Yan Zhang

47

Papers

193

Total Citations

1

Affiliations

Affiliations

Samsung - SAIT AI Lab, Montreal

Papers (47)

Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

EgoGen: An Egocentric Synthetic Data Generator

DiffAIL: Diffusion Adversarial Imitation Learning

CoA: Towards Real Image Dehazing via Compression-and-Adaptation

RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method

Feature Denoising Diffusion Model for Blind Image Quality Assessment

PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning

Degrees of Freedom Matter: Inferring Dynamics from Point Trajectories

UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models

A Theory for Conditional Generative Modeling on Multiple Data Sources

BUFF: Bayesian Uncertainty Guided Diffusion Probabilistic Model for Single Image Super-Resolution

Towards Macro-AUC Oriented Imbalanced Multi-Label Continual Learning

PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation

Local Temporal Bilinear Pooling for Fine-Grained Action Parsing

Generating 3D People in Scenes Without People

LEAP: Learning Articulated Occupancy of People

We Are More Than Our Joints: Predicting How 3D Bodies Move

The Wanderings of Odysseus in 3D Scenes

Truncating Wide Networks Using Binary Tree Architectures

Visualization of Convolutional Neural Networks for Monocular Depth Estimation

SerialGen: Personalized Image Generation by First Standardization Then Personalization

Learning Motion Priors for 4D Human Body Capture in 3D Scenes

Synthesizing Diverse Human Motions in 3D Indoor Scenes

Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views

EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices

SAGA: Stochastic Whole-Body Grasping with Contact

Compositional Human-Scene Interaction Synthesis with Semantic Control

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion

Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment

ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection

X-Mask: Improving Soft-Edge Occlusion in Optical See-Through Displays with Cross-Shaped Pinholes

Learning Concept Prerequisite Relation via Global Knowledge Relation Optimization

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues

APKGC: Noise-enhanced Multi-Modal Knowledge Graph Completion with Attention Penalty

Semi-supervised Blind Image Quality Assessment through Knowledge Distillation and Incremental Learning

LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes

Unsupervised Concept Discovery Mitigates Spurious Correlations

Improved Generalization of Weight Space Networks via Augmentations

Integrating Global Context Contrast and Local Sensitivity for Blind Image Quality Assessment

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity

Feature Quantization for Defending Against Distortion of Images

Deep Set Prediction Networks

Better Set Representations For Relational Reasoning

Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments