{"total":22,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2211.15979","title":"AirFormer: Predicting Nationwide Air Quality in China with Transformers","created":"2022-11-29","cited_by_count":73,"area":null},{"id":"2104.03964","title":"Handwriting Transformers","created":"2021-04-08","cited_by_count":37,"area":null},{"id":"2303.15269","title":"Handwritten Text Generation from Visual Archetypes","created":"2023-03-27","cited_by_count":32,"area":null},{"id":"2106.12271","title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2305.18719","title":"Graph Neural Processes for Spatio-Temporal Extrapolation","created":"2023-05-30","cited_by_count":19,"area":null},{"id":"2105.10528","title":"SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators","created":"2021-05-21","cited_by_count":17,"area":null},{"id":"2306.11052","title":"A spatio-temporal network for video semantic segmentation in surgical videos","created":"2023-06-19","cited_by_count":17,"area":null},{"id":"2109.08591","title":"Diverse Generation from a Single Video Made Possible","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2503.17074","title":"Zero-Shot Styled Text Image Generation, but Make It Autoregressive","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2312.11714","title":"Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version)","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2110.14317","title":"Ask \"Who\", Not \"What\": Bitcoin Volatility Forecasting with Twitter Data","created":"2021-10-27","cited_by_count":4,"area":null},{"id":"2510.23240","title":"Autoregressive Styled Text Image Generation, but Make it Reliable","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2305.15770","title":"TLNets: Transformation Learning Networks for long-range time-series prediction","created":"2023-05-25","cited_by_count":2,"area":null},{"id":"2202.12707","title":"Benchmarking Generative Latent Variable Models for Speech","created":"2022-02-22","cited_by_count":1,"area":null},{"id":"2508.21040","title":"FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2104.13853","title":"Learning deep autoregressive models for hierarchical data","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2203.07881","title":"LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space","created":"2022-03-15","cited_by_count":0,"area":null},{"id":"2205.05725","title":"Diverse Video Generation from a Single Video","created":"2022-05-11","cited_by_count":0,"area":null},{"id":"2511.18307","title":"ScriptViT: Vision Transformer-Based Personalized Handwriting Generation","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2607.06949","title":"SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}