5 papers
Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
Jiahao Li, Yang Lu, Yachao Zhang +3
Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-l…
PC-CrossDiff: Point-Cluster Dual-Level Cross-Modal Differential Attention for Unified 3D Referring and Segmentation
Wenbin Tan, Jiawen Lin, Fangyong Wang +4
3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentati…
Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective
Jiahao Li, Yang Lu, Yachao Zhang +4
Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhan…
Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation
Jiahao Li, Yang Lu, Yachao Zhang +3
Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-voc…
SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding
Jiawen Lin, Shiran Bian, Yihang Zhu +4
3D Visual Grounding (3DVG) aims to localize objects in 3D scenes using natural language descriptions. Although supervised methods achieve higher accuracy in constrained settings, z…