Publications
Detailed Information
Real-Time MDNet
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Ilchae | - |
dc.contributor.author | Son, Jeany | - |
dc.contributor.author | Baek, Mooyeol | - |
dc.contributor.author | Han, Bohyung | - |
dc.date.accessioned | 2024-03-22T08:41:54Z | - |
dc.date.available | 2024-03-22T08:41:54Z | - |
dc.date.created | 2024-03-14 | - |
dc.date.created | 2024-03-14 | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | COMPUTER VISION - ECCV 2018, PT IV, Vol.11208, pp.89-104 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | https://hdl.handle.net/10371/199242 | - |
dc.description.abstract | We present a fast and accurate visual tracking algorithm based on the multi-domain convolutional neural network (MDNet). The proposed approach accelerates feature extraction procedure and learns more discriminative models for instance classification; it enhances representation quality of target and background by maintaining a high resolution feature map with a large receptive field per activation. We also introduce a novel loss term to differentiate foreground instances across multiple domains and learn a more discriminative embedding of target objects with similar semantics. The proposed techniques are integrated into the pipeline of a well known CNN-based visual tracking algorithm, MDNet. We accomplish approximately 25 times speed-up with almost identical accuracy compared to MDNet. Our algorithm is evaluated in multiple popular tracking benchmark datasets including OTB2015, UAV123, and TempleColor, and outperforms the state-of-the-art real-time tracking methods consistently even without dataset-specific parameter tuning. | - |
dc.language | 영어 | - |
dc.publisher | SPRINGER INTERNATIONAL PUBLISHING AG | - |
dc.title | Real-Time MDNet | - |
dc.type | Article | - |
dc.identifier.doi | 10.1007/978-3-030-01225-0_6 | - |
dc.citation.journaltitle | COMPUTER VISION - ECCV 2018, PT IV | - |
dc.identifier.wosid | 000594212900006 | - |
dc.identifier.scopusid | 2-s2.0-85055456242 | - |
dc.citation.endpage | 104 | - |
dc.citation.startpage | 89 | - |
dc.citation.volume | 11208 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Han, Bohyung | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
dc.subject.keywordAuthor | Visual tracking | - |
dc.subject.keywordAuthor | Multi-domain learning | - |
dc.subject.keywordAuthor | RoIAlign | - |
dc.subject.keywordAuthor | Instance embedding loss | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.