Xiangyang Xue

48

Papers

100

Total Citations

Papers (48)

Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning

Generating and Reweighting Dense Contrastive Patterns for Unsupervised Anomaly Detection

ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning

MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model

Enhancing Cross-Subject fMRI-to-Video Decoding with Global-Local Functional Alignment

ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models

Spatial-Temporal Aware Visuomotor Diffusion Policy Learning

Weakly Supervised Semantic Segmentation for Social Images

Weakly Supervised Dense Video Captioning

Dual Skipping Networks

Towards Instance-Level Image-To-Image Translation

Neural Pose Transfer by Spatially Adaptive Instance Normalization

Sketch-BERT: Learning Sketch Bidirectional Encoder Representation From Transformers by Self-Supervised Learning of Sketch Gestalt

FM2u-Net: Face Morphological Multi-Branch Network for Makeup-Invariant Face Verification

Delving into Data: Effectively Substitute Training for Black-box Attack

Learning Dynamic Alignment via Meta-Filter for Few-Shot Learning

Learning Compositional Representation for 4D Captures With Neural ODE

Scene Text Telescope: Text-Focused Scene Image Super-Resolution

Depth-Conditioned Dynamic Message Propagation for Monocular 3D Object Detection

Density-Preserving Deep Point Cloud Compression

H4D: Human 4D Modeling by Learning Neural Compositional Representation

DST: Dynamic Substitute Training for Data-Free Black-Box Attack

SAR-Net: Shape Alignment and Recovery Network for Category-Level 6D Object Pose and Size Estimation

Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent With Learned Distance Functions

Multiple Granularity Descriptors for Fine-Grained Categorization

Towards 3D Human Pose Estimation in the Wild: A Weakly-Supervised Approach

DSOD: Learning Deeply Supervised Object Detectors From Scratch

Multi-Scale Deep Learning Architectures for Person Re-Identification

Towards Enhanced Image Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistency

The Devil Is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Learning Versatile 3D Shape Generation with Improved Auto-regressive Models

PourIt!: Weakly-Supervised Liquid Perception from a Single Image for Visual Closed-Loop Robotic Pouring

DeepSFM: Structure From Motion Via Deep Bundle Adjustment

LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling

RCLane: Relay Chain Prediction for Lane Detection

SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation

CocoER: Aligning Multi-Level Feature by Competition and Coordination for Emotion Recognition

CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image

Foundation Model Driven Appearance Extraction for Robust Multiple Object Tracking

PC-BEV: An Efficient Polar-Cartesian BEV Fusion Framework for LiDAR Semantic Segmentation

Exploring One-Shot Semi-supervised Federated Learning with Pre-trained Diffusion Models

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

Is normalization indispensable for training deep neural network?

Progressive Coordinate Transforms for Monocular 3D Object Detection

The Image Local Autoregressive Transformer

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Generative Modeling of Infinite Occluded Objects for Compositional Scene Representation