3 papers
cs.CV2026
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
Xuezhi Xiang, Jiayao Liu, Heqi Xiang +3
Accurate monocular depth estimation serves as a core enabler for single camera scene understanding. However, existing self-supervised monocular depth estimation methods generally s…
cs.CV2026
tcnerv:dual-domain temporal context modeling for implicit neural video compression
Xuezhi Xiang, Yixin Zhao, Heqi Xiang +2
Video compression aims to minimize reconstruction distor tion under a constrained bit rate. Existing video implicit neural representations (INRs) often decode frames independently,…
cs.CV2026
PSMP-CLIP: Patch-Prompt SAM and Multi-Semantic Prompting for CLIP-Based Zero-Shot Anomaly Detection
Xuezhi Xiang, Guanghao Wu, Heqi Xiang +4
Zero-shot anomaly detection aims to localize anomalies without target-domain samples. Existing CLIP-based methods suffer from coarse anomaly maps and limited semantic prompts. We p…