Conference
AttTrack: Online Deep Attention Transfer for Multi-object Tracking
Abstract
Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. The time and storage complexity required to execute deep learning models for visual object tracking hinder their adoption on embedded devices with limited computing power. In this paper, we aim to accelerate MOT by transferring the knowledge from high-level features of a complex network (teacher) to a …
Authors
Nalaie K; Zheng R
Volume
00
Pagination
pp. 1654-1663
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Publication Date
January 7, 2023
DOI
10.1109/wacv56688.2023.00170
Name of conference
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)