DiffusionVID: Denoising Object Boxes with Spatio-temporal Conditioning for Video Object Detection

Open paper

Benchmark	Model	Rank	Results
video-object-detection-on-imagenet-vid	DiffusionVID (Swin-B)	#2	MAP: 92.5
video-object-detection-on-imagenet-vid	DiffusionVID (ResNet-101)	#10	MAP: 87.1