{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2006.04558","title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","created":"2020-06-08","cited_by_count":717},{"id":"1507.05717","title":"An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition","created":"2015-07-21","cited_by_count":520},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1512.02595","title":"Deep Speech 2: End-to-End Speech Recognition in English and Mandarin","created":"2015-12-08","cited_by_count":451},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"id":"1412.5567","title":"Deep Speech: Scaling up end-to-end speech recognition","created":"2014-12-17","cited_by_count":354},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"2103.10213","title":"ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction","created":"2021-03-18","cited_by_count":256},{"id":"2007.04687","title":"Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision","created":"2020-07-09","cited_by_count":238},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1406.2227","title":"Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition","created":"2014-06-09","cited_by_count":214},{"id":"2103.06495","title":"Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition","created":"2021-03-11","cited_by_count":194},{"id":"1904.01906","title":"What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis","created":"2019-04-03","cited_by_count":191},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"2207.06966","title":"Scene Text Recognition with Permuted Autoregressive Sequence Models","created":"2022-07-14","cited_by_count":149},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140},{"id":"1907.00945","title":"ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019","created":"2019-07-01","cited_by_count":139},{"id":"2003.12294","title":"Towards Accurate Scene Text Recognition with Semantic Reasoning Networks","created":"2020-03-27","cited_by_count":131},{"id":"1811.00751","title":"Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition","created":"2018-11-02","cited_by_count":130},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"1603.03915","title":"Robust Scene Text Recognition with Automatic Rectification","created":"2016-03-12","cited_by_count":121},{"id":"2005.10977","title":"SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition","created":"2020-05-22","cited_by_count":119},{"id":"1912.10205","title":"Decoupled Attention Network for Text Recognition","created":"2019-12-21","cited_by_count":102},{"id":"2108.09661","title":"From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network","created":"2021-08-22","cited_by_count":97},{"id":"2007.07542","title":"RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition","created":"2020-07-15","cited_by_count":85},{"id":"1603.03101","title":"Recursive Recurrent Nets with Attention Modeling for OCR in the Wild","created":"2016-03-09","cited_by_count":74},{"id":"1912.12422","title":"TextScanner: Reading Characters in Order for Robust Scene Text Recognition","created":"2019-12-28","cited_by_count":68},{"id":"1910.02562","title":"MASTER: Multi-Aspect Non-local Network for Scene Text Recognition","created":"2019-10-07","cited_by_count":65},{"id":"2008.05789","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","created":"2020-08-13","cited_by_count":63},{"id":"1910.04396","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","created":"2019-10-10","cited_by_count":59},{"id":"1710.08969","title":"Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention","created":"2017-10-24","cited_by_count":57},{"id":"1809.06508","title":"Scene Text Recognition from Two-Dimensional Perspective","created":"2018-09-18","cited_by_count":57},{"id":"1905.09773","title":"Speech2Face: Learning the Face Behind a Voice","created":"2019-05-23","cited_by_count":55},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45},{"id":"2208.00438","title":"Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition","created":"2022-07-31","cited_by_count":45},{"id":"1506.04395","title":"Reading Scene Text in Deep Convolutional Sequences","created":"2015-06-14","cited_by_count":44},{"id":"2108.06543","title":"MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding","created":"2021-08-14","cited_by_count":40},{"id":"2209.03592","title":"Multi-Granularity Prediction for Scene Text Recognition","created":"2022-09-08","cited_by_count":36},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34},{"id":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23},{"id":"2204.13867","title":"Vision-Language Pre-Training for Boosting Scene Text Detectors","created":"2022-04-29","cited_by_count":18},{"id":"2112.04748","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","created":"2021-12-09","cited_by_count":10},{"id":"2205.12007","title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","created":"2022-05-20","cited_by_count":9},{"id":"2211.04963","title":"Pure Transformer with Integrated Experts for Scene Text Recognition","created":"2022-11-09","cited_by_count":9},{"id":"2201.01046","title":"Sound and Visual Representation Learning with Multiple Pretraining Tasks","created":"2022-01-04","cited_by_count":5},{"id":"2205.05206","title":"Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection","created":"2022-05-10","cited_by_count":4},{"id":"1601.03128","title":"Enhancing Energy Minimization Framework for Scene Text Recognition with Top-Down Cues","created":"2016-01-13","cited_by_count":2}],"next_cursor":null}