S²Teacher: Step-by-step Teacher for Sparsely Annotated Oriented Object Detection.

Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization.

Density-Driven Adaptive Hybrid Network for Large-Scale Place Recognition.

Joint Representation Learning Based on Feature Center Region Diffusion and Edge Radiation for Cross-View Geo-Localization.

Fast, Robust, Accurate, Multi-Body Motion Aware SLAM.

Self-supervised assisted multi-task learning network for one-shot defect segmentation with fake defect generation.