Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network

author: Seunghoon Hong, Pohang University of Science and Technology (POSTECH)
published: Jan. 6, 2016,   recorded: October 2015,   views: 2809

See Also:

Download slides icon Download slides: icml2015_hong_neural_network_01.pdf (13.5┬áMB)

Help icon Streaming Video Help

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


We propose an online visual tracking algorithm by learning discriminative saliency map using Convolutional Neural Network (CNN). Given a CNN pre-trained on a large-scale image repository in offline, our algorithm takes outputs from hidden layers of the network as feature descriptors since they show excellent representation performance in various general visual recognition problems. The features are used to learn discriminative target appearance models using an online Support Vector Machine (SVM). In addition, we construct target-specific saliency map by back-projecting CNN features with guidance of the SVM, and obtain the final tracking result in each frame based on the appearance model generatively constructed with the saliency map. Since the saliency map reveals spatial configuration of target effectively, it improves target localization accuracy and enables us to achieve pixel-level target segmentation. We verify the effectiveness of our tracking algorithm through extensive experiment on a challenging benchmark, where our method illustrates outstanding performance compared to the state-of-the-art tracking algorithms.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 Mariah Kozey, August 18, 2020 at 11:27 a.m.:

Glad to hear such valuable thoughts on the Visual Urban Perception and the advancements that are being made in this field with the help of Deep Semantic-Aware Network. I already have written an essay about this network with the help of writers here the the reviews of those writers. Yongchao Xu has explained every single thing about this field beautifully.

Write your own review or comment:

make sure you have javascript enabled or clear this field: