{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"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":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"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":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"2001.04643","title":"DDSP: Differentiable Digital Signal Processing","created":"2020-01-14","cited_by_count":178},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"1802.06182","title":"CREPE: A Convolutional Representation for Pitch Estimation","created":"2018-02-17","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":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"1608.07017","title":"Ambient Sound Provides Supervision for Visual Learning","created":"2016-08-25","cited_by_count":78},{"id":"2104.12671","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","created":"2021-04-26","cited_by_count":62},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35},{"id":"1610.02610","title":"Visual Closed-Loop Control for Pouring Liquids","created":"2016-10-09","cited_by_count":26},{"id":"1806.06053","title":"Deep Lip Reading: a comparison of models and an online application","created":"2018-06-15","cited_by_count":26},{"id":"2401.09294","title":"T-FOLEY: A Controllable Waveform-Domain Diffusion Model for Temporal-Event-Guided Foley Sound Synthesis","created":"2024-01-17","cited_by_count":19},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18},{"id":"2309.02265","title":"PESTO: Pitch Estimation with Self-supervised Transposition-equivariant Objective","created":"2023-09-05","cited_by_count":18},{"id":"1701.02718","title":"See the Glass Half Full: Reasoning about Liquid Containers, their Volume and Content","created":"2017-01-10","cited_by_count":11},{"id":"1903.00650","title":"Making Sense of Audio Vibration for Liquid Height Estimation in Robotic Pouring","created":"2019-03-02","cited_by_count":11},{"id":"1703.01564","title":"Perceiving and Reasoning About Liquids Using Fully Convolutional Networks","created":"2017-03-05","cited_by_count":10},{"id":"2203.01538","title":"Self-supervised Transparent Liquid Segmentation for Robotic Pouring","created":"2022-03-03","cited_by_count":10},{"id":"2307.11299","title":"PourIt!: Weakly-supervised Liquid Perception from a Single Image for Visual Closed-Loop Robotic Pouring","created":"2023-07-21","cited_by_count":10},{"id":"2011.10150","title":"Robot Gaining Accurate Pouring Skills through Self-Supervised Learning and Generalization","created":"2020-11-19","cited_by_count":9},{"id":"2003.00342","title":"Robust Robotic Pouring using Audition and Haptics","created":"2020-02-29","cited_by_count":6},{"id":"1705.09021","title":"Learning to Pour","created":"2017-05-25","cited_by_count":4},{"id":"1606.06266","title":"Detection and Tracking of Liquids with Fully Convolutional Networks","created":"2016-06-20","cited_by_count":2},{"id":"1608.00887","title":"Towards Learning to Perceive and Reason About Liquids","created":"2016-08-02","cited_by_count":2},{"id":"2109.07577","title":"Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the TransProteus CGI dataset","created":"2021-09-15","cited_by_count":2},{"id":"2203.01192","title":"Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings","created":"2022-03-02","cited_by_count":2},{"id":"1808.01725","title":"Liquid Pouring Monitoring via Rich Sensory Inputs","created":"2018-08-06","cited_by_count":1},{"id":"2105.12828","title":"Pouring Dynamics Estimation Using Gated Recurrent Units","created":"2021-05-08","cited_by_count":1},{"id":"2310.18473","title":"Pouring by Feel: An Analysis of Tactile and Proprioceptive Sensing for Accurate Pouring","created":"2023-10-27","cited_by_count":1}],"next_cursor":null}