{"total":13,"rows":[{"id":"2103.05489","title":"TS-Net: OCR Trained to Switch Between Text Transcription Styles","created":"2021-03-09","cited_by_count":7,"area":null},{"id":"2106.06736","title":"Multi-level Attention Fusion Network for Audio-visual Event Recognition","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2102.09582","title":"Benefits of Linear Conditioning with Metadata for Image Segmentation","created":"2021-02-18","cited_by_count":6,"area":null},{"id":"2302.06318","title":"Towards Writing Style Adaptation in Handwriting Recognition","created":"2023-02-13","cited_by_count":6,"area":null},{"id":"2110.08545","title":"A Unified Speaker Adaptation Approach for ASR","created":"2021-10-16","cited_by_count":5,"area":null},{"id":"2111.08462","title":"Towards Lightweight Controllable Audio Synthesis with Conditional Implicit Neural Representations","created":"2021-11-14","cited_by_count":5,"area":null},{"id":"2205.03027","title":"A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition","created":"2022-05-06","cited_by_count":3,"area":null},{"id":"2210.05387","title":"Sequential Ensembling for Semantic Segmentation","created":"2022-10-08","cited_by_count":2,"area":null},{"id":"2407.17834","title":"Towards the Spectral bias Alleviation by Normalizations in Coordinate Networks","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2202.12169","title":"Closing the Gap between Single-User and Multi-User VoiceFilter-Lite","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2510.25262","title":"IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2212.11275","title":"KL Regularized Normalization Framework for Low Resource Tasks","created":"2022-12-21","cited_by_count":0,"area":null},{"id":"2604.03479","title":"Contextual Control without Memory Growth in a Context-Switching Task","created":"2026-04-03","cited_by_count":0,"area":null}],"next_cursor":null}