{"list":"other","total":54,"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"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":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"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":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"1804.02958","title":"Generative Adversarial Networks for Extreme Learned Image Compression","created":"2018-04-09","cited_by_count":219},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"1608.05148","title":"Full Resolution Image Compression with Recurrent Neural Networks","created":"2016-08-18","cited_by_count":175},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"1801.04260","title":"Conditional Probability Models for Deep Image Compression","created":"2018-01-12","cited_by_count":133},{"id":"1909.04802","title":"Variable Rate Deep Image Compression With a Conditional Autoencoder","created":"2019-09-11","cited_by_count":114},{"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":"2001.03569","title":"Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics","created":"2020-01-10","cited_by_count":80},{"id":"2212.13824","title":"Multi-Realism Image Compression with a Conditional Generator","created":"2022-12-28","cited_by_count":80},{"id":"2107.08373","title":"Scalable Image Coding for Humans and Machines","created":"2021-07-18","cited_by_count":66},{"id":"2111.06707","title":"Transformer-based Image Compression","created":"2021-11-12","cited_by_count":62},{"id":"2108.09551","title":"Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform","created":"2021-08-21","cited_by_count":58},{"id":"2310.16387","title":"Frequency-Aware Transformer for Learned Image Compression","created":"2023-10-25","cited_by_count":58},{"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":"1912.05526","title":"Variable Rate Deep Image Compression with Modulated Autoencoder","created":"2019-12-11","cited_by_count":40},{"id":"2306.05085","title":"TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception","created":"2023-06-08","cited_by_count":32},{"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":"2011.06409","title":"End-to-end optimized image compression for machines, a study","created":"2020-11-10","cited_by_count":30},{"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":"2407.09853","title":"Image Compression for Machine and Human Vision with Spatial-Frequency Adaptation","created":"2024-07-13","cited_by_count":26},{"id":"2106.03511","title":"Task-driven Semantic Coding via Reinforcement Learning","created":"2021-06-07","cited_by_count":25},{"id":"2111.13475","title":"QMagFace: Simple and Accurate Quality-Aware Face Recognition","created":"2021-11-26","cited_by_count":25},{"id":"1704.08141","title":"Compact Descriptors for Video Analysis: the Emerging MPEG Standard","created":"2017-04-26","cited_by_count":20},{"id":"2206.05650","title":"Preprocessing Enhanced Image Compression for Machine Vision","created":"2022-06-12","cited_by_count":18},{"id":"2405.16817","title":"Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model","created":"2024-05-27","cited_by_count":17},{"id":"2309.03244","title":"EGIC: Enhanced Low-Bit-Rate Generative Image Compression Guided by Semantic Segmentation","created":"2023-09-06","cited_by_count":14},{"id":"2209.01355","title":"Semantic Segmentation in Learned Compressed Domain","created":"2022-09-03","cited_by_count":10},{"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":"2305.02578","title":"Prompt-ICM: A Unified Framework towards Image Coding for Machines with Task-driven Prompts","created":"2023-05-04","cited_by_count":7}],"next_cursor":null}