Experts has a new look! Let us know what you think of the updates.

Provide feedback
Home
Scholarly Works
AttTrack: Online Deep Attention Transfer for...
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)