{"total":17,"rows":[{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2312.02142","title":"Object Recognition as Next Token Prediction","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2502.06593","title":"SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2312.04402","title":"Semi-Supervised Active Learning for Semantic Segmentation in Unknown Environments Using Informative Path Planning","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2504.14446","title":"Neglected Risks: The Disturbing Reality of Children's Images in Datasets and the Urgent Call for Accountability","created":"2025-04-20","cited_by_count":6,"area":null},{"id":"2402.05917","title":"Point-VOS: Pointing Up Video Object Segmentation","created":"2024-02-08","cited_by_count":5,"area":null},{"id":"2303.17595","title":"Neglected Free Lunch -- Learning Image Classifiers Using Annotation Byproducts","created":"2023-03-30","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2409.16736","title":"Commonly Interesting Images","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2505.01431","title":"ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2412.04591","title":"Aberration Correcting Vision Transformers for High-Fidelity Metalens Imaging","created":"2024-12-05","cited_by_count":1,"area":null},{"id":"2506.22531","title":"Preserve Anything: Controllable Image Synthesis with Object Preservation","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2605.29212","title":"MetaRanker: Human-in-the-loop Active Ranking for Metalens Image Quality","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2505.15628","title":"SNAP: A Benchmark for Testing the Effects of Capture Conditions on Fundamental Vision Tasks","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2508.14707","title":"Seeing Further on the Shoulders of Giants: Knowledge Inheritance for Vision Foundation Models","created":"2025-08-20","cited_by_count":0,"area":null},{"id":"2509.21365","title":"MAJORScore: A Novel Metric for Evaluating Multimodal Relevance via Joint Representation","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2606.10892","title":"Improving Text-Instance Alignment Of Foreground Conditioned Out-Painting Via Customized Concept Embedding","created":"2026-06-09","cited_by_count":0,"area":null}],"next_cursor":null}