Ramanan	mAP	34.6	—	Unverified
8	R*CNN	mAP	28.5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	HOI4ABOT	Detection: Full (mAP@0.5)	11.12	—	Unverified
2	ST-GAZE	Detection: Full (mAP@0.5)	10.4	—	Unverified
3	STTRAN	Detection: Full (mAP@0.5)	7.61	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DJ-RN	mAP	10.37	—	Unverified
2	iCAN	mAP	8.14	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SlowFast + FasterRCNN	mAP@0.5 role	25.93	—	Unverified