{"total":62,"rows":[{"id":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400,"area":null},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267,"area":null},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2103.14146","title":"Describing and Localizing Multiple Changes with Transformers","created":"2021-03-25","cited_by_count":47,"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":"2202.04298","title":"Image Difference Captioning with Pre-training and Contrastive Learning","created":"2022-02-09","cited_by_count":39,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2206.00629","title":"CLIP4IDC: CLIP for Image Difference Captioning","created":"2022-06-01","cited_by_count":25,"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":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19,"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":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","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":"2409.12612","title":"Enhancing Perception of Key Changes in Remote Sensing Image Change Captioning","created":"2024-09-19","cited_by_count":16,"area":null},{"id":"2407.05645","title":"OneDiff: A Generalist Model for Image Difference Captioning","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2503.07860","title":"Video Action Differencing","created":"2025-03-10","cited_by_count":14,"area":null},{"id":"2411.11360","title":"CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset","created":"2024-11-18","cited_by_count":13,"area":null},{"id":"2104.01703","title":"FixMyPose: Pose Correctional Captioning and Retrieval","created":"2021-04-04","cited_by_count":12,"area":null},{"id":"2110.10328","title":"R$^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning","created":"2021-10-20","cited_by_count":12,"area":null},{"id":"2402.19119","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","created":"2024-02-29","cited_by_count":12,"area":null},{"id":"2412.03911","title":"Multi-View Pose-Agnostic Change Localization with Zero Labels","created":"2024-12-05","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":"2110.01839","title":"Truth-Conditional Captioning of Time Series Data","created":"2021-10-05","cited_by_count":11,"area":null},{"id":"2404.16222","title":"Step Differences in Instructional Video","created":"2024-04-24","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2207.07568","title":"Reasoning about Actions over Visual and Linguistic Modalities: A Survey","created":"2022-07-15","cited_by_count":10,"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":"2102.01860","title":"L2C: Describing Visual Differences Needs Semantic Understanding of Individuals","created":"2021-02-03","cited_by_count":8,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2210.11109","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","created":"2022-10-20","cited_by_count":6,"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":"2204.11004","title":"Training and challenging models for text-guided fashion image retrieval","created":"2022-04-23","cited_by_count":5,"area":null},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2502.16941","title":"Gaussian Difference: Find Any Change Instance in 3D Scenes","created":"2025-02-24","cited_by_count":5,"area":null},{"id":"2509.19245","title":"ConViS-Bench: Estimating Video Similarity Through Semantic Concepts","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2410.00436","title":"Task Success Prediction for Open-Vocabulary Manipulation Based on Multi-Level Aligned Representations","created":"2024-10-01","cited_by_count":3,"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":"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":"2209.14341","title":"The Change You Want to See","created":"2022-09-28","cited_by_count":2,"area":null},{"id":"2401.10805","title":"Learning to Visually Connect Actions and their Effects","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2512.03405","title":"ViDiC: Video Difference Captioning","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2607.29585","title":"Sycophancy Undermines Epistemic Vigilance in Cooperative Vision-Language Tasks","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2504.01952","title":"Image Difference Grounding with Natural Language","created":"2025-04-02","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":"2605.04503","title":"DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2203.08362","title":"Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2408.12945","title":"Find the Assembly Mistakes: Error Segmentation for Industrial Applications","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2603.12832","title":"Hierarchical Dual-Change Collaborative Learning for UAV Scene Change Captioning","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","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":"2606.31745","title":"JL1-CC&QA: Extending the JL1-CD Benchmark with Change Captioning and Question Answering","created":"2026-06-30","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":"2607.12752","title":"Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation","created":"2026-07-14","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},{"id":"2609.10356","title":"Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}