RLIPv2: Fast Scaling of Relational Language-Image Pre-training
Open paper
Benchmark
Model
Rank
Results
human-object-interaction-detection-on-hico-det
RLIPv2 (Swin-L)
#1
mAP: 45.09
human-object-interaction-detection-on-v-coco
RLIPv2
#1
AP(S1): 72.1
AP(S2): 74.1
Rank counts only results with a code link.