{"list":"other","total":61,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"1703.07737","title":"In Defense of the Triplet Loss for Person Re-Identification","created":"2017-03-22","cited_by_count":786},{"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":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"2004.11660","title":"Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning","created":"2020-04-24","cited_by_count":220},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"id":"2306.05705","title":"On the Challenges and Perspectives of Foundation Models for Medical Image Analysis","created":"2023-06-09","cited_by_count":135},{"id":"1801.04260","title":"Conditional Probability Models for Deep Image Compression","created":"2018-01-12","cited_by_count":133},{"id":"2203.09974","title":"SynthStrip: Skull-Stripping for Any Brain Image","created":"2022-03-18","cited_by_count":127},{"id":"1905.00292","title":"AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations","created":"2019-05-01","cited_by_count":83},{"id":"2111.03452","title":"Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports","created":"2021-11-04","cited_by_count":80},{"id":"1911.01685","title":"Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory & Practice","created":"2019-11-05","cited_by_count":71},{"id":"2305.19894","title":"Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias","created":"2023-05-31","cited_by_count":57},{"id":"2202.08994","title":"REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening","created":"2022-02-18","cited_by_count":38},{"id":"2310.18341","title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","created":"2023-10-22","cited_by_count":37},{"id":"2012.03769","title":"Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive Evaluation","created":"2020-11-29","cited_by_count":36},{"id":"2104.10326","title":"A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation","created":"2021-04-21","cited_by_count":34},{"id":"2107.09700","title":"3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images","created":"2021-07-20","cited_by_count":32},{"id":"1911.11758","title":"MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation","created":"2019-11-26","cited_by_count":29},{"id":"2503.18421","title":"4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video","created":"2025-03-24","cited_by_count":27},{"id":"2405.06228","title":"Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation","created":"2024-05-10","cited_by_count":25},{"id":"1911.11759","title":"Password-conditioned Anonymization and Deanonymization with Face Identity Transformers","created":"2019-11-26","cited_by_count":24},{"id":"2405.11793","title":"MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise","created":"2024-05-20","cited_by_count":24},{"id":"2103.07073","title":"DP-Image: Differential Privacy for Image Data in Feature Space","created":"2021-03-12","cited_by_count":23},{"id":"2107.11639","title":"Self-Conditioned Probabilistic Learning of Video Rescaling","created":"2021-07-24","cited_by_count":19},{"id":"2202.02813","title":"A Coding Framework and Benchmark towards Low-Bitrate Video Understanding","created":"2022-02-06","cited_by_count":17},{"id":"2107.10771","title":"EAN: Event Adaptive Network for Enhanced Action Recognition","created":"2021-07-22","cited_by_count":16},{"id":"2407.00752","title":"Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation","created":"2024-06-30","cited_by_count":16},{"id":"2412.11362","title":"VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression","created":"2024-12-16","cited_by_count":14},{"id":"1909.04087","title":"Privacy-Net: An Adversarial Approach for Identity-Obfuscated Segmentation of Medical Images","created":"2019-09-09","cited_by_count":13},{"id":"2406.04765","title":"SMC++: Masked Learning of Unsupervised Video Semantic Compression","created":"2024-06-07","cited_by_count":12},{"id":"2501.13630","title":"VARFVV: View-Adaptive Real-Time Interactive Free-View Video Streaming with Edge Computing","created":"2025-01-23","cited_by_count":12},{"id":"2503.10078","title":"Image Quality Assessment: From Human to Machine Preference","created":"2025-03-13","cited_by_count":12},{"id":"2102.11072","title":"Obfuscation of Images via Differential Privacy: From Facial Images to General Images","created":"2021-02-19","cited_by_count":11},{"id":"2409.11718","title":"Free-VSC: Free Semantics from Visual Foundation Models for Unsupervised Video Semantic Compression","created":"2024-09-18","cited_by_count":10},{"id":"2503.10079","title":"Information Density Principle for MLLM Benchmarks","created":"2025-03-13","cited_by_count":9},{"id":"1302.5062","title":"P3: Toward Privacy-Preserving Photo Sharing","created":"2013-02-20","cited_by_count":8},{"id":"2207.07918","title":"Discriminative Kernel Convolution Network for Multi-Label Ophthalmic Disease Detection on Imbalanced Fundus Image Dataset","created":"2022-07-16","cited_by_count":6},{"id":"2503.08173","title":"Towards All-in-One Medical Image Re-Identification","created":"2025-03-11","cited_by_count":6},{"id":"2209.11531","title":"Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy","created":"2022-09-23","cited_by_count":5},{"id":"2409.17091","title":"Ctrl-GenAug: Controllable Generative Augmentation for Medical Sequence Classification","created":"2024-09-25","cited_by_count":4},{"id":"2412.10804","title":"Medical Manifestation-Aware De-Identification","created":"2024-12-14","cited_by_count":4},{"id":"1609.00881","title":"CryptoImg: Privacy Preserving Processing Over Encrypted Images","created":"2016-09-04","cited_by_count":1}],"next_cursor":null}