{"list":"other","total":90,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"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":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"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":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1710.07035","title":"Generative Adversarial Networks: An Overview","created":"2017-10-19","cited_by_count":590},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"1606.00709","title":"f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization","created":"2016-06-02","cited_by_count":506},{"id":"2306.06546","title":"High-Fidelity Audio Compression with Improved RVQGAN","created":"2023-06-11","cited_by_count":431},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"1804.02815","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","created":"2018-04-09","cited_by_count":371},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"1612.02295","title":"Large-Margin Softmax Loss for Convolutional Neural Networks","created":"2016-12-07","cited_by_count":296},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"1612.06321","title":"Large-Scale Image Retrieval with Attentive Deep Local Features","created":"2016-12-19","cited_by_count":238},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210},{"id":"1608.05148","title":"Full Resolution Image Compression with Recurrent Neural Networks","created":"2016-08-18","cited_by_count":175},{"id":"1702.08502","title":"Understanding Convolution for Semantic Segmentation","created":"2017-02-27","cited_by_count":168},{"id":"1809.10452","title":"Context-adaptive Entropy Model for End-to-end Optimized Image Compression","created":"2018-09-27","cited_by_count":143},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"1710.01992","title":"Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks","created":"2017-10-04","cited_by_count":138},{"id":"1702.05374","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","created":"2017-02-17","cited_by_count":128},{"id":"1908.03851","title":"IoU Loss for 2D/3D Object Detection","created":"2019-08-11","cited_by_count":128},{"id":"1511.06281","title":"Density Modeling of Images using a Generalized Normalization Transformation","created":"2015-11-19","cited_by_count":127},{"id":"2303.10883","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","created":"2023-03-20","cited_by_count":114},{"id":"2305.18887","title":"How Does Information Bottleneck Help Deep Learning?","created":"2023-05-30","cited_by_count":93},{"id":"2006.02535","title":"A Survey on Deep Learning Techniques for Stereo-based Depth Estimation","created":"2020-06-01","cited_by_count":90},{"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":"2210.02192","title":"Are All Losses Created Equal: A Neural Collapse Perspective","created":"2022-10-04","cited_by_count":78},{"id":"2107.08373","title":"Scalable Image Coding for Humans and Machines","created":"2021-07-18","cited_by_count":66},{"id":"2003.09764","title":"Lifespan Age Transformation Synthesis","created":"2020-03-21","cited_by_count":60},{"id":"2303.08138","title":"Diversity-Aware Meta Visual Prompting","created":"2023-03-14","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":"2306.04050","title":"LLMZip: Lossless Text Compression using Large Language Models","created":"2023-06-06","cited_by_count":44},{"id":"2108.11510","title":"Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey","created":"2021-08-25","cited_by_count":43},{"id":"2204.12684","title":"Density-preserving Deep Point Cloud Compression","created":"2022-04-27","cited_by_count":39},{"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":"2011.06409","title":"End-to-end optimized image compression for machines, a study","created":"2020-11-10","cited_by_count":30},{"id":"2203.04963","title":"Neural Data-Dependent Transform for Learned Image Compression","created":"2022-03-09","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":"2302.09598","title":"Guided Depth Map Super-resolution: A Survey","created":"2023-02-19","cited_by_count":23},{"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":"2009.12430","title":"Pareto-Optimal Bit Allocation for Collaborative Intelligence","created":"2020-09-25","cited_by_count":17},{"id":"2002.07048","title":"Bit Allocation for Multi-Task Collaborative Intelligence","created":"2020-02-14","cited_by_count":13},{"id":"2402.03254","title":"Minimum Description Length and Generalization Guarantees for Representation Learning","created":"2024-02-05","cited_by_count":11},{"id":"2103.00233","title":"Learning with Smooth Hinge Losses","created":"2021-02-27","cited_by_count":9},{"id":"1807.02232","title":"Progressive Spatial Recurrent Neural Network for Intra Prediction","created":"2018-07-06","cited_by_count":6},{"id":"2303.04571","title":"A Categorical Framework of General Intelligence","created":"2023-03-08","cited_by_count":5},{"id":"1605.08308","title":"Efficient Multiple Line-Based Intra Prediction for HEVC","created":"2016-05-26","cited_by_count":4},{"id":"2009.04646","title":"Key-Point Sequence Lossless Compression for Intelligent Video Analysis","created":"2020-09-10","cited_by_count":4},{"id":"2011.03800","title":"Reducing latency and bandwidth for video streaming using keypoint extraction and digital puppetry","created":"2020-11-07","cited_by_count":3},{"id":"1806.07008","title":"A Group Variational Transformation Neural Network for Fractional Interpolation of Video Coding","created":"2018-06-19","cited_by_count":2},{"id":"2303.05132","title":"Multispectral Image Compression Based on HEVC Using Pel-Recursive Inter-Band Prediction","created":"2023-03-09","cited_by_count":1}],"next_cursor":null}