Xiatian Zhu

Adaptive Diffusion-based Augmentation for Recommendation AAAI 2026 EthoCLIP: Ontology-Enhanced Video-Language Pretraining for Animal Behavior Understanding CVPR 2026 RAID: Retrieval-Augmented Anomaly Detection CVPR 2026 SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving CVPR 2026 Bayesian Test-Time Adaptation for Vision-Language Models CVPR 2025 CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering ICML 2025 Domain Adaptive Diabetic Retinopathy Grading with Model Absence and Flowing Data CVPR 2025 Driving View Synthesis on Free-form Trajectories with Generative Prior ICCV 2025 FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion CVPR 2025 High Dynamic Range Novel View Synthesis with Single Exposure ICML 2025 Improving Gaussian Splatting with Localized Points Management CVPR 2025 Multi-modal Multi-platform Person Re-Identification: Benchmark and Method ICCV 2025 OmniCount: Multi-label Object Counting with Semantic-Geometric Priors AAAI 2025 Proxy Denoising for Source-Free Domain Adaptation ICLR 2025 Reflective Gaussian Splatting ICLR 2025 Robust Low-light Scene Restoration via Illumination Transition ICCV 2025 SEBRA : Debiasing through Self-Guided Bias Ranking ICLR 2025 Self-Prompting Analogical Reasoning for UAV Object Detection AAAI 2025 TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering CVPR 2025 Unsupervised Audio-Visual Segmentation with Modality Alignment AAAI 2025 AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis NeurIPS 2024 Bayesian Detector Combination for Object Detection with Crowdsourced Annotations ECCV 2024 Cloud Object Detector Adaptation by Integrating Different Source Knowledge NeurIPS 2024 DiffSED: Sound Event Detection with Denoising Diffusion AAAI 2024 Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping ICLR 2024 Motion Forecasting in Continuous Driving NeurIPS 2024 PartCraft: Crafting Creative Objects by Parts ECCV 2024 Recognize Any Regions NeurIPS 2024 Source-Free Domain Adaptation with Frozen Multimodal Foundation Model CVPR 2024 Tetrahedron Splatting for 3D Generation NeurIPS 2024 Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion ICCV 2023 DeepChange: A Long-Term Person Re-Identification Benchmark with Clothes Change ICCV 2023 DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion ICCV 2023 FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks CVPR 2023 Generative Semantic Segmentation CVPR 2023 HeadSculpt: Crafting 3D Head Avatars with Text NeurIPS 2023 Homeomorphism Alignment for Unsupervised Domain Adaptation ICCV 2023 Independent Feature Decomposition and Instance Alignment for Unsupervised Domain Adaptation IJCAI 2023 PolarFormer: Multi-Camera 3D Object Detection with Polar Transformer AAAI 2023 Post-Processing Temporal Action Detection CVPR 2023 Accelerating Score-Based Generative Models with Preconditioned Diffusion Sampling ECCV 2022 DeepInteraction: 3D Object Detection via Modality Interaction NeurIPS 2022 EdgeViTs: Competing Light-Weight CNNs on Mobile Devices with Vision Transformers ECCV 2022 FashionViL: Fashion-Focused Vision-and-Language Representation Learning ECCV 2022 KUNet: Imaging Knowledge-Inspired Single HDR Image Reconstruction IJCAI 2022 Learning Ego 3D Representation As Ray Tracing ECCV 2022 MetaTeacher: Coordinating Multi-Model Domain Adaptation for Medical Image Classification NeurIPS 2022 Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning ECCV 2022 Semi-Supervised Temporal Action Detection with Proposal-Free Masking ECCV 2022 SOS! Self-Supervised Learning over Sets of Handled Objects in Egocentric Action Recognition ECCV 2022 Source-Free Object Detection by Learning To Overlook Domain Style CVPR 2022 ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning NeurIPS 2022 Zero-Shot Temporal Action Detection via Vision-Language Prompting ECCV 2022 Boundary-Sensitive Pre-Training for Temporal Localization in Videos ICCV 2021 Low-Fidelity Video Encoder Optimization for Temporal Action Localization NeurIPS 2021 Rethinking Semantic Segmentation From a Sequence-to-Sequence Perspective With Transformers CVPR 2021 Simpler Is Better: Few-Shot Semantic Segmentation With Classifier Weight Transformer ICCV 2021 SOFT: Softmax-free Transformer with Linear Complexity NeurIPS 2021 Characteristic Regularisation for Super-Resolving Face Images WACV 2020 Deep Semantic Clustering by Partition Confidence Maximisation CVPR 2020 Distribution-Aware Coordinate Representation for Human Pose Estimation CVPR 2020 Incremental Few-Shot Object Detection CVPR 2020 Inter-Task Association Critic for Cross-Resolution Person Re-Identification CVPR 2020 Neural Graph Embedding for Neural Architecture Search AAAI 2020 Semi-Supervised Learning under Class Distribution Mismatch AAAI 2020 Stochastic Classifiers for Unsupervised Domain Adaptation CVPR 2020 Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification AAAI 2020 Unsupervised Deep Learning via Affinity Diffusion AAAI 2020 Fast Human Pose Estimation CVPR 2019 Instance-Guided Context Rendering for Cross-Domain Person Re-Identification ICCV 2019 Person Search by Text Attribute Query As Zero-Shot Learning ICCV 2019 Single-Label Multi-Class Image Classification by Deep Logistic Regression AAAI 2019 Unsupervised Deep Learning by Neighbourhood Discovery ICML 2019 Harmonious Attention Network for Person Re-Identification CVPR 2018 Knowledge Distillation by On-the-Fly Native Ensemble NeurIPS 2018 Person Search by Multi-Scale Matching ECCV 2018 Semi-Supervised Deep Learning with Memory ECCV 2018 Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification CVPR 2018 Unsupervised Person Re-identification by Deep Learning Tracklet Association ECCV 2018 Attribute Recognition by Joint Recurrent Learning of Context and Correlation ICCV 2017 Class Rectification Hard Mining for Imbalanced Deep Learning ICCV 2017 Person Re-Identification by Deep Joint Learning of Multi-Loss Classification IJCAI 2017 Constructing Robust Affinity Graphs for Spectral Clustering CVPR 2014 Video Synopsis by Heterogeneous Multi-source Correlation ICCV 2013