{"list":"other","total":65,"rows":[{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"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":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"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":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64},{"id":"1603.07772","title":"Co-occurrence Feature Learning for Skeleton based Action Recognition using Regularized Deep LSTM Networks","created":"2016-03-24","cited_by_count":63},{"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":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56},{"id":"2011.01143","title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds","created":"2020-11-02","cited_by_count":55},{"id":"2104.10955","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","created":"2021-04-22","cited_by_count":53},{"id":"2105.00335","title":"Audio Transformers","created":"2021-05-01","cited_by_count":41},{"id":"1910.10997","title":"Vision-Infused Deep Audio Inpainting","created":"2019-10-24","cited_by_count":40},{"id":"2108.03256","title":"The Right to Talk: An Audio-Visual Transformer Approach","created":"2021-08-06","cited_by_count":33},{"id":"2002.08742","title":"Disentangled Speech Embeddings using Cross-modal Self-supervision","created":"2020-02-20","cited_by_count":30},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24},{"id":"2108.11575","title":"Shifted Chunk Transformer for Spatio-Temporal Representational Learning","created":"2021-08-26","cited_by_count":20},{"id":"2303.10757","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","created":"2023-03-19","cited_by_count":16},{"id":"1912.02615","title":"Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events","created":"2019-12-02","cited_by_count":9},{"id":"2104.10116","title":"Detection of Audio-Video Synchronization Errors Via Event Detection","created":"2021-04-20","cited_by_count":6}],"next_cursor":null}