Matches in Ghent University Academic Bibliography for { <https://biblio.ugent.be/publication/01GPFHH4K0F79ADJ3BJCX976MV> ?p ?o. }
Showing items 1 to 26 of
26
with 100 items per page.
- 01GPFHH4K0F79ADJ3BJCX976MV classification P1.
- 01GPFHH4K0F79ADJ3BJCX976MV date "2023".
- 01GPFHH4K0F79ADJ3BJCX976MV language "eng".
- 01GPFHH4K0F79ADJ3BJCX976MV type conference.
- 01GPFHH4K0F79ADJ3BJCX976MV hasPart 01GPFHY0E34DQCKNQCJMZ6FKHV.pdf.
- 01GPFHH4K0F79ADJ3BJCX976MV hasPart 01GPFJ01T21CXWWHQPCJ0V1ANZ.pdf.
- 01GPFHH4K0F79ADJ3BJCX976MV subject "Technology and Engineering".
- 01GPFHH4K0F79ADJ3BJCX976MV doi "10.1109/WACVW58289.2023.00014".
- 01GPFHH4K0F79ADJ3BJCX976MV isbn "9798350320565".
- 01GPFHH4K0F79ADJ3BJCX976MV isbn "9798350320572".
- 01GPFHH4K0F79ADJ3BJCX976MV issn "2572-4398".
- 01GPFHH4K0F79ADJ3BJCX976MV issn "2690-621X".
- 01GPFHH4K0F79ADJ3BJCX976MV presentedAt urn:uuid:ed177717-e932-4744-b80c-c5cf9cb5824c.
- 01GPFHH4K0F79ADJ3BJCX976MV abstract "Occlusion is one of the most challenging problems in single-view pedestrian detection. To alleviate the occlusion problem, multi-view systems have been exploited to fully acquire and recognize blocked targets. Most often, methods from the literature exploit perspective transformation to aggregate different sensing view angles of the scene, but projection distortion issues cause spatial structure break and prevent these methods from fully exploring the projected features. In this paper, we propose a novel approach, Multi-view Target Transformation (MVTT), to address the distortion problem inherent in multi-view aggregation by encoding the full target features and limiting the area of interest of the projected features. Experiment results show that the performance of our proposed method compares favorably against recent relevant methods on public datasets. The ablation studies also confirm the effectiveness of the proposed components.".
- 01GPFHH4K0F79ADJ3BJCX976MV author 35a40208-eefa-11ea-a3c8-de5064b9e46b.
- 01GPFHH4K0F79ADJ3BJCX976MV author F4733938-F0ED-11E1-A9DE-61C894A0A6B4.
- 01GPFHH4K0F79ADJ3BJCX976MV author F82F3036-F0ED-11E1-A9DE-61C894A0A6B4.
- 01GPFHH4K0F79ADJ3BJCX976MV dateCreated "2023-01-11T04:31:05Z".
- 01GPFHH4K0F79ADJ3BJCX976MV dateModified "2024-12-12T19:23:40Z".
- 01GPFHH4K0F79ADJ3BJCX976MV name "Multi-view target transformation for pedestrian detection".
- 01GPFHH4K0F79ADJ3BJCX976MV pagination urn:uuid:a31ea60e-bf1b-4b49-92ea-73f2de7cbf38.
- 01GPFHH4K0F79ADJ3BJCX976MV publisher urn:uuid:6916f574-9904-4b44-a3f8-b93f034f6977.
- 01GPFHH4K0F79ADJ3BJCX976MV sameAs LU-01GPFHH4K0F79ADJ3BJCX976MV.
- 01GPFHH4K0F79ADJ3BJCX976MV sourceOrganization urn:uuid:073cfe37-27e5-46c6-80a7-936a43819fa8.
- 01GPFHH4K0F79ADJ3BJCX976MV sourceOrganization urn:uuid:39049d6e-e753-4f27-9e0b-8a5cce395496.
- 01GPFHH4K0F79ADJ3BJCX976MV type P1.