37 citations · 38 across the 3 of their papers we have counts for
Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023
End-to-End 3D Dense Captioning with Vote2Cap-DETR
Sijin Chen, Hongyuan Zhu, Xin Chen +3
3D dense captioning aims to generate multiple captions localized with their associated object regions. Existing methods follow a sophisticated ``detect-then-describe'' pipeline equ…
cs.CV2020★ 37 cited
CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud
Wu Zheng, Weiliang Tang, Sijin Chen +2
Existing single-stage detectors for locating objects in point clouds often treat object localization and category classification as separate tasks, so the localization accuracy and…