Mingyang Li

papers

434

total citations

papers (12)

SuperLine3D: Self-Supervised Line Segmentation and Description for LiDAR Point Cloud

ECCV 2022arXiv

citations

Interpretable Foreground Object Search As Knowledge Distillation

ECCV 2020arXiv

citations

ProtCLIP: Function-Informed Protein Multi-Modal Learning

AAAI 2025arXiv

citations

Universal Visuo-Tactile Video Understanding for Embodied Interaction

NEURIPS 2025arXiv

citations

Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment

CVPR 2025arXiv

citations

Sparse Adversarial Attack via Perturbation Factorization

ECCV 2020

citations

Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer

AAAI 2025

citations

Mingyang Li

papers (12)

MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

Revisiting Sparse Convolutional Model for Visual Recognition

Incremental Learning of Structured Memory via Closed-Loop Transcription

SFOD: Spiking Fusion Object Detector

A New Benchmark and Model for Challenging Image Manipulation Detection

SuperLine3D: Self-Supervised Line Segmentation and Description for LiDAR Point Cloud

Interpretable Foreground Object Search As Knowledge Distillation

ProtCLIP: Function-Informed Protein Multi-Modal Learning

Universal Visuo-Tactile Video Understanding for Embodied Interaction

Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment

Sparse Adversarial Attack via Perturbation Factorization

Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer

papers (12)

MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

Revisiting Sparse Convolutional Model for Visual Recognition

Incremental Learning of Structured Memory via Closed-Loop Transcription

SFOD: Spiking Fusion Object Detector

A New Benchmark and Model for Challenging Image Manipulation Detection

SuperLine3D: Self-Supervised Line Segmentation and Description for LiDAR Point Cloud

Interpretable Foreground Object Search As Knowledge Distillation

ProtCLIP: Function-Informed Protein Multi-Modal Learning

Universal Visuo-Tactile Video Understanding for Embodied Interaction

Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment

Sparse Adversarial Attack via Perturbation Factorization

Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer