CTRL_FSD_TTA

Authors	Lue Fan, Yuxue Yang, Yiming Mao, Feng Wang, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang
Description	CTRL (onCe detecTed neveR Lost) is a single-model offline detector, designed in a track-centric perspective with simple methodology. It features a bidirectional tracking module (past and future frames) and a track-centric learning module, which makes CTRL capable of inferring a full-length track once the object is detected at a certain moment.
Project Link	Link

TYPE_VEHICLE