Objects do not disappear: Video object detection by single-frame object location anticipation
Paper
•
2308.04770
•
Published
Xin Liu
XinLIU-kid
AI & ML interests
1. Efficient deep learning for video understanding, e.g. video object detection/tracking, segmentation, and action recognition.
2. Optimization for efficient training of DNNs on large-volume temporal data.
3. Efficient diffusion models.
Organizations
None yet
authored
a
paper
almost 2 years ago