VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision
Open paper
Benchmark
Model
Rank
Results
pedestrian-detection-on-caltech
VLPD
#4
Reasonable Miss Rate: 2.3
Heavy MR^-2: 37.7
pedestrian-detection-on-citypersons
VLPD
#5
Reasonable MR^-2: 9.4
Heavy MR^-2: 43.1
Partial MR^-2: 8.8
…
Rank counts only results with a code link.