| RLIPv2: Fast Scaling of Relational Language-Image Pre-training | ✓ Link | 72.1 | 74.1 | | | RLIPv2 | 2023-08-18 |
| Relational Context Learning for Human-Object Interaction Detection | ✓ Link | 68.8 | 71.0 | | | MUREN | 2023-04-11 |
| Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection | ✓ Link | 66.0 | 70.7 | 74 | | STIP | 2022-06-13 |
| Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model | ✓ Link | 65.7 | 68.2 | | | DiffHOI | 2023-05-20 |
| Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics | ✓ Link | 65.3 | 67.1 | | | OCN (ResNet101) | 2022-02-01 |
| Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics | ✓ Link | 64.2 | 66.3 | 43 | | OCN (ResNet50) | 2022-02-01 |
| Mining the Benefits of Two-stage and One-stage HOI Detection | ✓ Link | 63.91 | 65.89 | | | CDN (ResNet101) | 2021-08-11 |
| HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models | ✓ Link | 63.50 | 64.81 | | | HOICLIP | 2023-03-28 |
| Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection | ✓ Link | 63.0 | 65.1 | | | Body Part Interactiveness | 2022-07-28 |
| Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer | ✓ Link | 61.3 | 67.1 | 131 | | UPT-R101-DC5 | 2021-12-03 |
| Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer | ✓ Link | 60.7 | 66.2 | 64 | | UPT-R101 | 2021-12-03 |
| Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer | ✓ Link | 59.0 | 64.5 | 43 | | UPT-R50 | 2021-12-03 |
| QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information | ✓ Link | 58.8 | 61.0 | 46 | | QPIC (ResNet50) | 2021-03-09 |
| QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information | ✓ Link | 58.3 | 60.7 | 63 | | QPIC (ResNet101) | 2021-03-09 |
| DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection | ✓ Link | 56.1 | | 68 | | DIRV | 2020-10-02 |
| HOTR: End-to-End Human-Object Interaction Detection with Transformers | ✓ Link | 55.2 | 64.4 | | | HOTR | 2021-04-28 |
| Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection | ✓ Link | 54.7 | | | | GGNet | 2021-04-12 |
| Spatially Conditioned Graphs for Detecting Human-Object Interactions | ✓ Link | 54.2 | 60.9 | 500 | | SCG | 2020-12-11 |
| Polysemy Deciphering Network for Robust Human-Object Interaction Detection | ✓ Link | 53.34 | | | | PD-Net | 2020-08-07 |
| HOI Analysis: Integrating and Decomposing Human-Object Interaction | ✓ Link | 53.3 | 60.3 | | | IDN | 2020-10-30 |
| Detecting Human-Object Interactions with Action Co-occurrence Priors | ✓ Link | 53.23 | | | | ACP | |
| A Skeleton-aware Graph Convolutional Network for Human-Object Interaction Detection | ✓ Link | 53.1 | 57.9 | | | SGCN4HOI | 2022-07-11 |
| Pose-based Modular Network for Human-Object Interaction Detection | ✓ Link | 51.8 | | | | PMN | 2020-08-05 |
| VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions | ✓ Link | 51.76 | 57.0 | 312 | | VSGNet | 2020-03-11 |
| PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection | ✓ Link | 51.1 | | 71 | | PPDM | 2019-12-30 |
| PaStaNet: Toward Human Activity Knowledge Engine | ✓ Link | 51.0 | 57.5 | | | PaStaNet | 2020-04-02 |
| DRG: Dual Relation Graph for Human-Object Interaction Detection | ✓ Link | 51.0 | | | | DRG | 2020-08-26 |
| Transferable Interactiveness Knowledge for Human-Object Interaction Detection | ✓ Link | 49.1 | | | | TIN (TIPAMI) | 2021-01-25 |
| Transferable Interactiveness Knowledge for Human-Object Interaction Detection | ✓ Link | 49.0 | | 513 | | TIN (Interactiveness) | 2018-11-20 |
| Transferable Interactiveness Knowledge for Human-Object Interaction Detection | ✓ Link | 48.7 | | | | TIN (CVPR) | 2018-11-20 |
| iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection | ✓ Link | 44.7 | | | | iCAN | 2018-08-30 |
| Learning Human-Object Interactions by Graph Parsing Neural Networks | ✓ Link | 44.0 | | | | GPNN | 2018-08-23 |
| Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection | ✓ Link | | | | 63.1 | QPIC + CPC | 2022-04-11 |
| Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection | ✓ Link | | | | 61.6 | HOTR + CPC | 2022-04-11 |