{"list":"other","total":62,"rows":[{"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"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":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"1904.01038","title":"fairseq: A Fast, Extensible Toolkit for Sequence Modeling","created":"2019-04-01","cited_by_count":1488},{"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":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"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":"2002.06353","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","created":"2020-02-15","cited_by_count":259},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"1508.04395","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","created":"2015-08-18","cited_by_count":151},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"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":"1910.12607","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","created":"2019-10-23","cited_by_count":82},{"id":"2204.03409","title":"MAESTRO: Matched Speech Text Representations through Modality Matching","created":"2022-04-07","cited_by_count":79},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75},{"id":"1911.04890","title":"Recurrent Neural Network Transducer for Audio-Visual Speech Recognition","created":"2019-11-08","cited_by_count":74},{"id":"1911.03912","title":"Effectiveness of self-supervised pre-training for speech recognition","created":"2019-11-10","cited_by_count":72},{"id":"2005.08392","title":"Vector-Quantized Autoregressive Predictive Coding","created":"2020-05-17","cited_by_count":69},{"id":"2110.10329","title":"SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training","created":"2021-10-20","cited_by_count":69},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68},{"id":"1912.01679","title":"Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition","created":"2019-12-03","cited_by_count":66},{"id":"1810.00108","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","created":"2018-09-28","cited_by_count":64},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63},{"id":"2005.05592","title":"Discriminative Multi-modality Speech Recognition","created":"2020-05-12","cited_by_count":58},{"id":"1807.05162","title":"Large-Scale Visual Speech Recognition","created":"2018-07-13","cited_by_count":57},{"id":"2011.00406","title":"Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies","created":"2020-11-01","cited_by_count":47},{"id":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47},{"id":"2210.03730","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","created":"2022-10-07","cited_by_count":40},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","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":"2201.10439","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","created":"2022-01-25","cited_by_count":31},{"id":"2204.00465","title":"Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition","created":"2022-04-01","cited_by_count":12},{"id":"2210.16498","title":"Articulatory Representation Learning Via Joint Factor Analysis and Neural Matrix Factorization","created":"2022-10-29","cited_by_count":11},{"id":"2110.09890","title":"Multi-Modal Pre-Training for Automated Speech Recognition","created":"2021-10-12","cited_by_count":10}],"next_cursor":null}