Shaohui Lin

OpenReview

papers

2,292

total citations

papers (22)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

CVPR 2025arXiv

917

citations

Contrastive Learning for Compact Single Image Dehazing

CVPR 2021arXiv

786

citations

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

CVPR 2021arXiv

154

citations

DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning

ECCV 2022arXiv

citations

Weakly Supervised Open-Vocabulary Object Detection

AAAI 2024arXiv

citations

SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space

AAAI 2024arXiv

citations

A General and Efficient Training for Transformer via Token Expansion

CVPR 2024arXiv

citations

WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection

ICCV 2025arXiv

citations

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

ICLR 2025arXiv

citations

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

AAAI 2025arXiv

citations

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

ICLR 2025

citations

Interpretable Neural Network Decoupling

ECCV 2020arXiv

citations

Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion

CVPR 2025

citations

Probability-Density-aware Semi-supervised Learning

AAAI 2025arXiv

citations

CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning

CVPR 2024

citations

SET: Spectral Enhancement for Tiny Object Detection

CVPR 2025

citations

Kumaraswamy Wavelet for Heterophilic Scene Graph Generation

AAAI 2024

citations

HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization

CVPR 2022

citations

Shaohui Lin

papers (22)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Contrastive Learning for Compact Single Image Dehazing

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

Towards Compact CNNs via Collaborative Compression

PAMS: Quantized Super-Resolution via Parameterized Max Scale

Aligning and Prompting Everything All at Once for Universal Visual Perception

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning

Weakly Supervised Open-Vocabulary Object Detection

SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space

A General and Efficient Training for Transformer via Token Expansion

WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

Interpretable Neural Network Decoupling

Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion

Probability-Density-aware Semi-supervised Learning

CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning

SET: Spectral Enhancement for Tiny Object Detection

Kumaraswamy Wavelet for Heterophilic Scene Graph Generation

HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization

papers (22)

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Contrastive Learning for Compact Single Image Dehazing

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

Towards Compact CNNs via Collaborative Compression

PAMS: Quantized Super-Resolution via Parameterized Max Scale

Aligning and Prompting Everything All at Once for Universal Visual Perception

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

DisCo: Remedying Self-Supervised Learning on Lightweight Models with Distilled Contrastive Learning

Weakly Supervised Open-Vocabulary Object Detection

SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space

A General and Efficient Training for Transformer via Token Expansion

WaveMamba: Wavelet-Driven Mamba Fusion for RGB-Infrared Object Detection

Knowledge Distillation with Multi-granularity Mixture of Priors for Image Super-Resolution

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution

Interpretable Neural Network Decoupling

Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion

Probability-Density-aware Semi-supervised Learning

CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning

SET: Spectral Enhancement for Tiny Object Detection

Kumaraswamy Wavelet for Heterophilic Scene Graph Generation

HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization