The indices of quantized pixels are used as tokens for the inputs and prediction targets of transformer.
Recent online Multi-Object Tracking (MOT) methods have achieved desirable tracking performance.
In addition, such practice of re-identification still can not track those highly occluded objects when they are missed by the detector.
Ranked #6 on Multi-Object Tracking on MOT16 (using extra training data)
First, MDFR is a well-designed encoder-decoder architecture which extracts feature representation from an input face image with arbitrary low-quality factors and restores it to a high-quality counterpart.