{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"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":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1905.12681","title":"What Makes Training Multi-Modal Classification Networks Hard?","created":"2019-05-29","cited_by_count":344},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"2207.13532","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","created":"2022-07-27","cited_by_count":133},{"id":"2006.09199","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","created":"2020-06-16","cited_by_count":111},{"id":"2205.14204","title":"Multimodal Masked Autoencoders Learn Transferable Representations","created":"2022-05-27","cited_by_count":109},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82},{"id":"2203.16691","title":"MAE-AST: Masked Autoencoding Audio Spectrogram Transformer","created":"2022-03-30","cited_by_count":82},{"id":"2103.15916","title":"Robust Audio-Visual Instance Discrimination","created":"2021-03-29","cited_by_count":80},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56},{"id":"2204.12260","title":"Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representation","created":"2022-04-26","cited_by_count":52},{"id":"2204.12768","title":"Masked Spectrogram Prediction For Self-Supervised Audio Pre-Training","created":"2022-04-27","cited_by_count":51},{"id":"2003.04298","title":"On Compositions of Transformations in Contrastive Self-Supervised Learning","created":"2020-03-09","cited_by_count":34},{"id":"2104.12807","title":"Multimodal Self-Supervised Learning of General Audio Representations","created":"2021-04-26","cited_by_count":32},{"id":"2006.01595","title":"Large Scale Audiovisual Learning of Sounds with Weakly Labeled Data","created":"2020-05-29","cited_by_count":27},{"id":"2205.06126","title":"One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code","created":"2022-05-12","cited_by_count":26},{"id":"2110.07313","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","created":"2021-10-14","cited_by_count":22},{"id":"2203.13448","title":"AudioTagging Done Right: 2nd comparison of deep learning methods for environmental sound classification","created":"2022-03-25","cited_by_count":4}],"next_cursor":null}