{"arxiv_id":"2403.17886","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":10,"sentences":19,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":3,"sentences":4,"quotes":[{"arxiv_id":"1611.01704","title":"End-to-end Optimized Image Compression","url":"/paper/1611.01704","section":"METHOD","sentence":"In this section, we frame our method as the optimization of a rate-distortion objective following the framework of end-to-end learned compression established in Balle et al. [ref] .","intent_p":0.96,"contests_p":null},{"arxiv_id":"2011.03029","title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research","url":"/paper/2011.03029","section":"METHOD","sentence":"Specifically, we leverage the implementation in the CompressAI [ref] library.","intent_p":1.0,"contests_p":null},{"arxiv_id":"2306.06842","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","url":"/paper/2306.06842","section":"EXPERIMENTS","sentence":"We process it as is standard [ref] , obtaining tiles of size $512 ×512$.","intent_p":0.87,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":9,"sentences":11,"quotes":[{"arxiv_id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","url":"/paper/1812.00101","section":"INTRODUCTION","sentence":"In this study, we propose the application of learned neural compression, which has been well studied in the domain of image and video compression [ref] .","intent_p":0.85,"contests_p":null},{"arxiv_id":"1611.01704","title":"End-to-end Optimized Image Compression","url":"/paper/1611.01704","section":"INTRODUCTION","sentence":"In this study, we propose the application of learned neural compression, which has been well studied in the domain of image and video compression [ref] .","intent_p":0.85,"contests_p":null},{"arxiv_id":"2306.05704","title":"Exploring Effective Mask Sampling Modeling for Neural Image Compression","url":"/paper/2306.05704","section":"RELATED WORK","sentence":"Recently, some works have leveraged masked auto-encoding (MAE) as a lossy compression method, dropping data at the image patch [ref] or embedding level [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2306.15561","title":"You Can Mask More For Extremely Low-Bitrate Image Compression","url":"/paper/2306.15561","section":"RELATED WORK","sentence":"Recently, some works have leveraged masked auto-encoding (MAE) as a lossy compression method, dropping data at the image patch [ref] or embedding level [ref] .","intent_p":0.93,"contests_p":null},{"arxiv_id":"2306.06842","title":"AerialFormer: Multi-resolution Transformer for Aerial Image Segmentation","url":"/paper/2306.06842","section":"EXPERIMENTS","sentence":"Most state-of-the-art models for semantic segmentation [ref] combine embeddings from different stages of the encoder.","intent_p":0.86,"contests_p":null}]}],"unlabelled_sentences":4},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2403.17886"}}