Human-Object Interaction Detection on HICO-DET

Metric: mAP (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	mAP▼	Extra Data	Paper	Date↕	Code
1	Ours (PViC+)	46.49	No	Dynamic Scene Understanding from Vision-Language...	2025-01-20	-
2	RLIPv2 (Swin-L)	45.09	Yes	RLIPv2: Fast Scaling of Relational Language-Imag...	2023-08-18	Code
3	PViC-SwinL	44.32	No	Exploring Predicate Visual Context in Detecting ...	2023-08-11	Code
4	SOV-STG (Swin-L)	43.35	No	Focusing on what to decode and what to train: SO...	2023-07-05	Code
5	DiffHOI	41.5	Yes	Boosting Human-Object Interaction Detection with...	2023-05-20	Code
6	ViPLO	37.22	No	ViPLO: Vision Transformer based Pose-Conditioned...	2023-04-17	Code
7	FGAHOI	37.18	No	FGAHOI: Fine-Grained Anchors for Human-Object In...	2023-01-08	Code
8	ERNet	36.89	No	-	-	Code
9	CQL+GEN-VLKT-L	36.03	No	Category Query Learning for Human-Object Interac...	2023-03-24	Code
10	QAHOI (Swin-L)	35.78	No	QAHOI: Query-Based Anchors for Human-Object Inte...	2021-12-16	Code
11	CQL+GEN-VLKT-B	35.36	No	Category Query Learning for Human-Object Interac...	2023-03-24	Code
12	Body Part Interactiveness	35.15	No	Mining Cross-Person Cues for Body-Part Interacti...	2022-07-28	Code
13	GEN-VLKT-R101	34.95	No	GEN-VLKT: Simplify Association and Enhance Inter...	2022-03-26	Code
14	HOIGen	34.84	No	Unseen No More: Unlocking the Potential of CLIP ...	2024-08-12	Code
15	PViC-R50	34.69	No	Exploring Predicate Visual Context in Detecting ...	2023-08-11	Code
16	HOICLIP	34.69	No	HOICLIP: Efficient Knowledge Transfer for HOI De...	2023-03-28	Code
17	MUREN	32.87	No	Relational Context Learning for Human-Object Int...	2023-04-11	Code
18	RLIP-ParSe (ResNet-50)	32.84	No	RLIP: Relational Language-Image Pre-training for...	2022-09-05	Code
19	ParSe (ResNet-101)	32.76	No	RLIP: Relational Language-Image Pre-training for...	2022-09-05	Code
20	UPT-R101-DC5	32.62	No	Efficient Two-Stage Detection of Human-Object In...	2021-12-03	Code
21	DEFR	32.35	No	The Overlooked Classifier in Human-Object Intera...	2021-12-13	-
22	UPT-R101	32.31	No	Efficient Two-Stage Detection of Human-Object In...	2021-12-03	Code
23	STIP (ResNet-50)	32.22	No	Exploring Structure-aware Transformer over Inter...	2022-06-13	Code
24	CDN (ResNet101)	32.07	No	Mining the Benefits of Two-stage and One-stage H...	2021-08-11	Code
25	UPT-R50	31.66	No	Efficient Two-Stage Detection of Human-Object In...	2021-12-03	Code
26	OCN (ResNet101)	31.43	No	Detecting Human-Object Interactions with Object-...	2022-02-01	Code
27	QPIC (ResNet101)	29.9	Yes	QPIC: Query-Based Pairwise Human-Object Interact...	2021-03-09	Code
28	QPIC + CPC	29.63	No	Consistency Learning via Decoding Path Augmentat...	2022-04-11	Code
29	SCG (DETR-R101)	29.26	No	Spatially Conditioned Graphs for Detecting Human...	2020-12-11	Code
30	QPIC (ResNet50)	29.07	Yes	QPIC: Query-Based Pairwise Human-Object Interact...	2021-03-09	Code
31	AS-Net (ResNet50)	28.87	Yes	Reformulating HOI Detection as Adaptive Set Pred...	2021-03-10	Code
32	HOITrans(ResNet101)	26.61	Yes	End-to-End Human Object Interaction Detection wi...	2021-03-08	Code
33	IDN (finetuned detector)	26.29	Yes	HOI Analysis: Integrating and Decomposing Human-...	2020-10-30	Code
34	HOTR + CPC	26.16	No	Consistency Learning via Decoding Path Augmentat...	2022-04-11	Code
35	ConsNet-F (ResNet-50)	25.94	Yes	ConsNet: Learning Consistency Graph for Zero-Sho...	2020-08-14	Code
36	DRG	24.53	No	DRG: Dual Relation Graph for Human-Object Intera...	2020-08-26	Code
37	HOITrans(ResNet50)	23.46	Yes	End-to-End Human Object Interaction Detection wi...	2021-03-08	Code
38	HOTR	23.46	No	HOTR: End-to-End Human-Object Interaction Detect...	2021-04-28	Code
39	IDN (COCO detector)	23.36	No	HOI Analysis: Integrating and Decomposing Human-...	2020-10-30	Code
40	PaStaNet	22.65	No	PaStaNet: Toward Human Activity Knowledge Engine	2020-04-02	Code
41	PD-Net	22.37	No	Polysemy Deciphering Network for Robust Human-Ob...	2020-08-07	Code
42	ConsNet (ResNet-50)	22.15	No	ConsNet: Learning Consistency Graph for Zero-Sho...	2020-08-14	Code
43	ACP++	22.11	No	ACP++: Action Co-occurrence Priors for Human-Obj...	2021-09-09	Code
44	PPDM	21.92	No	PPDM: Parallel Point Detection and Matching for ...	2019-12-30	Code
45	DIRV	21.81	No	DIRV: Dense Interaction Region Voting for End-to...	2020-10-02	Code
46	DJ-RN	21.34	No	Detailed 2D-3D Joint Representation for Human-Ob...	2020-04-17	Code
47	PMN	21.21	No	Pose-based Modular Network for Human-Object Inte...	2020-08-05	Code
48	TIN (TIPAMI)	20.93	No	Transferable Interactiveness Knowledge for Human...	2021-01-25	Code
49	ACP	20.59	No	-	-	Code
50	VSGNet	19.8	No	VSGNet: Spatial Attention Network for Detecting ...	2020-03-11	Code
51	TIN (Interactiveness)	17.54	No	Transferable Interactiveness Knowledge for Human...	2018-11-20	Code
52	TIN (CVPR)	17.22	No	Transferable Interactiveness Knowledge for Human...	2018-11-20	Code
53	iCAN	14.84	No	iCAN: Instance-Centric Attention Network for Hum...	2018-08-30	Code
54	GPNN	13.11	No	Learning Human-Object Interactions by Graph Pars...	2018-08-23	Code
55	InteractNet	9.94	No	Detecting and Recognizing Human-Object Interacti...	2017-04-24	Code

#1Ours (PViC+)SOTA
46.49
mAP· 2025-01-20
Dynamic Scene Understanding from Vision-Language Representations
#2RLIPv2 (Swin-L)SOTA
45.09
mAP· Extra Data· 2023-08-18
RLIPv2: Fast Scaling of Relational Language-Image Pre-training Code
#3PViC-SwinLSOTA
44.32
mAP· 2023-08-11
Exploring Predicate Visual Context in Detecting Human-Object Interactions Code
#4SOV-STG (Swin-L)SOTA
43.35
mAP· 2023-07-05
Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor Code
#5DiffHOISOTA
41.5
mAP· Extra Data· 2023-05-20
Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model Code
#6ViPLOSOTA
37.22
mAP· 2023-04-17
ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection Code
#7FGAHOISOTA
37.18
mAP· 2023-01-08
FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection Code
#8ERNet
36.89
mAP
No paperCode
#9CQL+GEN-VLKT-L
36.03
mAP· 2023-03-24
Category Query Learning for Human-Object Interaction Classification Code
#10QAHOI (Swin-L)SOTA
35.78
mAP· 2021-12-16
QAHOI: Query-Based Anchors for Human-Object Interaction Detection Code
#11CQL+GEN-VLKT-B
35.36
mAP· 2023-03-24
Category Query Learning for Human-Object Interaction Classification Code
#12Body Part Interactiveness
35.15
mAP· 2022-07-28
Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection Code
#13GEN-VLKT-R101
34.95
mAP· 2022-03-26
GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection Code
#14HOIGen
34.84
mAP· 2024-08-12
Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection Code
#15PViC-R50
34.69
mAP· 2023-08-11
Exploring Predicate Visual Context in Detecting Human-Object Interactions Code
#16HOICLIP
34.69
mAP· 2023-03-28
HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models Code
#17MUREN
32.87
mAP· 2023-04-11
Relational Context Learning for Human-Object Interaction Detection Code
#18RLIP-ParSe (ResNet-50)
32.84
mAP· 2022-09-05
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection Code
#19ParSe (ResNet-101)
32.76
mAP· 2022-09-05
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection Code
#20UPT-R101-DC5SOTA
32.62
mAP· 2021-12-03
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer Code
#21DEFR
32.35
mAP· 2021-12-13
The Overlooked Classifier in Human-Object Interaction Recognition
#22UPT-R101
32.31
mAP· 2021-12-03
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer Code
#23STIP (ResNet-50)
32.22
mAP· 2022-06-13
Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection Code
#24CDN (ResNet101)SOTA
32.07
mAP· 2021-08-11
Mining the Benefits of Two-stage and One-stage HOI Detection Code
#25UPT-R50
31.66
mAP· 2021-12-03
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer Code
#26OCN (ResNet101)
31.43
mAP· 2022-02-01
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics Code
#27QPIC (ResNet101)SOTA
29.9
mAP· Extra Data· 2021-03-09
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information Code
#28QPIC + CPC
29.63
mAP· 2022-04-11
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection Code
#29SCG (DETR-R101)SOTA
29.26
mAP· 2020-12-11
Spatially Conditioned Graphs for Detecting Human-Object Interactions Code
#30QPIC (ResNet50)
29.07
mAP· Extra Data· 2021-03-09
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information Code
#31AS-Net (ResNet50)
28.87
mAP· Extra Data· 2021-03-10
Reformulating HOI Detection as Adaptive Set Prediction Code
#32HOITrans(ResNet101)
26.61
mAP· Extra Data· 2021-03-08
End-to-End Human Object Interaction Detection with HOI Transformer Code
#33IDN (finetuned detector)SOTA
26.29
mAP· Extra Data· 2020-10-30
HOI Analysis: Integrating and Decomposing Human-Object Interaction Code
#34HOTR + CPC
26.16
mAP· 2022-04-11
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection Code
#35ConsNet-F (ResNet-50)SOTA
25.94
mAP· Extra Data· 2020-08-14
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection Code
#36DRG
24.53
mAP· 2020-08-26
DRG: Dual Relation Graph for Human-Object Interaction Detection Code
#37HOITrans(ResNet50)
23.46
mAP· Extra Data· 2021-03-08
End-to-End Human Object Interaction Detection with HOI Transformer Code
#38HOTR
23.46
mAP· 2021-04-28
HOTR: End-to-End Human-Object Interaction Detection with Transformers Code
#39IDN (COCO detector)
23.36
mAP· 2020-10-30
HOI Analysis: Integrating and Decomposing Human-Object Interaction Code
#40PaStaNetSOTA
22.65
mAP· 2020-04-02
PaStaNet: Toward Human Activity Knowledge Engine Code
#41PD-Net
22.37
mAP· 2020-08-07
Polysemy Deciphering Network for Robust Human-Object Interaction Detection Code
#42ConsNet (ResNet-50)
22.15
mAP· 2020-08-14
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection Code
#43ACP++
22.11
mAP· 2021-09-09
ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection Code
#44PPDMSOTA
21.92
mAP· 2019-12-30
PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection Code
#45DIRV
21.81
mAP· 2020-10-02
DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection Code
#46DJ-RN
21.34
mAP· 2020-04-17
Detailed 2D-3D Joint Representation for Human-Object Interaction Code
#47PMN
21.21
mAP· 2020-08-05
Pose-based Modular Network for Human-Object Interaction Detection Code
#48TIN (TIPAMI)
20.93
mAP· 2021-01-25
Transferable Interactiveness Knowledge for Human-Object Interaction Detection Code
#49ACP
20.59
mAP
No paperCode
#50VSGNet
19.8
mAP· 2020-03-11
VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions Code
#51TIN (Interactiveness)SOTA
17.54
mAP· 2018-11-20
Transferable Interactiveness Knowledge for Human-Object Interaction Detection Code
#52TIN (CVPR)
17.22
mAP· 2018-11-20
Transferable Interactiveness Knowledge for Human-Object Interaction Detection Code
#53iCANSOTA
14.84
mAP· 2018-08-30
iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection Code
#54GPNNSOTA
13.11
mAP· 2018-08-23
Learning Human-Object Interactions by Graph Parsing Neural Networks Code
#55InteractNetSOTA
9.94
mAP· 2017-04-24
Detecting and Recognizing Human-Object Interactions Code