Xinpeng Ding

8

Papers

29

Total Citations

Papers (8)

C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models

Holistic Autonomous Driving Understanding by Bird’s-Eye-View Injected Multi-Modal Large Models

Boosting Weakly-Supervised Temporal Action Localization With Text Information

Support-Set Based Cross-Supervision for Video Grounding

GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation

Learning Shadow Correspondence for Video Shadow Detection

Token Activation Map to Visually Explain Multimodal LLMs