IEEE

Multimodal Cross-City Semantic Segmentation Based on Similarity-Inspired Fusion and Invertible Transformation Learning Network

Abstract: Multimodal cross-city semantic segmentation aims to adapt a network trained on multiple labeled source domains (MSDs) from one city to multiple unlabeled target domains (MTDs) in another ...
GitHub

InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes, Zesong Yang, Bangbang Yang, Wenqi Dong, Chenxuan Cao, Liyuan Cui, Yuewen Ma, Zhaopeng Cui, Hujun Bao It ...
IEEE

Difference-Aware Fusion Network for Efficient RGB-D Semantic Segmentation in Indoor Robots

Abstract: Incorporating both RGB and depth images has proven effective for enhancing the performance of semantic segmentation. However, current RGB-D semantic segmentation methods tend to overlook the ...
GitHub

Semantic Code Search Engine (semcode)

semcode is a Python-first semantic code search engine that ingests C++ and Python repositories, splits source files into logical chunks with Tree-sitter + Code2Prompt heuristics, embeds those chunks ...