Goto

Collaborating Authors

 Africa






VastTrack: Vast Category Visual Object Tracking

Neural Information Processing Systems

V astTrack consists of a few attractive properties: (1) V ast Object Category . In particular, it covers targets from 2,115 categories, significantly surpassing object classes of existing popular benchmarks ( e.g ., GOT -10k with 563 classes and LaSOT with 70 categories). Through providing such vast object classes, we expect to learn more general object tracking.



Activation Map Compression through Tensor Decomposition for Deep Learning

Neural Information Processing Systems

The application of low-order decomposition results in considerable memory savings while preserving the features essential for learning, and also offers theoretical guarantees to convergence.