{"list":"other","total":52,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301},{"id":"1809.07294","title":"Generative Adversarial Network in Medical Imaging: A Review","created":"2018-09-19","cited_by_count":257},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"2207.08208","title":"Unsupervised Medical Image Translation with Adversarial Diffusion Models","created":"2022-07-17","cited_by_count":192},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"1806.06397","title":"MedGAN: Medical Image Translation using GANs","created":"2018-06-17","cited_by_count":152},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141},{"id":"1906.02849","title":"Multi-scale self-guided attention for medical image segmentation","created":"2019-06-07","cited_by_count":84},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51},{"id":"2012.05440","title":"Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding","created":"2020-12-10","cited_by_count":48},{"id":"2306.04811","title":"Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation","created":"2023-06-07","cited_by_count":47},{"id":"2304.02777","title":"MoStGAN-V: Video Generation with Temporal Motion Styles","created":"2023-04-05","cited_by_count":37},{"id":"2106.06908","title":"Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation","created":"2021-06-13","cited_by_count":33},{"id":"2212.01602","title":"StegaNeRF: Embedding Invisible Information within Neural Radiance Fields","created":"2022-12-03","cited_by_count":32},{"id":"2402.17403","title":"Sora Generates Videos with Stunning Geometrical Consistency","created":"2024-02-27","cited_by_count":31},{"id":"2203.07667","title":"SATS: Self-Attention Transfer for Continual Semantic Segmentation","created":"2022-03-15","cited_by_count":25},{"id":"2006.01997","title":"Automatic Text Summarization of COVID-19 Medical Research Articles using BERT and GPT-2","created":"2020-06-03","cited_by_count":23},{"id":"2203.12121","title":"Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection","created":"2022-03-23","cited_by_count":20},{"id":"2207.05409","title":"Knowledge Condensation Distillation","created":"2022-07-12","cited_by_count":20},{"id":"2306.07598","title":"Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images","created":"2023-06-13","cited_by_count":18},{"id":"1906.10643","title":"A Review on Deep Learning in Medical Image Reconstruction","created":"2019-06-23","cited_by_count":17},{"id":"2103.09097","title":"Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification","created":"2021-03-16","cited_by_count":15},{"id":"2105.14732","title":"Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation","created":"2021-05-31","cited_by_count":15},{"id":"2305.15832","title":"All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation","created":"2023-05-25","cited_by_count":13},{"id":"2401.14148","title":"LanDA: Language-Guided Multi-Source Domain Adaptation","created":"2024-01-25","cited_by_count":13},{"id":"2009.05722","title":"Generator Versus Segmentor: Pseudo-healthy Synthesis","created":"2020-09-12","cited_by_count":12},{"id":"2204.07963","title":"AFSC: Adaptive Fourier Space Compression for Anomaly Detection","created":"2022-04-17","cited_by_count":12},{"id":"2403.03063","title":"CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections","created":"2024-03-05","cited_by_count":12},{"id":"2103.09094","title":"Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation","created":"2021-03-16","cited_by_count":11},{"id":"2310.03015","title":"Efficient-3DiM: Learning a Generalizable Single-image Novel-view Synthesizer in One Day","created":"2023-10-04","cited_by_count":11},{"id":"2310.16052","title":"Synthetic Data as Validation","created":"2023-10-24","cited_by_count":10},{"id":"2111.14094","title":"Topic Driven Adaptive Network for Cross-Domain Sentiment Classification","created":"2021-11-28","cited_by_count":3}],"next_cursor":null}