{"total":24,"rows":[{"id":"2312.12470","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","created":"2023-12-19","cited_by_count":76,"area":null},{"id":"2408.14180","title":"I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing","created":"2024-08-26","cited_by_count":63,"area":null},{"id":"2401.10090","title":"Cross-Modality Perturbation Synergy Attack for Person Re-identification","created":"2024-01-18","cited_by_count":45,"area":null},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37,"area":null},{"id":"2407.05363","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2306.07532","title":"Referring Camouflaged Object Detection","created":"2023-06-13","cited_by_count":19,"area":null},{"id":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18,"area":null},{"id":"2412.16919","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","created":"2024-12-22","cited_by_count":16,"area":null},{"id":"2503.12929","title":"AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction","created":"2025-03-17","cited_by_count":15,"area":null},{"id":"2405.00954","title":"X-Oscar: A Progressive Framework for High-quality Text-guided 3D Animatable Avatar Generation","created":"2024-05-02","cited_by_count":5,"area":null},{"id":"2407.04958","title":"Entropy-Informed Weighting Channel Normalizing Flow for Deep Generative Models","created":"2024-07-06","cited_by_count":5,"area":null},{"id":"2408.07605","title":"Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2406.00334","title":"Image Captioning via Dynamic Path Customization","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2409.06224","title":"MIP-GAF: A MLLM-annotated Benchmark for Most Important Person Localization and Group Context Understanding","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2412.16553","title":"Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers","created":"2024-12-21","cited_by_count":3,"area":null},{"id":"2412.19155","title":"Referencing Where to Focus: Improving VisualGrounding with Referential Query","created":"2024-12-26","cited_by_count":2,"area":null},{"id":"2501.14828","title":"An Ensemble Model with Attention Based Mechanism for Image Captioning","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2506.01370","title":"PointT2I: LLM-based text-to-image generation via keypoints","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2506.05399","title":"Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2606.04373","title":"Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2508.06853","title":"AGIC: Attention-Guided Image Captioning to Improve Caption Relevance","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2508.07318","title":"RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2605.28604","title":"Mining Multi-Modality Spatio-Temporal Cues for Video Important Person Identification","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.15570","title":"An Extensive Benchmark for Single-round and Multi-round Instruction-based Image Editing","created":"2026-06-14","cited_by_count":0,"area":null}],"next_cursor":null}