Shaohui Lin

23

Papers

899

Total Citations

Papers (23)

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

Weakly Supervised Open-Vocabulary Object Detection

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

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

Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration

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

Aligning and Prompting Everything All at Once for Universal Visual Perception

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning

Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression

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

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

AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning

Interpretable Neural Network Decoupling

PAMS: Quantized Super-Resolution via Parameterized Max Scale

Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion

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

SET: Spectral Enhancement for Tiny Object Detection

Probability-Density-aware Semi-supervised Learning

Kumaraswamy Wavelet for Heterophilic Scene Graph Generation

A General and Efficient Training for Transformer via Token Expansion

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