OpenCodePapers

human-object-interaction-detection-on-hico

Human-Object Interaction Detection
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodemAPTime Per Frame (ms)Detection: Full (mAP@0.5)Detection: Non-Rare (mAP@0.5)Detection: Rare (mAP@0.5)ModelNameReleaseDate
Dynamic Scene Understanding from Vision-Language Representations46.49Ours (PViC+)2025-01-20
RLIPv2: Fast Scaling of Relational Language-Image Pre-training✓ Link45.09RLIPv2 (Swin-L)2023-08-18
Exploring Predicate Visual Context in Detecting Human-Object Interactions✓ Link44.32PViC-SwinL2023-08-11
Focusing on what to decode and what to train: SOV Decoding with Specific Target Guided DeNoising and Vision Language Advisor✓ Link43.35SOV-STG (Swin-L)2023-07-05
Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model✓ Link41.50DiffHOI2023-05-20
ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection✓ Link37.22ViPLO2023-04-17
FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection✓ Link37.18FGAHOI2023-01-08
ERNet: Efficient and Reliable Human-Object Interaction Detection✓ Link36.89ERNet2023-01-26
Category Query Learning for Human-Object Interaction Classification✓ Link36.03CQL+GEN-VLKT-L2023-03-24
QAHOI: Query-Based Anchors for Human-Object Interaction Detection✓ Link35.78QAHOI (Swin-L)2021-12-16
Category Query Learning for Human-Object Interaction Classification✓ Link35.36CQL+GEN-VLKT-B2023-03-24
Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection✓ Link35.15Body Part Interactiveness2022-07-28
GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection✓ Link34.95GEN-VLKT-R1012022-03-26
Unseen No More: Unlocking the Potential of CLIP for Generative Zero-shot HOI Detection✓ Link34.8434.8434.9434.52HOIGen2024-08-12
Exploring Predicate Visual Context in Detecting Human-Object Interactions✓ Link34.69PViC-R502023-08-11
HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models✓ Link34.69HOICLIP2023-03-28
Relational Context Learning for Human-Object Interaction Detection✓ Link32.87MUREN2023-04-11
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection✓ Link32.84RLIP-ParSe (ResNet-50)2022-09-05
RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection✓ Link32.76ParSe (ResNet-101)2022-09-05
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer✓ Link32.62124UPT-R101-DC52021-12-03
The Overlooked Classifier in Human-Object Interaction Recognition32.35DEFR2021-12-13
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer✓ Link32.3161UPT-R1012021-12-03
Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection✓ Link32.2274STIP (ResNet-50)2022-06-13
Mining the Benefits of Two-stage and One-stage HOI Detection✓ Link32.07CDN (ResNet101)2021-08-11
Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer✓ Link31.6642UPT-R502021-12-03
Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics✓ Link31.43OCN (ResNet101)2022-02-01
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information✓ Link29.9063QPIC (ResNet101)2021-03-09
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection✓ Link29.63QPIC + CPC2022-04-11
Spatially Conditioned Graphs for Detecting Human-Object Interactions✓ Link29.26SCG (DETR-R101)2020-12-11
QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information✓ Link29.0746QPIC (ResNet50)2021-03-09
Reformulating HOI Detection as Adaptive Set Prediction✓ Link28.8771AS-Net (ResNet50)2021-03-10
End-to-End Human Object Interaction Detection with HOI Transformer✓ Link26.61HOITrans(ResNet101)2021-03-08
HOI Analysis: Integrating and Decomposing Human-Object Interaction✓ Link26.29IDN (finetuned detector)2020-10-30
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection✓ Link26.16HOTR + CPC2022-04-11
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection✓ Link25.94ConsNet-F (ResNet-50)2020-08-14
DRG: Dual Relation Graph for Human-Object Interaction Detection✓ Link24.53DRG2020-08-26
End-to-End Human Object Interaction Detection with HOI Transformer✓ Link23.46HOITrans(ResNet50)2021-03-08
HOTR: End-to-End Human-Object Interaction Detection with Transformers✓ Link23.46HOTR2021-04-28
HOI Analysis: Integrating and Decomposing Human-Object Interaction✓ Link23.36IDN (COCO detector)2020-10-30
PaStaNet: Toward Human Activity Knowledge Engine✓ Link22.65PaStaNet2020-04-02
Polysemy Deciphering Network for Robust Human-Object Interaction Detection✓ Link22.37PD-Net2020-08-07
ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection✓ Link22.15ConsNet (ResNet-50)2020-08-14
ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection✓ Link22.11ACP++2021-09-09
PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection✓ Link21.9271PPDM2019-12-30
DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection✓ Link21.8168DIRV2020-10-02
Detailed 2D-3D Joint Representation for Human-Object Interaction✓ Link21.34DJ-RN2020-04-17
Pose-based Modular Network for Human-Object Interaction Detection✓ Link21.21PMN2020-08-05
Transferable Interactiveness Knowledge for Human-Object Interaction Detection✓ Link20.93TIN (TIPAMI)2021-01-25
Detecting Human-Object Interactions with Action Co-occurrence Priors✓ Link20.59ACP
VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions✓ Link19.8VSGNet2020-03-11
Transferable Interactiveness Knowledge for Human-Object Interaction Detection✓ Link17.54512TIN (Interactiveness)2018-11-20
Transferable Interactiveness Knowledge for Human-Object Interaction Detection✓ Link17.22TIN (CVPR)2018-11-20
iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection✓ Link14.84iCAN2018-08-30
Learning Human-Object Interactions by Graph Parsing Neural Networks✓ Link13.11GPNN2018-08-23
Detecting and Recognizing Human-Object Interactions✓ Link9.94145InteractNet2017-04-24