Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107130
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electrical and Electronic Engineering | - |
dc.creator | Liu, T | en_US |
dc.creator | Zhao, R | en_US |
dc.creator | Xiao, J | en_US |
dc.creator | Lam, KM | en_US |
dc.date.accessioned | 2024-06-13T01:04:05Z | - |
dc.date.available | 2024-06-13T01:04:05Z | - |
dc.identifier.issn | 1070-9908 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/107130 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
dc.rights | The following publication T. Liu, R. Zhao, J. Xiao and K. -M. Lam, "Progressive Motion Representation Distillation With Two-Branch Networks for Egocentric Activity Recognition," in IEEE Signal Processing Letters, vol. 27, pp. 1320-1324, 2020 is available at https://doi.org/10.1109/LSP.2020.3011326. | en_US |
dc.subject | Egocentric activity recognition | en_US |
dc.subject | Knowledge distillation | en_US |
dc.subject | Motion representation | en_US |
dc.subject | Two-branch networks | en_US |
dc.title | Progressive motion representation distillation with two-branch networks for egocentric activity recognition | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 1320 | en_US |
dc.identifier.epage | 1324 | en_US |
dc.identifier.volume | 27 | en_US |
dc.identifier.doi | 10.1109/LSP.2020.3011326 | en_US |
dcterms.abstract | Video-based egocentric activity recognition involves fine-grained spatiooral human-object interactions. State-of-the-art methods, based on the two-branch-based architecture, rely on pre-calculated optical flows to provide motion information. However, this two-stage strategy is computationally intensive, storage demanding, and not task-oriented, which hampers it from being deployed in real-world applications. Albeit there have been numerous attempts to explore other motion representations to replace optical flows, most of the methods were designed for third-person activities, without capturing fine-grained cues. To tackle these issues, in this letter, we propose a progressive motion representation distillation (PMRD) method, based on two-branch networks, for egocentric activity recognition. We exploit a generalized knowledge distillation framework to train a hallucination network, which receives RGB frames as input and produces motion cues guided by the optical-flow network. Specifically, we propose a progressive metric loss, which aims to distill local fine-grained motion patterns in terms of each temporal progress level. To further enforce the proposed distillation framework to concentrate on those informative frames, we integrate a temporal attention mechanism into the metric loss. Moreover, a multi-stage training procedure is employed for the efficient learning of the hallucination network. Experimental results on three egocentric activity benchmarks demonstrate the state-of-the-art performance of the proposed method. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE signal processing letters, 2020, v. 27, p. 1320-1324 | en_US |
dcterms.isPartOf | IEEE signal processing letters | en_US |
dcterms.issued | 2020 | - |
dc.identifier.scopus | 2-s2.0-85089947593 | - |
dc.identifier.eissn | 1558-2361 | en_US |
dc.description.validate | 202403 bckw | - |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | EIE-0188 | - |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 50281666 | - |
dc.description.oaCategory | Green (AAM) | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Liu_Progressive_Motion_Representation.pdf | Pre-Published version | 872.05 kB | Adobe PDF | View/Open |
Page views
2
Citations as of Jun 30, 2024
Downloads
1
Citations as of Jun 30, 2024
SCOPUSTM
Citations
3
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
3
Citations as of Jun 27, 2024
![](/image/google_scholar.jpg)
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.