{"list":"other","total":70,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"1808.06226","title":"SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing","created":"2018-08-19","cited_by_count":1989},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2012.03411","title":"MLS: A Large-Scale Multilingual Dataset for Speech Research","created":"2020-12-07","cited_by_count":476},{"id":"2101.00390","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","created":"2021-01-02","cited_by_count":463},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151},{"id":"1810.10220","title":"DSFD: Dual Shot Face Detector","created":"2018-10-24","cited_by_count":116},{"id":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114},{"id":"2001.08702","title":"Lipreading using Temporal Convolutional Networks","created":"2020-01-23","cited_by_count":102},{"id":"2102.01757","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","created":"2021-02-02","cited_by_count":101},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95},{"id":"1911.12747","title":"ASR is all you need: cross-modal distillation for lip reading","created":"2019-11-28","cited_by_count":88},{"id":"1611.01599","title":"LipNet: End-to-End Sentence-level Lipreading","created":"2016-11-05","cited_by_count":80},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75},{"id":"1802.06424","title":"End-to-end Audiovisual Speech Recognition","created":"2018-02-18","cited_by_count":73},{"id":"1703.04105","title":"Combining Residual Networks with LSTMs for Lipreading","created":"2017-03-12","cited_by_count":68},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63},{"id":"1810.06990","title":"LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild","created":"2018-10-16","cited_by_count":51},{"id":"2007.06504","title":"Towards Practical Lipreading with Distilled and Efficient Models","created":"2020-07-13","cited_by_count":45},{"id":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44},{"id":"2008.06884","title":"DeVLBert: Learning Deconfounded Visio-Linguistic Representations","created":"2020-08-16","cited_by_count":42},{"id":"2303.08536","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","created":"2023-03-15","cited_by_count":42},{"id":"1911.11502","title":"Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers","created":"2019-11-26","cited_by_count":41},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41},{"id":"2204.01725","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","created":"2022-04-04","cited_by_count":39},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37},{"id":"2003.03206","title":"Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition","created":"2020-03-06","cited_by_count":30},{"id":"2305.18108","title":"Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning","created":"2023-05-29","cited_by_count":28},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28},{"id":"1908.04917","title":"A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading","created":"2019-08-14","cited_by_count":25},{"id":"2207.06020","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","created":"2022-07-13","cited_by_count":24},{"id":"1905.02540","title":"Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading","created":"2019-05-04","cited_by_count":22},{"id":"2003.05709","title":"Deformation Flow Based Two-Stream Network for Lip Reading","created":"2020-03-12","cited_by_count":22},{"id":"2302.08841","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","created":"2023-02-17","cited_by_count":21},{"id":"2011.07557","title":"Learn an Effective Lip Reading Model without Pains","created":"2020-11-15","cited_by_count":19},{"id":"2003.06439","title":"Mutual Information Maximization for Effective Lip Reading","created":"2020-03-13","cited_by_count":18},{"id":"2204.01265","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","created":"2022-04-04","cited_by_count":18},{"id":"2208.04498","title":"Speaker-adaptive Lip Reading with User-dependent Padding","created":"2022-08-09","cited_by_count":17},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16},{"id":"2302.08102","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","created":"2023-02-16","cited_by_count":14},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11},{"id":"2305.04542","title":"Multi-Temporal Lip-Audio Memory for Visual Speech Recognition","created":"2023-05-08","cited_by_count":9},{"id":"2005.03846","title":"Synchronous Bidirectional Learning for Multilingual Lip Reading","created":"2020-05-08","cited_by_count":6}],"next_cursor":null}