95 citations · 218 across the 23 of their papers we have counts for
5 papers · 1 filter
RefMask3D: Language-Guided Transformer for 3D Referring Segmentation
Shuting He, Henghui Ding
3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The…
SegPoint: Segment Any Point Cloud via Large Language Model
Shuting He, Henghui Ding, Xudong Jiang +1
Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the…
PVUW 2024 Challenge on Complex Video Understanding: Methods and Results
Henghui Ding, Chang Liu, Yunchao Wei +34
Pixel-level Video Understanding in the Wild Challenge (PVUW) focus on complex video understanding. In this CVPR 2024 workshop, we add two new tracks, Complex Video Object Segmentat…
Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation
Shuting He, Henghui Ding
Referring video segmentation relies on natural language expressions to identify and segment objects, often emphasizing motion clues. Previous works treat a sentence as a whole and…
Context-Aware Integration of Language and Visual References for Natural Language Tracking
Yanyan Shao, Shuting He, Qi Ye +3
Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodolog…