Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/107179
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electrical and Electronic Engineering | - |
dc.creator | He, CH | en_US |
dc.creator | Lai, SC | en_US |
dc.creator | Lam, KM | en_US |
dc.date.accessioned | 2024-06-13T01:04:25Z | - |
dc.date.available | 2024-06-13T01:04:25Z | - |
dc.identifier.isbn | 978-1-4799-8131-1 (Electronic) | en_US |
dc.identifier.isbn | 978-1-4799-8132-8 (Print on Demand(PoD)) | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/107179 | - |
dc.description | ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK | en_US |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | ©2019 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 C. -H. He, S. -C. Lai and K. -M. Lam, "Improving Object Detection with Relation Graph Inference," ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019, pp. 2537-2541 is available at https://doi.org/10.1109/ICASSP.2019.8682335. | en_US |
dc.subject | Graph convolutional neural network | en_US |
dc.subject | Object detection | en_US |
dc.title | Improving object detection with relation graph inference | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.spage | 2537 | en_US |
dc.identifier.epage | 2541 | en_US |
dc.identifier.doi | 10.1109/ICASSP.2019.8682335 | en_US |
dcterms.abstract | Many classic object detection approaches have proven that detection performance can be improved by adding the object's context information. However, only a few methods have attempted to exploit the object-to-object relationship during learning. The reason for this is that objects may appear at different locations in an image, with an arbitrary size and scale. This makes it difficult to model the objects in a unified way within a network. Inspired by Graph Convolutional Network (GCN), we propose a detection algorithm that can infer the relationship among multiple objects during the inference, achieved by constructing a relation graph dynamically with a self-adopted attention mechanism. The relation graph encodes both the geometric and visual relationship between objects. This can enrich the object feature by aggregating the information from the object and its relevant neighbors. Experiments show that our proposed module can efficiently improve the detection performance of existing object detectors. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | In Proceedings of ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 12-17 May 2019, Brighton, UK, p. 2537-2541 | en_US |
dcterms.issued | 2019 | - |
dc.identifier.scopus | 2-s2.0-85069003239 | - |
dc.relation.conference | International Conference on Acoustics, Speech, and Signal Processing [ICASSP] | - |
dc.description.validate | 202404 bckw | - |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | EIE-0382 | - |
dc.description.fundingSource | Others | en_US |
dc.description.fundingText | Hong Kong Polytechnic University | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 20082841 | - |
dc.description.oaCategory | Green (AAM) | en_US |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
He_Improving_Object_Detection.pdf | Pre-Published version | 1.46 MB | Adobe PDF | View/Open |
Page views
2
Citations as of Jun 30, 2024
SCOPUSTM
Citations
18
Citations as of Jun 21, 2024
WEB OF SCIENCETM
Citations
13
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.