{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1910.04751","title":"Panoptic-DeepLab","created":"2019-10-10","cited_by_count":363},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"1703.00395","title":"Lossy Image Compression with Compressive Autoencoders","created":"2017-03-01","cited_by_count":294},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"1804.02958","title":"Generative Adversarial Networks for Extreme Learned Image Compression","created":"2018-04-09","cited_by_count":219},{"id":"1704.00648","title":"Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations","created":"2017-04-03","cited_by_count":152},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"1801.04260","title":"Conditional Probability Models for Deep Image Compression","created":"2018-01-12","cited_by_count":133},{"id":"1705.05823","title":"Real-Time Adaptive Image Compression","created":"2017-05-16","cited_by_count":130},{"id":"1703.10114","title":"Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks","created":"2017-03-29","cited_by_count":92},{"id":"2006.04240","title":"Improving Inference for Neural Image Compression","created":"2020-06-07","cited_by_count":83},{"id":"1703.10553","title":"Learning Convolutional Networks for Content-weighted Image Compression","created":"2017-03-30","cited_by_count":76},{"id":"2011.09704","title":"Causal Contextual Prediction for Learned Image Compression","created":"2020-11-19","cited_by_count":73},{"id":"2104.05168","title":"Soft then Hard: Rethinking the Quantization in Neural Image Compression","created":"2021-04-12","cited_by_count":51},{"id":"2108.09993","title":"Image coding for machines: an end-to-end learned approach","created":"2021-08-23","cited_by_count":47},{"id":"2007.11797","title":"End-to-end Learning of Compressible Features","created":"2020-07-23","cited_by_count":43},{"id":"2001.02915","title":"Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach","created":"2020-01-09","cited_by_count":31},{"id":"2207.01932","title":"Image Coding for Machines with Omnipotent Feature Learning","created":"2022-07-05","cited_by_count":31},{"id":"1904.00664","title":"Learning Content-Weighted Deep Image Compression","created":"2019-04-01","cited_by_count":28},{"id":"2004.10043","title":"Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression","created":"2020-04-21","cited_by_count":28},{"id":"1806.03348","title":"DSSLIC: Deep Semantic Segmentation-based Layered Image Compression","created":"2018-06-08","cited_by_count":27},{"id":"2106.03511","title":"Task-driven Semantic Coding via Reinforcement Learning","created":"2021-06-07","cited_by_count":25},{"id":"2104.10315","title":"Visual Analysis Motivated Rate-Distortion Model for Image Coding","created":"2021-04-21","cited_by_count":21},{"id":"2108.09992","title":"Learned Image Coding for Machines: A Content-Adaptive Approach","created":"2021-08-23","cited_by_count":21},{"id":"1704.08141","title":"Compact Descriptors for Video Analysis: the Emerging MPEG Standard","created":"2017-04-26","cited_by_count":20},{"id":"2201.10162","title":"Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks","created":"2022-01-25","cited_by_count":7}],"next_cursor":null}