{"total":18,"rows":[{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2308.10133","title":"TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Security","created":"2023-08-20","cited_by_count":22,"area":null},{"id":"2306.00238","title":"Bytes Are All You Need: Transformers Operating Directly On File Bytes","created":"2023-05-31","cited_by_count":18,"area":null},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13,"area":null},{"id":"2404.05558","title":"JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients","created":"2024-04-03","cited_by_count":7,"area":null},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2405.17146","title":"Compressed-Language Models for Understanding Compressed File Formats: a JPEG Exploration","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2503.00782","title":"Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation","created":"2025-03-02","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2304.04518","title":"Are Visual Recognition Models Robust to Image Compression?","created":"2023-04-10","cited_by_count":2,"area":null},{"id":"2411.13040","title":"RobustFormer: Noise-Robust Pre-training for images and videos","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2512.12774","title":"Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior","created":"2025-12-14","cited_by_count":2,"area":null},{"id":"2404.12330","title":"A Perspective on Deep Vision Performance with Standard Image and Video Codecs","created":"2024-04-18","cited_by_count":1,"area":null},{"id":"2506.21171","title":"Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2506.23532","title":"GViT: Representing Images as Gaussians for Visual Recognition","created":"2025-06-30","cited_by_count":1,"area":null},{"id":"2507.23521","title":"JPEG Processing Neural Operator for Backward-Compatible Coding","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2510.23665","title":"Transformers from Compressed Representations","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2512.04284","title":"Learning Single-Image Super-Resolution in the JPEG Compressed Domain","created":"2025-12-03","cited_by_count":0,"area":null}],"next_cursor":null}