File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV48922.2021.00292
- Scopus: eid_2-s2.0-85120944689
- WOS: WOS:000797698903012
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds
Title | 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds |
---|---|
Authors | |
Issue Date | 2021 |
Citation | Proceedings of the IEEE International Conference on Computer Vision, 2021, p. 2908-2917 How to Cite? |
Abstract | Visual grounding on 3D point clouds is an emerging vision and language task that benefits various applications in understanding the 3D visual world. By formulating this task as a grounding-by-detection problem, lots of recent works focus on how to exploit more powerful detectors and comprehensive language features, but (1) how to model complex relations for generating context-aware object proposals and (2) how to leverage proposal relations to distinguish the true target object from similar proposals are not fully studied yet. Inspired by the well-known transformer architecture, we propose a relation-aware visual grounding method on 3D point clouds, named as 3DVG-Transformer, to fully utilize the contextual clues for relation-enhanced proposal generation and cross-modal proposal disambiguation, which are enabled by a newly designed coordinate-guided contextual aggregation (CCA) module in the object proposal generation stage, and a multiplex attention (MA) module in the cross-modal feature fusion stage. We validate that our 3DVG-Transformer outperforms the state-of-the-art methods by a large margin, on two point cloud-based visual grounding datasets, ScanRefer and Nr3D/Sr3D from ReferIt3D, especially for complex scenarios containing multiple objects of the same category. |
Persistent Identifier | http://hdl.handle.net/10722/321974 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Lichen | - |
dc.contributor.author | Cai, Daigang | - |
dc.contributor.author | Sheng, Lu | - |
dc.contributor.author | Xu, Dong | - |
dc.date.accessioned | 2022-11-03T02:22:44Z | - |
dc.date.available | 2022-11-03T02:22:44Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the IEEE International Conference on Computer Vision, 2021, p. 2908-2917 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321974 | - |
dc.description.abstract | Visual grounding on 3D point clouds is an emerging vision and language task that benefits various applications in understanding the 3D visual world. By formulating this task as a grounding-by-detection problem, lots of recent works focus on how to exploit more powerful detectors and comprehensive language features, but (1) how to model complex relations for generating context-aware object proposals and (2) how to leverage proposal relations to distinguish the true target object from similar proposals are not fully studied yet. Inspired by the well-known transformer architecture, we propose a relation-aware visual grounding method on 3D point clouds, named as 3DVG-Transformer, to fully utilize the contextual clues for relation-enhanced proposal generation and cross-modal proposal disambiguation, which are enabled by a newly designed coordinate-guided contextual aggregation (CCA) module in the object proposal generation stage, and a multiplex attention (MA) module in the cross-modal feature fusion stage. We validate that our 3DVG-Transformer outperforms the state-of-the-art methods by a large margin, on two point cloud-based visual grounding datasets, ScanRefer and Nr3D/Sr3D from ReferIt3D, especially for complex scenarios containing multiple objects of the same category. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE International Conference on Computer Vision | - |
dc.title | 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/ICCV48922.2021.00292 | - |
dc.identifier.scopus | eid_2-s2.0-85120944689 | - |
dc.identifier.spage | 2908 | - |
dc.identifier.epage | 2917 | - |
dc.identifier.isi | WOS:000797698903012 | - |