List your company

Human-Object Interaction Detection on V-COCO (AP Role Metrics)

73.4AP^1 RoleHOI-IDiff
38.66447.68256.765.718Oct 26, 2024Jan 3, 2025Mar 14, 2025May 23, 2025Aug 1, 2025Oct 10, 2025Dec 19, 2025

Evaluation results

MethodLinks
HOI-IDiff2025.0373.476.1——
GRASP-HOIBackbone=ResNet-50+MLLM, Closed-set setting=true2025.1272.576.2——
Yuan et al.2025.0372.174.1——
RLIPv2Backbone=Swin-L, Closed-set setting=true2025.1272.174.1——
Luo et al.2025.0371.175.5——
SICHOIBackbone=R101+VIT-L, Closed-set setting=true2025.1271.175.6——
HORPBackbone=Swin-L+CLIP, Closed-set setting=true2025.1268.971.1——
BC-HOIBackbone=ResNet-50, Closed-set setting=true2025.1268.270.1——
UniHOI-1Backbone=R101+VIT-L, Closed-set setting=true2025.1268.170.8——
DIFFUSIONHOIBackbone=ViT-L, VL Pretrain=Stable unCLIP2024.1067.171.1——
DIFFUSIONHOIBackbone=VQGAN, VL Pretrain=Stable Diffusion2024.1066.870.9——
DP-HOIBackbone=ResNet-50, Closed-set setting=true2025.1266.6———
CQLBackbone=ResNet-101, Closed-set setting=true2025.1266.569.9——
CQLBackbone=R50, VL Pretrain=CLIP2024.1066.469.2——
Yang et al.2025.0366.267.6——
MP-HOIBackbone=Swin-L+ViT, Closed-set setting=true2025.1266.267.6——
STIPBackbone=R50, VL Pretrain=-2024.106670.7——
Wang et al.2025.0365.869.9——
BCOMBackbone=ResNet-50, Closed-set setting=true2025.1265.869.9——
AGERBackbone=R50, VL Pretrain=CLIP2024.1065.769.7——
AGERBackbone=ResNet-50, Closed-set setting=true2025.1265.769.7——
DiffHOIBackbone=Swin-L, Closed-set setting=true2025.1265.768.2——
RmLRBackbone=ResNet-101, Closed-set setting=true2025.1264.270.2——
PVICBackbone=Swin-L, VL Pretrain=-2024.1064.170.2——
Zhang et al. [63]2025.0364.170.2——
PVICBackbone=Swin-L, Closed-set setting=true2025.1264.170.2——
RmLRBackbone=R50, VL Pretrain=MobileBERT2024.1063.869.8——
SSRTBackbone=R50, VL Pretrain=CLIP2024.1063.765.9——
Liao et al.2025.0363.665.9——
DOQBackbone=R50, VL Pretrain=CLIP2024.1063.5———
HOICLIPBackbone=R50, VL Pretrain=CLIP2024.1063.564.8——
HOICLIPBackbone=ResNet-50, Closed-set setting=true2025.1263.564.8——
CPChoiBackbone=R50, VL Pretrain=-2024.1063.165.4——
IF-HOIBackbone=R50, VL Pretrain=-2024.106365.2——
MCPCBackbone=R50, VL Pretrain=-2024.106365.1——
Wu et al.2025.036368.7——
PAFRBackbone=Swin-L, Closed-set setting=true2025.126368.7——
PVICBackbone=R50, VL Pretrain=-2024.1062.867.8——
GEN-VLKBackbone=R50, VL Pretrain=CLIP2024.1062.464.4——
GEN-VLKTBackbone=R50+CLIP, Closed-set setting=true2025.1262.464.7——
CDNBackbone=R50, VL Pretrain=-2024.1062.364.4——
CDNBackbone=ResNet-50, Closed-set setting=true2025.1262.364.4——
VIPLOBackbone=ViT-B, VL Pretrain=CLIP2024.1062.268——
VIPLOBackbone=R50+CLIP, Closed-set setting=true2025.1262.268——
MSTRBackbone=R50, VL Pretrain=-2024.106265.2——
RLIPBackbone=ResNet-50, Closed-set setting=true2025.1261.964.2——
Zhang et al. [62]2025.0361.367.1——
UPTBackbone=ResNet-101, Closed-set setting=true2025.1261.367.1——
IwinBackbone=R50-FPN, VL Pretrain=-2024.1060.5———
FGAHOIBackbone=Swin-L, Closed-set setting=true2025.1260.561.2——
EZ-HOIBackbone=ResNet-50, Closed-set setting=true2025.1260.566.2——
CTANBackbone=R50, VL Pretrain=CLIP2024.1060.1———
UPTBackbone=R50, VL Pretrain=-2024.105964.5——
QPICBackbone=R50, VL Pretrain=-2024.1058.861——
Tamura et al.2025.0358.861——
QPICBackbone=ResNet-101, Closed-set setting=true2025.1258.861——
ADA-CMBackbone=ViT-L, VL Pretrain=CLIP2024.1058.664——
ADA-CMBackbone=R50+CLIP, Closed-set setting=true2025.1258.664——
HOTRBackbone=R50, VL Pretrain=-2024.1055.264.4——
AS-NetBackbone=R50, VL Pretrain=-2024.1053.9———
DRGBackbone=R50-FPN, VL Pretrain=-2024.1051———
UnionDetBackbone=R50, VL Pretrain=-2024.1047.556.2——
Kim et al.2025.0347.556.2——
iCANBackbone=R50, VL Pretrain=-2024.1045.3———
Gkioxari et al.2025.034048——
ADA-CMSupervision Setting=fully supervised2026.02———61.2
BC-HOIFeature Extractor=BLIP2, Supervision Setting=fully supervised2026.02——68.270.6
BCOMSupervision Setting=fully supervised2026.02——65.869.9
CLIP4HOIBackbone=ResNet-50, Closed-set setting=true2025.12—66.3——
CLIP4HOISupervision Setting=fully supervised2026.02———66.3
CMMPBackbone=ResNet-50, Closed-set setting=true2025.12—64——
CMMPSupervision Setting=fully supervised2026.02———64
DA-HOISupervision Setting=fully supervised2026.02——69.471.7
DA-HOIDetector=Grounding-DINO, Supervision Setting=fully supervised2026.02——70.472.5
DA-HOIDetector=Yolo-World, Supervision Setting=fully supervised2026.02——70.172.4
EZ-HOISupervision Setting=fully supervised2026.02——60.566.2
GEN-VLKTSupervision Setting=fully supervised2026.02——62.464.5
HOICLIPSupervision Setting=fully supervised2026.02——63.564.8
LAINSupervision Setting=fully supervised2026.02———65.1
UniHOIFeature Extractor=BLIP2, Supervision Setting=fully supervised2026.02——65.668.3