Spatiality-guided transformer for 3d dense captioning on point clouds

H Wang, C Zhang, J Yu, W Cai - arXiv preprint arXiv:2204.10688, 2022 - arxiv.org
Dense captioning in 3D point clouds is an emerging vision-and-language task involving
object-level 3D scene understanding. Apart from coarse semantic class prediction and …
被引用次数：30 相关文章
[PDF] archive.org

[PDF][PDF] Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

H Wang, C Zhang, J Yu, W Cai - scholar.archive.org
Dense captioning in 3D point clouds is an emerging vision-and-language task involving
object-level 3D scene understanding. Apart from coarse semantic class prediction and …
[PDF] ijcai.org

[PDF][PDF] Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

H Wang, C Zhang, J Yu, W Cai - ijcai.org
Dense captioning in 3D point clouds is an emerging vision-and-language task involving
object-level 3D scene understanding. Apart from coarse semantic class prediction and …

Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds

H Wang, C Zhang, J Yu, W Cai - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Dense captioning in 3D point clouds is an emerging vision-and-language task involving
object-level 3D scene understanding. Apart from coarse semantic class prediction and …