{"total":32,"rows":[{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63,"area":null},{"id":"2304.01091","title":"Changes to Captions: An Attentive Network for Remote Sensing Change Captioning","created":"2023-04-03","cited_by_count":41,"area":null},{"id":"2303.00355","title":"Progressive Scale-aware Network for Remote sensing Image Change Captioning","created":"2023-03-01","cited_by_count":27,"area":null},{"id":"2409.08582","title":"ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning","created":"2024-09-13","cited_by_count":23,"area":null},{"id":"2309.16283","title":"Self-supervised Cross-view Representation Reconstruction for Change Captioning","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2308.10417","title":"The Change You Want to See (Now in 3D)","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2303.03171","title":"Neighborhood Contrastive Transformer for Change Captioning","created":"2023-03-06","cited_by_count":16,"area":null},{"id":"2312.15311","title":"Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioning","created":"2023-12-23","cited_by_count":14,"area":null},{"id":"2404.05215","title":"Spatio-Temporal Attention and Gaussian Processes for Personalized Video Gaze Estimation","created":"2024-04-08","cited_by_count":12,"area":null},{"id":"2503.11093","title":"OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2405.20810","title":"Context-aware Difference Distilling for Multi-change Captioning","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2207.11118","title":"Rethinking the Reference-based Distinctive Image Captioning","created":"2022-07-22","cited_by_count":8,"area":null},{"id":"2410.10047","title":"ChangeMinds: Multi-task Framework for Detecting and Describing Changes in Remote Sensing","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2312.02751","title":"C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRF","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2407.11683","title":"Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2306.14259","title":"Improving Reference-based Distinctive Image Captioning with Contrastive Rewards","created":"2023-06-25","cited_by_count":4,"area":null},{"id":"2410.23946","title":"MV-CC: Mask Enhanced Video Model for Remote Sensing Change Caption","created":"2024-10-31","cited_by_count":3,"area":null},{"id":"2412.15939","title":"Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2505.16624","title":"Grounding Chest X-Ray Visual Question Answering with Generated Radiology Reports","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2511.21420","title":"SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2606.27410","title":"DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning","created":"2026-06-25","cited_by_count":2,"area":null},{"id":"2506.02976","title":"Deep Learning for Retinal Degeneration Assessment: A Comprehensive Analysis of the MARIO Challenge","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2603.05969","title":"Imagine How To Change: Explicit Procedure Modeling for Change Captioning","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2605.04409","title":"UAV as Urban Construction Change Monitor: A New Benchmark and Change Captioning Model","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2505.08426","title":"DHECA-SuperGaze: Dual Head-Eye Cross-Attention and Super-Resolution for Unconstrained Gaze Estimation","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2509.25374","title":"Saliency Guided Longitudinal Medical Visual Question Answering","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2606.06534","title":"Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foundation Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.25445","title":"C3-Bench: A Context-Aware Change Captioning Benchmark","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.01728","title":"Beyond Pixel Diffs: Benchmarking Image Change Captioning for Web UI Visual Regression Testing","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.12502","title":"HIMEC: Directional Change Representation and Fixed-Interface Decoding for Remote Sensing Image Change Captioning","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.01136","title":"Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}