TDT: Teaching Detectors to Track without Fully Annotated Videos. (arXiv:2205.05583v1 [cs.CV])

Web: http://arxiv.org/abs/2205.05583

Recently, one-stage trackers that use a joint model to predict both
detections and appearance embeddings in one forward pass received much
attention and achieved state-of-the-art results on the Multi-Object Tracking
(MOT) benchmarks. However, their success depends on the availability of videos
that are fully annotated with tracking data, which is expensive and hard to
obtain. This can limit the model generalization. In comparison, the two-stage
approach, which performs detection and embedding separately, is slower but
easier to train as their …

arxiv cv teaching videos