Large Kernel Network for Efficient Image Restoration
ArtIR: an efficient large-kernel network for image restoration across single-degradation, all-in-one, and composite-degradation scenarios.
TIP
Zongyan Han
Postdoctoral Associate
I am a Postdoctoral Associate at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), working with Prof. Fahad Shahbaz Khan and Prof. Rao Muhammad Anwer.
I received my Ph.D. in Engineering from Nanjing University of Science and Technology, advised by Prof. Jian Yang (IAPR Fellow) and Prof. Zhenyong Fu. Previously, I was a Research Assistant at The Hong Kong Polytechnic University, advised by Prof. Chang Wen Chen (IEEE Fellow; SPIE Fellow; MAE).
AgroGround: Multi-Granularity Grounded Recognition in Agriculture
AgroGround: Multi-Granularity Grounded Recognition in Agriculture
arXiv:2610.04425 · Preprint
Ground3D-LMM: Fine-Grained 3D Point Grounding and Spatial Reasoning with LMM
Fine-grained 3D point grounding and spatial reasoning with large multimodal models.
ECCV
Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats
Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats
arXiv:2608.15651 · Preprint
Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs
Thinking Beyond Labels: Vocabulary-Free Fine-Grained Recognition using Reasoning-Augmented LMMs
CVPR
Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation
Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation
arXiv:2602.03892 · Preprint
Bring Your Dreams to Life: Continual Text-to-Video Customization
Bring Your Dreams to Life: Continual Text-to-Video Customization
AAAI
MIRA: A Novel Framework for Fusing Modalities in Medical RAG
MIRA: A Novel Framework for Fusing Modalities in Medical RAG
ACM Multimedia
All in One: Visual-Description-Guided Unified Point Cloud Segmentation
Visual-description-guided unified point cloud segmentation.
ICCV
Composed Object Retrieval: Object-level Retrieval via Composed Expressions
Composed Object Retrieval: Object-level Retrieval via Composed Expressions
arXiv:2508.04424 · Preprint
OpenSeg-R: Improving Open-Vocabulary Segmentation via Step-by-Step Visual Reasoning
Open-vocabulary segmentation via step-by-step visual reasoning.
arXiv:2505.16974 · Preprint
ZS-VAT: Learning Unbiased Attribute Knowledge for Zero-Shot Recognition through Visual Attribute Transformer
ZS-VAT: Learning Unbiased Attribute Knowledge for Zero-Shot Recognition through Visual Attribute Transformer
TNNLS
Semantic Contrastive Embedding for Generalized Zero-Shot Learning
Semantic Contrastive Embedding for Generalized Zero-Shot Learning
IJCV
Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval
Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval
AAAI
Contrastive Embedding for Generalized Zero-Shot Learning
Contrastive Embedding for Generalized Zero-Shot Learning
CVPR
Inference Guided Feature Generation for Generalized Zero-Shot Learning
Inference Guided Feature Generation for Generalized Zero-Shot Learning
Neurocomputing
Autoencoder-Based Latent Block-Diagonal Representation for Subspace Clustering
Autoencoder-Based Latent Block-Diagonal Representation for Subspace Clustering
IEEE Transactions on Cybernetics
Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
CVPR