ML Research Wiki / Benchmarks / Human-Object Interaction Detection / V-COCO

V-COCO

Human-Object Interaction Detection Benchmark

Performance Over Time

📊 Showing 34 results | 📏 Metric: AP(S1)

Top Performing Models

Rank	Model	Paper	AP(S1)	Date	Code
1	RLIPv2	RLIPv2: Fast Scaling of Relational Language-Image Pre-training	72.10	2023-08-18	📦 jacobyuan7/rlipv2 📦 jacobyuan7/rlip 📦 jacobyuan7/ocn-hoi-benchmark
2	MUREN	Relational Context Learning for Human-Object Interaction Detection	68.80	2023-04-11	📦 OreoChocolate/MUREN
3	STIP	Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection	66.00	2022-06-13	📦 zyong812/stip
4	DiffHOI	Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model	65.70	2023-05-20	📦 IDEA-Research/DiffHOI
5	OCN (ResNet101)	Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics	65.30	2022-02-01	📦 jacobyuan7/ocn-hoi-benchmark
6	OCN (ResNet50)	Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics	64.20	2022-02-01	📦 jacobyuan7/ocn-hoi-benchmark
7	CDN (ResNet101)	Mining the Benefits of Two-stage and One-stage HOI Detection	63.91	2021-08-11	📦 YueLiao/CDN
8	HOICLIP	HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models	63.50	2023-03-28	📦 artanic30/hoiclip
9	QPIC + CPC	Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection	63.10	2022-04-11	📦 mlvlab/cpchoi
10	Body Part Interactiveness	Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection	63.00	2022-07-28	📦 enlighten0707/body-part-map-for-interactiveness

All Papers (34)

RLIPv2: Fast Scaling of Relational Language-Image Pre-training

2023

RLIPv2

jacobyuan7/rlipv2 jacobyuan7/rlip jacobyuan7/ocn-hoi-benchmark

Relational Context Learning for Human-Object Interaction Detection

2023

MUREN

OreoChocolate/MUREN

Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection

2022

STIP

zyong812/stip

Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model

2023

DiffHOI

IDEA-Research/DiffHOI

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

2022

OCN (ResNet101)

jacobyuan7/ocn-hoi-benchmark

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

2022

OCN (ResNet50)

jacobyuan7/ocn-hoi-benchmark

Mining the Benefits of Two-stage and One-stage HOI Detection

2021

CDN (ResNet101)

YueLiao/CDN

HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models

2023

HOICLIP

artanic30/hoiclip

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

2022

QPIC + CPC

mlvlab/cpchoi

Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

2022

Body Part Interactiveness

enlighten0707/body-part-map-for-interactiveness

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

2022

HOTR + CPC

mlvlab/cpchoi

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

2021

UPT-R101-DC5

fredzzhang/upt

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

2021

UPT-R101

fredzzhang/upt

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

2021

UPT-R50

fredzzhang/upt

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

2021

QPIC (ResNet50)

hitachi-rd-cv/qpic

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

2021

QPIC (ResNet101)

hitachi-rd-cv/qpic

DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection

2020

DIRV

MVIG-SJTU/DIRV

HOTR: End-to-End Human-Object Interaction Detection with Transformers

2021

HOTR

kakaobrain/HOTR

Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection

2021

GGNet

SherlockHolmes221/GGNet

Spatially Conditioned Graphs for Detecting Human-Object Interactions

2020

SCG

fredzzhang/spatially-conditioned-graphs fredzzhang/hicodet

Polysemy Deciphering Network for Robust Human-Object Interaction Detection

2020

PD-Net

MuchHair/PD-Net MuchHair/PD-Net-Extended-Version

HOI Analysis: Integrating and Decomposing Human-Object Interaction

2020

IDN

DirtyHarryLYL/HAKE-Action-Torch UCSB-VRL/GTNet

Detecting Human-Object Interactions with Action Co-occurrence Priors

2020

ACP

Dong-JinKim/ActionCooccurrencePriors

A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection

2022

SGCN4HOI

zhumanli/sgcn4hoi

Pose-based Modular Network for Human-Object Interaction Detection

2020

PMN

birlrobotics/PMN

VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions

2020

VSGNet

ASMIftekhar/VSGNet UCSB-VRL/GTNet

PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection

2019

PPDM

YueLiao/PPDM

DRG: Dual Relation Graph for Human-Object Interaction Detection

2020

DRG

vt-vl-lab/DRG

PaStaNet: Toward Human Activity Knowledge Engine

2020

PaStaNet

DirtyHarryLYL/HAKE-Action-Torch DirtyHarryLYL/HAKE

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

2021

TIN (TIPAMI)

DirtyHarryLYL/Transferable-Interactiveness-Network

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

2018

TIN (Interactiveness)

DirtyHarryLYL/Transferable-Interactiveness-Network zhihou7/FCL Imposingapple/Transferable_Interactiveness_Network_with_Partpair

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

2018

TIN (CVPR)

DirtyHarryLYL/Transferable-Interactiveness-Network zhihou7/FCL Imposingapple/Transferable_Interactiveness_Network_with_Partpair

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

2018

iCAN

vt-vl-lab/iCAN zhihou7/VCL

Learning Human-Object Interactions by Graph Parsing Neural Networks

2018

GPNN

SiyuanQi/gpnn

Model	Paper	AP(S1)	Date
RLIPv2	RLIPv2: Fast Scaling of Relational Language-Image…	72.10	2023-08-18
MUREN	Relational Context Learning for Human-Object Inte…	68.80	2023-04-11
STIP	Exploring Structure-aware Transformer over Intera…	66.00	2022-06-13
DiffHOI	Boosting Human-Object Interaction Detection with …	65.70	2023-05-20
OCN (ResNet101)	Detecting Human-Object Interactions with Object-G…	65.30	2022-02-01
OCN (ResNet50)	Detecting Human-Object Interactions with Object-G…	64.20	2022-02-01
CDN (ResNet101)	Mining the Benefits of Two-stage and One-stage HO…	63.91	2021-08-11
HOICLIP	HOICLIP: Efficient Knowledge Transfer for HOI Det…	63.50	2023-03-28
QPIC + CPC	Consistency Learning via Decoding Path Augmentati…	63.10	2022-04-11
Body Part Interactiveness	Mining Cross-Person Cues for Body-Part Interactiv…	63.00	2022-07-28
HOTR + CPC	Consistency Learning via Decoding Path Augmentati…	61.60	2022-04-11
UPT-R101-DC5	Efficient Two-Stage Detection of Human-Object Int…	61.30	2021-12-03
UPT-R101	Efficient Two-Stage Detection of Human-Object Int…	60.70	2021-12-03
UPT-R50	Efficient Two-Stage Detection of Human-Object Int…	59.00	2021-12-03
QPIC (ResNet50)	QPIC: Query-Based Pairwise Human-Object Interacti…	58.80	2021-03-09
QPIC (ResNet101)	QPIC: Query-Based Pairwise Human-Object Interacti…	58.30	2021-03-09
DIRV	DIRV: Dense Interaction Region Voting for End-to-…	56.10	2020-10-02
HOTR	HOTR: End-to-End Human-Object Interaction Detecti…	55.20	2021-04-28
GGNet	Glance and Gaze: Inferring Action-aware Points fo…	54.70	2021-04-12
SCG	Spatially Conditioned Graphs for Detecting Human-…	54.20	2020-12-11
PD-Net	Polysemy Deciphering Network for Robust Human-Obj…	53.34	2020-08-07
IDN	HOI Analysis: Integrating and Decomposing Human-O…	53.30	2020-10-30
ACP	Detecting Human-Object Interactions with Action C…	53.23
SGCN4HOI	A Skeleton-aware Graph Convolutional Network for …	53.10	2022-07-11
PMN	Pose-based Modular Network for Human-Object Inter…	51.80	2020-08-05
VSGNet	VSGNet: Spatial Attention Network for Detecting H…	51.76	2020-03-11
PPDM	PPDM: Parallel Point Detection and Matching for R…	51.10	2019-12-30
DRG	DRG: Dual Relation Graph for Human-Object Interac…	51.00	2020-08-26
PaStaNet	PaStaNet: Toward Human Activity Knowledge Engine	51.00	2020-04-02
TIN (TIPAMI)	Transferable Interactiveness Knowledge for Human-…	49.10	2021-01-25
TIN (Interactiveness)	Transferable Interactiveness Knowledge for Human-…	49.00	2018-11-20
TIN (CVPR)	Transferable Interactiveness Knowledge for Human-…	48.70	2018-11-20
iCAN	iCAN: Instance-Centric Attention Network for Huma…	44.70	2018-08-30
GPNN	Learning Human-Object Interactions by Graph Parsi…	44.00	2018-08-23

V-COCO

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (34)

RLIPv2: Fast Scaling of Relational Language-Image Pre-training

Relational Context Learning for Human-Object Interaction Detection

Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection

Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics

Mining the Benefits of Two-stage and One-stage HOI Detection

HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information

DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection

HOTR: End-to-End Human-Object Interaction Detection with Transformers

Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection

Spatially Conditioned Graphs for Detecting Human-Object Interactions

Polysemy Deciphering Network for Robust Human-Object Interaction Detection

HOI Analysis: Integrating and Decomposing Human-Object Interaction

Detecting Human-Object Interactions with Action Co-occurrence Priors

A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection

Pose-based Modular Network for Human-Object Interaction Detection

VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions

PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection

DRG: Dual Relation Graph for Human-Object Interaction Detection

PaStaNet: Toward Human Activity Knowledge Engine

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

Transferable Interactiveness Knowledge for Human-Object Interaction Detection

iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection

Learning Human-Object Interactions by Graph Parsing Neural Networks