{"list":"other","total":57,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1807.11626","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","created":"2018-07-31","cited_by_count":943},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1808.08750","title":"Generalisation in humans and deep neural networks","created":"2018-08-27","cited_by_count":237},{"id":"1604.04004","title":"Understanding How Image Quality Affects Deep Neural Networks","created":"2016-04-14","cited_by_count":119},{"id":"1904.03567","title":"Image and Video Compression with Neural Networks: A Review","created":"2019-04-07","cited_by_count":86},{"id":"2107.08373","title":"Scalable Image Coding for Humans and Machines","created":"2021-07-18","cited_by_count":66},{"id":"2002.03711","title":"Learning End-to-End Lossy Image Compression: A Benchmark","created":"2020-02-10","cited_by_count":60},{"id":"1803.06131","title":"Towards Image Understanding from Deep Compression without Decoding","created":"2018-03-16","cited_by_count":52},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52},{"id":"2008.06091","title":"A Technical Overview of AV1","created":"2020-08-13","cited_by_count":47},{"id":"1701.01500","title":"VideoSet: A Large-Scale Compressed Video Quality Dataset Based on JND Measurement","created":"2017-01-05","cited_by_count":33},{"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":"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":"2112.09300","title":"Towards End-to-End Image Compression and Analysis with Transformers","created":"2021-12-17","cited_by_count":26},{"id":"2106.03511","title":"Task-driven Semantic Coding via Reinforcement Learning","created":"2021-06-07","cited_by_count":25},{"id":"1710.11151","title":"High efficiency compression for object detection","created":"2017-10-30","cited_by_count":24},{"id":"2104.10315","title":"Visual Analysis Motivated Rate-Distortion Model for Image Coding","created":"2021-04-21","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":"2102.08168","title":"Just Noticeable Difference for Deep Machine Vision","created":"2021-02-16","cited_by_count":19},{"id":"2105.10089","title":"Latent-space scalability for multi-task collaborative intelligence","created":"2021-05-21","cited_by_count":17},{"id":"2108.05058","title":"Towards Top-Down Just Noticeable Difference Estimation of Natural Images","created":"2021-08-11","cited_by_count":15},{"id":"2011.04976","title":"Conceptual Compression via Deep Structure and Texture Synthesis","created":"2020-11-10","cited_by_count":14},{"id":"2105.12653","title":"Recent Standard Development Activities on Video Coding for Machines","created":"2021-05-26","cited_by_count":14},{"id":"2111.02249","title":"Learned Image Compression for Machine Perception","created":"2021-11-03","cited_by_count":14},{"id":"2110.09241","title":"Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics","created":"2021-10-18","cited_by_count":11},{"id":"1801.09468","title":"DeepSIC: Deep Semantic Image Compression","created":"2018-01-29","cited_by_count":10},{"id":"2112.12284","title":"A Survey on Perceptually Optimized Video Coding","created":"2021-12-23","cited_by_count":10},{"id":"2103.04178","title":"End-to-end optimized image compression for multiple machine tasks","created":"2021-03-06","cited_by_count":9},{"id":"1903.05921","title":"Scalable Facial Image Compression with Deep Feature Reconstruction","created":"2019-03-14","cited_by_count":8},{"id":"2203.05890","title":"Video Coding for Machines with Feature-Based Rate-Distortion Optimization","created":"2022-03-11","cited_by_count":8},{"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},{"id":"1910.07392","title":"Reinforced Bit Allocation under Task-Driven Semantic Distortion Metrics","created":"2019-10-16","cited_by_count":6},{"id":"2001.02002","title":"SUR-FeatNet: Predicting the Satisfied User Ratio Curvefor Image Compression with Deep Feature Learning","created":"2020-01-07","cited_by_count":3},{"id":"1710.11090","title":"Prediction of Satisfied User Ratio for Compressed Video","created":"2017-10-30","cited_by_count":2},{"id":"1807.00681","title":"Analysis and prediction of JND-based video quality model","created":"2018-06-28","cited_by_count":2},{"id":"2205.06519","title":"Evaluation of Video Coding for Machines without Ground Truth","created":"2022-05-13","cited_by_count":1}],"next_cursor":null}