Search Results for author:
Found 2 papers, 1 papers with code
DiffusionVID: Denoising Object Boxes with Spatio-temporal Conditioning for Video Object Detection
To effectively refine the box from the degraded images in the videos, we used three novel approaches: cascade refinement, dynamic core-set conditioning, and local batch refinement.
Ranked #1 on
Video Object Detection
on ImageNet VID
DAFA: Diversity-Aware Feature Aggregation for Attention-Based Video Object Detection
Our method with global and local attention stages obtains 84. 5 and 85. 9 mAP on ResNet-101 and ResNeXt-101, respectively, thus achieving state-of-the-art performance without requiring additional post-processing methods.
Ranked #10 on
Video Object Detection
on ImageNet VID
