Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, Epiciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Conference papers

Residual Transfer Learning for Multiple Object Tracking

Abstract : To address the Multiple Object Tracking (MOT) challenge , we propose to enhance the tracklet appearance features , given by a Convolutional Neural Network (CNN), based on the Residual Transfer Learning (RTL) method. Considering that object classification and tracking are significantly different tasks at high level. And that traditional fine-tuning limits the possible variations in all the layers of the network since it changes the last convolutional layers. Beyond that, our proposed method provides more flexibility in terms of modelling the difference between these two tasks with a four-stage training. This transfer approach increases the feature performance compared to traditional CNN fine-tuning. Experiments on the MOT17 challenge show competitive results with the current state-of-the-art methods.
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Juan Diego Gonzales Zuniga Connect in order to contact the contributor
Submitted on : Tuesday, November 20, 2018 - 4:14:24 PM
Last modification on : Saturday, June 25, 2022 - 11:32:47 PM


Files produced by the author(s)


  • HAL Id : hal-01928612, version 1



Juan Diego Gonzales Zuniga, Thi-Lan-Anh Nguyen, Francois Bremond. Residual Transfer Learning for Multiple Object Tracking. International Conference on Advanced Video and Signal-based Surveillance (AVSS), IEEE, Nov 2018, Auckland, New Zealand. ⟨hal-01928612⟩



Record views


Files downloads