In this supplementary material, we provide detailed dense captioning results on the
ScanRefer dataset in Sec. 1. To showcase the effectiveness of the proposed pre-training …

Abstract 3D dense captioning aims to generate multiple captions localized with their
associated object regions. Existing methods follow a sophisticated" detect-then-describe" …

Abstract 3D dense captioning aims to describe individual objects by natural language in 3D
scenes, where 3D scenes are usually represented as RGB-D scans or point clouds …

3D dense captioning aims to semantically describe each object detected in a 3D scene,
which plays a significant role in 3D scene understanding. Previous works lack a complete …

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 …

3D dense captioning requires a model to translate its understanding of an input 3D scene
into several captions associated with different object regions. Existing methods adopt a …

3D Visual Grounding (3DVG) and 3D Dense Captioning (3DDC) are two crucial tasks in
various 3D applications, which require both shared and complementary information in …

Abstract 3D dense captioning is a recently-proposed novel task, where point clouds contain
more geometric information than the 2D counterpart. However, it is also more challenging …

In this supplementary material, we provide results on the ReferIt3D dataset in Sec. 1. To
showcase the effectiveness of our speaker-listener architecture, we provide additional …

There has been a lot of previous work in the area of cross-modal scene understanding,
especially for the tasks of image captioning [32] and the related task of dense captioning …