Human Object Interaction Detection On Hico
Metrics
mAP
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | mAP |
|---|---|
| detecting-human-object-interactions-with-1 | 20.59 |
| detailed-2d-3d-joint-representation-for-human | 21.34 |
| transferable-interactiveness-knowledge-for | 20.93 |
| consistency-learning-via-decoding-path | 26.16 |
| consistency-learning-via-decoding-path | 29.63 |
| exploring-predicate-visual-context-in | 44.32 |
| learning-human-object-interactions-by-graph | 13.11 |
| ernet-efficient-and-reliable-human-object | 36.89 |
| mining-the-benefits-of-two-stage-and-one | 32.07 |
| end-to-end-human-object-interaction-detection | 23.46 |
| hoi-analysis-integrating-and-decomposing | 23.36 |
| consnet-learning-consistency-graph-for-zero | 22.15 |
| dynamic-scene-understanding-from-vision | 46.49 |
| category-query-learning-for-human-object | 36.03 |
| category-query-learning-for-human-object | 35.36 |
| rlipv2-fast-scaling-of-relational-language | 45.09 |
| end-to-end-human-object-interaction-detection | 26.61 |
| gen-vlkt-simplify-association-and-enhance | 34.95 |
| mining-cross-person-cues-for-body-part | 35.15 |
| ican-instance-centric-attention-network-for | 14.84 |
| efficient-two-stage-detection-of-human-object | 31.66 |
| spatio-attentive-graphs-for-human-object | 29.26 |
| focusing-on-what-to-decode-and-what-to-train | 43.35 |
| drg-dual-relation-graph-for-human-object | 24.53 |
| qahoi-query-based-anchors-for-human-object | 35.78 |
| detecting-and-recognizing-human-object | 9.94 |
| rlip-relational-language-image-pre-training | 32.84 |
| ppdm-parallel-point-detection-and-matching | 21.92 |
| efficient-two-stage-detection-of-human-object | 32.31 |
| consnet-learning-consistency-graph-for-zero | 25.94 |
| exploring-structure-aware-transformer-over-1 | 32.22 |
| transferable-interactiveness-prior-for-human | 17.54 |
| pose-based-modular-network-for-human-object | 21.21 |
| boosting-human-object-interaction-detection | 41.50 |
| exploring-predicate-visual-context-in | 34.69 |
| hotr-end-to-end-human-object-interaction | 23.46 |
| vsgnet-spatial-attention-network-for | 19.8 |
| relational-context-learning-for-human-object | 32.87 |
| unseen-no-more-unlocking-the-potential-of | 34.84 |
| acp-action-co-occurrence-priors-for-human | 22.11 |
| qpic-query-based-pairwise-human-object | 29.07 |
| fgahoi-fine-grained-anchors-for-human-object | 37.18 |
| pastanet-toward-human-activity-knowledge | 22.65 |
| detecting-human-object-interactions-with-2 | 31.43 |
| transferable-interactiveness-prior-for-human | 17.22 |
| viplo-vision-transformer-based-pose | 37.22 |
| polysemy-deciphering-network-for-robust-human | 22.37 |
| qpic-query-based-pairwise-human-object | 29.90 |
| efficient-two-stage-detection-of-human-object | 32.62 |
| reformulating-hoi-detection-as-adaptive-set | 28.87 |
| dirv-dense-interaction-region-voting-for-end | 21.81 |
| hoiclip-efficient-knowledge-transfer-for-hoi | 34.69 |
| hoi-analysis-integrating-and-decomposing | 26.29 |
| decoupling-object-detection-from-human-object-1 | 32.35 |
| rlip-relational-language-image-pre-training | 32.76 |