TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Human-Object Interaction Detection/HICO-DET

Human-Object Interaction Detection on HICO-DET

Metric: mAP (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mAP▼Extra DataPaperDate↕Code
1Ours (PViC+)46.49NoDynamic Scene Understanding from Vision-Language...2025-01-20-
2RLIPv2 (Swin-L)45.09YesRLIPv2: Fast Scaling of Relational Language-Imag...2023-08-18Code
3PViC-SwinL44.32NoExploring Predicate Visual Context in Detecting ...2023-08-11Code
4SOV-STG (Swin-L)43.35NoFocusing on what to decode and what to train: SO...2023-07-05Code
5DiffHOI41.5YesBoosting Human-Object Interaction Detection with...2023-05-20Code
6ViPLO37.22NoViPLO: Vision Transformer based Pose-Conditioned...2023-04-17Code
7FGAHOI37.18NoFGAHOI: Fine-Grained Anchors for Human-Object In...2023-01-08Code
8ERNet36.89No--Code
9CQL+GEN-VLKT-L36.03NoCategory Query Learning for Human-Object Interac...2023-03-24Code
10QAHOI (Swin-L)35.78NoQAHOI: Query-Based Anchors for Human-Object Inte...2021-12-16Code
11CQL+GEN-VLKT-B35.36NoCategory Query Learning for Human-Object Interac...2023-03-24Code
12Body Part Interactiveness35.15NoMining Cross-Person Cues for Body-Part Interacti...2022-07-28Code
13GEN-VLKT-R10134.95NoGEN-VLKT: Simplify Association and Enhance Inter...2022-03-26Code
14HOIGen34.84NoUnseen No More: Unlocking the Potential of CLIP ...2024-08-12Code
15PViC-R5034.69NoExploring Predicate Visual Context in Detecting ...2023-08-11Code
16HOICLIP34.69NoHOICLIP: Efficient Knowledge Transfer for HOI De...2023-03-28Code
17MUREN32.87NoRelational Context Learning for Human-Object Int...2023-04-11Code
18RLIP-ParSe (ResNet-50)32.84NoRLIP: Relational Language-Image Pre-training for...2022-09-05Code
19ParSe (ResNet-101)32.76NoRLIP: Relational Language-Image Pre-training for...2022-09-05Code
20UPT-R101-DC532.62NoEfficient Two-Stage Detection of Human-Object In...2021-12-03Code
21DEFR32.35NoThe Overlooked Classifier in Human-Object Intera...2021-12-13-
22UPT-R10132.31NoEfficient Two-Stage Detection of Human-Object In...2021-12-03Code
23STIP (ResNet-50)32.22NoExploring Structure-aware Transformer over Inter...2022-06-13Code
24CDN (ResNet101)32.07NoMining the Benefits of Two-stage and One-stage H...2021-08-11Code
25UPT-R5031.66NoEfficient Two-Stage Detection of Human-Object In...2021-12-03Code
26OCN (ResNet101)31.43NoDetecting Human-Object Interactions with Object-...2022-02-01Code
27QPIC (ResNet101)29.9YesQPIC: Query-Based Pairwise Human-Object Interact...2021-03-09Code
28QPIC + CPC29.63NoConsistency Learning via Decoding Path Augmentat...2022-04-11Code
29SCG (DETR-R101)29.26NoSpatially Conditioned Graphs for Detecting Human...2020-12-11Code
30QPIC (ResNet50)29.07YesQPIC: Query-Based Pairwise Human-Object Interact...2021-03-09Code
31AS-Net (ResNet50)28.87YesReformulating HOI Detection as Adaptive Set Pred...2021-03-10Code
32HOITrans(ResNet101)26.61YesEnd-to-End Human Object Interaction Detection wi...2021-03-08Code
33IDN (finetuned detector)26.29YesHOI Analysis: Integrating and Decomposing Human-...2020-10-30Code
34HOTR + CPC26.16NoConsistency Learning via Decoding Path Augmentat...2022-04-11Code
35ConsNet-F (ResNet-50)25.94YesConsNet: Learning Consistency Graph for Zero-Sho...2020-08-14Code
36DRG24.53NoDRG: Dual Relation Graph for Human-Object Intera...2020-08-26Code
37HOITrans(ResNet50)23.46YesEnd-to-End Human Object Interaction Detection wi...2021-03-08Code
38HOTR23.46NoHOTR: End-to-End Human-Object Interaction Detect...2021-04-28Code
39IDN (COCO detector)23.36NoHOI Analysis: Integrating and Decomposing Human-...2020-10-30Code
40PaStaNet22.65NoPaStaNet: Toward Human Activity Knowledge Engine2020-04-02Code
41PD-Net22.37NoPolysemy Deciphering Network for Robust Human-Ob...2020-08-07Code
42ConsNet (ResNet-50)22.15NoConsNet: Learning Consistency Graph for Zero-Sho...2020-08-14Code
43ACP++22.11NoACP++: Action Co-occurrence Priors for Human-Obj...2021-09-09Code
44PPDM21.92NoPPDM: Parallel Point Detection and Matching for ...2019-12-30Code
45DIRV21.81NoDIRV: Dense Interaction Region Voting for End-to...2020-10-02Code
46DJ-RN21.34NoDetailed 2D-3D Joint Representation for Human-Ob...2020-04-17Code
47PMN21.21NoPose-based Modular Network for Human-Object Inte...2020-08-05Code
48TIN (TIPAMI)20.93NoTransferable Interactiveness Knowledge for Human...2021-01-25Code
49ACP20.59No--Code
50VSGNet19.8NoVSGNet: Spatial Attention Network for Detecting ...2020-03-11Code
51TIN (Interactiveness)17.54NoTransferable Interactiveness Knowledge for Human...2018-11-20Code
52TIN (CVPR)17.22NoTransferable Interactiveness Knowledge for Human...2018-11-20Code
53iCAN14.84NoiCAN: Instance-Centric Attention Network for Hum...2018-08-30Code
54GPNN13.11NoLearning Human-Object Interactions by Graph Pars...2018-08-23Code
55InteractNet9.94NoDetecting and Recognizing Human-Object Interacti...2017-04-24Code