Few-Shot Video Object Detection
1 papers with code • 0 benchmarks • 0 datasets
Few-Shot Video Object Detection (FSVOD): given only a few support images of the target object in an unseen class, detect all the objects belonging to the same class in a given query video.
Benchmarks
These leaderboards are used to track progress in Few-Shot Video Object Detection
Most implemented papers
Few-Shot Video Object Detection
fanq15/FewX
•
•
We introduce Few-Shot Video Object Detection (FSVOD) with three contributions to real-world visual learning challenge in our highly diverse and dynamic world: 1) a large-scale video dataset FSVOD-500 comprising of 500 classes with class-balanced videos in each category for few-shot learning; 2) a novel Tube Proposal Network (TPN) to generate high-quality video tube proposals for aggregating feature representation for the target video object which can be highly dynamic; 3) a strategically improved Temporal Matching Network (TMN+) for matching representative query tube features with better discriminative ability thus achieving higher diversity.
