Lixin Duan

CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices AAAI 2026 Dynamic Logits Adjustment and Exploration for Test-Time Adaptation in Vision Language Models CVPR 2026 iSplat: Iterative Learning for Fine-Grained Gaussian Splatting CVPR 2026 The Devil is in Attention Sharing: Improving Complex Non-rigid Image Editing Faithfulness via Attention Synergy CVPR 2026 Balanced Sharpness-Aware Minimization for Imbalanced Regression ICCV 2025 GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation CVPR 2025 GL-LCM: Global-Local Latent Consistency Models for Fast High-Resolution Bone Suppression in Chest X-Ray Images MICCAI 2025 Leveraging Diffusion Models for Continual Test-Time Adaptation in Fundus Image Classification MICCAI 2025 LidarGait++: Learning Local Features and Size Awareness from LiDAR Point Clouds for 3D Gait Recognition CVPR 2025 ResCLIP: Residual Attention for Training-free Dense Vision-language Inference CVPR 2025 S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field AAAI 2025 The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning ICCV 2025 Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning AAAI 2024 Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation ECCV 2024 Cache-Driven Spatial Test-Time Adaptation for Cross-Modality Medical Image Segmentation MICCAI 2024 Diffusion-Enhanced Transformation Consistency Learning for Retinal Image Segmentation MICCAI 2024 Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction ECCV 2024 Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning ECCV 2024 Towards Unsupervised Model Selection for Domain Adaptive Object Detection NeurIPS 2024 Harmonious Teacher for Cross-Domain Object Detection CVPR 2023 Learning Motion Refinement for Unsupervised Face Animation NeurIPS 2023 Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks CVPR 2023 Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation AAAI 2022 Learning Pixel-Level Distinctions for Video Highlight Detection CVPR 2022 Motion and Appearance Adaptation for Cross-Domain Motion Transfer ECCV 2022 Motion Transformer for Unsupervised Image Animation ECCV 2022 Structure-Aware Motion Transfer With Deformable Anchor Model CVPR 2022 Undoing the Damage of Label Shift for Cross-Domain Semantic Segmentation CVPR 2022 BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-Domain Semantic Segmentation ICCV 2021 Progressive Modality Reinforcement for Human Multimodal Emotion Recognition From Unaligned Multimodal Sequences CVPR 2021 Unbiased Mean Teacher for Cross-Domain Object Detection CVPR 2021 Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction ECCV 2020 Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation EMNLP 2020 Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach ICCV 2019 Learning Transferable Self-Attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision AAAI 2019 Exploiting Images for Video Recognition with Hierarchical Generative Adversarial Networks IJCAI 2018 Learning User Dependencies for Recommendation IJCAI 2017 Event Recognition in Videos by Learning from Heterogeneous Web Sources CVPR 2013