{"total":54,"rows":[{"id":"2407.12705","title":"IMAGDressing-v1: Customizable Virtual Dressing","created":"2024-07-17","cited_by_count":100,"area":"diffusion"},{"id":"2412.12974","title":"Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance","created":"2024-12-17","cited_by_count":63,"area":"diffusion"},{"id":"2410.11795","title":"Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices","created":"2024-10-15","cited_by_count":41,"area":"diffusion"},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2410.06244","title":"Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2503.00740","title":"FaceShot: Bring Any Character into Life","created":"2025-03-02","cited_by_count":13,"area":null},{"id":"2412.11578","title":"DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2506.15980","title":"Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization","created":"2025-06-19","cited_by_count":9,"area":"diffusion"},{"id":"2407.09774","title":"ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context","created":"2024-07-13","cited_by_count":8,"area":null},{"id":"2409.19608","title":"Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model","created":"2024-09-29","cited_by_count":6,"area":"diffusion"},{"id":"2412.11710","title":"Re-Attentional Controllable Video Diffusion Editing","created":"2024-12-16","cited_by_count":5,"area":"diffusion"},{"id":"2505.24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2501.16757","title":"ITVTON: Virtual Try-On Diffusion Transformer Based on Integrated Image and Text","created":"2025-01-28","cited_by_count":4,"area":"diffusion"},{"id":"2412.20725","title":"Dialogue Director: Bridging the Gap in Dialogue Visualization for Multimodal Storytelling","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2501.17983","title":"Efficient Feature Fusion for UAV Object Detection","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2504.16016","title":"Efficient Temporal Consistency in Diffusion-Based Video Editing with Adaptor Modules: A Theoretical Framework","created":"2025-04-22","cited_by_count":2,"area":"diffusion"},{"id":"2410.02528","title":"HiFiSeg: High-Frequency Information Enhanced Polyp Segmentation with Global-Local Vision Transformer","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2412.09817","title":"Enhancing Multimodal Large Language Models Complex Reason via Similarity Computation","created":"2024-12-13","cited_by_count":1,"area":"lr"},{"id":"2501.03700","title":"AuxDepthNet: Real-Time Monocular 3D Object Detection with Depth-Sensitive Features","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2501.15063","title":"Cross-modal Context Fusion and Adaptive Graph Convolutional Network for Multimodal Conversational Emotion Recognition","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2502.19200","title":"HDM: Hybrid Diffusion Model for Unified Image Anomaly Detection","created":"2025-02-26","cited_by_count":1,"area":"diffusion"},{"id":"2503.21208","title":"An improved EfficientNetV2 for garbage classification","created":"2025-03-27","cited_by_count":1,"area":null},{"id":"2503.24387","title":"CoCoIns: Consistent Subject Generation via Contrastive Instantiated Concepts","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.23365","title":"MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.04509","title":"MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization","created":"2025-07-06","cited_by_count":1,"area":"mllm"},{"id":"2604.18575","title":"ReCap: Lightweight Referential Grounding for Coherent Story Visualization","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.02042","title":"Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks","created":"2026-06-01","cited_by_count":1,"area":"diffusion"},{"id":"2407.15066","title":"LSReGen: Large-Scale Regional Generator via Backward Guidance Framework","created":"2024-07-21","cited_by_count":0,"area":null},{"id":"2409.04958","title":"DDNet: Deformable Convolution and Dense FPN for Surface Defect Detection in Recycled Books","created":"2024-09-08","cited_by_count":0,"area":null},{"id":"2411.12547","title":"S3TU-Net: Structured Convolution and Superpixel Transformer for Lung Nodule Segmentation","created":"2024-11-19","cited_by_count":0,"area":null},{"id":"2411.13997","title":"Mirror Target YOLO: An Improved YOLOv8 Method with Indirect Vision for Heritage Buildings Fire Detection","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2412.03200","title":"Fab-ME: A Vision State-Space and Attention-Enhanced Framework for Fabric Defect Detection","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2501.02811","title":"First-place Solution for Streetscape Shop Sign Recognition Competition","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2501.06053","title":"Enhancing, Refining, and Fusing: Towards Robust Multi-Scale and Dense Ship Detection","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2501.14190","title":"High-Precision Fabric Defect Detection via Adaptive Shape Convolutions and Large Kernel Spatial Modeling","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2502.11338","title":"WRT-SAM: Foundation Model-Driven Segmentation for Generalized Weld Radiographic Testing","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2503.00521","title":"2DMCG:2DMambawith Change Flow Guidance for Change Detection in Remote Sensing","created":"2025-03-01","cited_by_count":0,"area":"ssm"},{"id":"2504.00759","title":"MSSFC-Net:Enhancing Building Interpretation with Multi-Scale Spatial-Spectral Feature Collaboration","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2504.01326","title":"CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection","created":"2025-04-02","cited_by_count":0,"area":null},{"id":"2504.13224","title":"ICAS: IP Adapter and ControlNet-based Attention Structure for Multi-Subject Style Transfer Optimization","created":"2025-04-17","cited_by_count":0,"area":"diffusion"},{"id":"2505.06117","title":"Photovoltaic Defect Image Generator with Boundary Alignment Smoothing Constraint for Domain Shift Mitigation","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2506.11913","title":"O2Former:Direction-Aware and Multi-Scale Query Enhancement for SAR Ship Instance Segmentation","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2506.23252","title":"DGE-YOLO: Dual-Branch Gathering and Attention for Accurate UAV Object Detection","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2506.23295","title":"DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-On","created":"2025-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2507.00789","title":"OptiPrune: Boosting Prompt-Image Consistency with Attention-Guided Noise and Dynamic Token Selection","created":"2025-07-01","cited_by_count":0,"area":"diffusion"},{"id":"2508.02043","title":"Conditional Diffusion Model with Anatomical-Dose Dual Constraints for End-to-End Multi-Tumor Dose Prediction","created":"2025-08-04","cited_by_count":0,"area":"diffusion"},{"id":"2508.10397","title":"PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection","created":"2025-08-14","cited_by_count":0,"area":"mllm"},{"id":"2601.02038","title":"AlignVTOFF: Texture-Spatial Feature Alignment for High-Fidelity Virtual Try-Off","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2602.03914","title":"Causal Discovery for Cross-Sectional Data Based on Super-Structure and Divide-and-Conquer","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.10710","title":"FGAA-FPN: Foreground-Guided Angle-Aware Feature Pyramid Network for Oriented Object Detection","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.23820","title":"RSTNet: Enhancing Small-Target Recognition in Noisy SAR Imagery via Robust Feature Learning and Distribution-Aware Regression","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.14540","title":"WILD-SAM: Phase-Aware Expert Adaptation of SAM for Landslide Detection in Wrapped InSAR Interferograms","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.17051","title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.20667","title":"LER-YOLO: Reliability-Aware Expert Routing for Misaligned RGB-Infrared UAV Detection","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":null}