Bytetrack: Multi-object tracking by associating every detection box
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in
videos. Most methods obtain identities by associating detection boxes whose scores are …
videos. Most methods obtain identities by associating detection boxes whose scores are …
Part-based pseudo label refinement for unsupervised person re-identification
Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …
Transreid: Transformer-based object re-identification
Extracting robust feature representation is one of the key challenges in object re-
identification (ReID). Although convolution neural network (CNN)-based methods have …
identification (ReID). Although convolution neural network (CNN)-based methods have …
Trackformer: Multi-object tracking with transformers
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about
track initialization, identity, and spatio-temporal trajectories. We formulate this task as a …
track initialization, identity, and spatio-temporal trajectories. We formulate this task as a …