Dingkang Liang

11

Papers

5

Total Citations

Papers (11)

Make Your ViT-based Multi-view 3D Detectors Faster via Token Compression

NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding

NeurIPS 2025arXiv

SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

SOOD: Towards Semi-Supervised Oriented Object Detection

CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model

A Simple Vision Transformer for Weakly Semi-supervised 3D Object Detection

An End-to-End Transformer Model for Crowd Localization

MINIMA: Modality Invariant Image Matching

When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition

A Unified Image-Dense Annotation Generation Model for Underwater Scenes