{"list":"other","total":56,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2210.02186","title":"TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis","created":"2022-10-05","cited_by_count":1058},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2402.03885","title":"MOMENT: A Family of Open Time-series Foundation Models","created":"2024-02-06","cited_by_count":482},{"id":"1610.00081","title":"Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction","created":"2016-10-01","cited_by_count":333},{"id":"2409.16040","title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","created":"2024-09-24","cited_by_count":287},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"1811.08055","title":"A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data","created":"2018-11-20","cited_by_count":182},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"2406.16964","title":"Are Language Models Actually Useful for Time Series Forecasting?","created":"2024-06-22","cited_by_count":168},{"id":"2410.16032","title":"TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis","created":"2024-10-21","cited_by_count":116},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105},{"id":"2408.17253","title":"VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters","created":"2024-08-30","cited_by_count":88},{"id":"1506.00327","title":"Imaging Time-Series to Improve Classification and Imputation","created":"2015-06-01","cited_by_count":85},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82},{"id":"2303.12799","title":"Time Series as Images: Vision Transformer for Irregularly Sampled Time Series","created":"2023-03-01","cited_by_count":79},{"id":"1701.04245","title":"Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction","created":"2017-01-16","cited_by_count":67},{"id":"2402.03182","title":"Empowering Time Series Analysis with Large Language Models: A Survey","created":"2024-02-05","cited_by_count":60},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56},{"id":"2410.19538","title":"Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series","created":"2024-10-25","cited_by_count":43},{"id":"2202.02691","title":"TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network","created":"2022-02-06","cited_by_count":41},{"id":"1710.00886","title":"Classification of Time-Series Images Using Deep Convolutional Neural Networks","created":"2017-10-02","cited_by_count":38},{"id":"1904.08064","title":"Forecasting with time series imaging","created":"2019-04-17","cited_by_count":22},{"id":"2301.10166","title":"Leveraging Vision-Language Models for Granular Market Change Prediction","created":"2023-01-17","cited_by_count":22},{"id":"2411.02465","title":"See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers","created":"2024-11-04","cited_by_count":20},{"id":"2011.09052","title":"Visual Time Series Forecasting: An Image-driven Approach","created":"2020-11-18","cited_by_count":13},{"id":"2407.07311","title":"ViTime: Foundation Model for Time Series Forecasting Powered by Vision Intelligence","created":"2024-07-10","cited_by_count":11},{"id":"1907.10046","title":"Trading via Image Classification","created":"2019-07-23","cited_by_count":10},{"id":"2303.03689","title":"AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer","created":"2023-03-07","cited_by_count":10},{"id":"1905.01697","title":"Multivariate Time Series Classification using Dilated Convolutional Neural Network","created":"2019-05-05","cited_by_count":9},{"id":"2403.11047","title":"From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting","created":"2024-03-17","cited_by_count":9},{"id":"2410.02637","title":"Plots Unlock Time-Series Understanding in Multimodal Models","created":"2024-10-03","cited_by_count":9},{"id":"2402.06318","title":"TimEHR: Image-based Time Series Generation for Electronic Health Records","created":"2024-02-09","cited_by_count":8},{"id":"2412.17304","title":"On the Feasibility of Vision-Language Models for Time-Series Classification","created":"2024-12-23","cited_by_count":8},{"id":"2411.12058","title":"Vision Language Models Are Few-Shot Audio Spectrogram Classifiers","created":"2024-11-18","cited_by_count":7},{"id":"2102.12061","title":"Deep Video Prediction for Time Series Forecasting","created":"2021-02-24","cited_by_count":4},{"id":"2406.01833","title":"CAFO: Feature-Centric Explanation on Time Series Classification","created":"2024-06-03","cited_by_count":4},{"id":"2408.14756","title":"Training-Free Time-Series Anomaly Detection: Leveraging Image Foundation Models","created":"2024-08-27","cited_by_count":4},{"id":"2302.14390","title":"Your time series is worth a binary image: machine vision assisted deep framework for time series forecasting","created":"2023-02-28","cited_by_count":3}],"next_cursor":null}