{"list":"other","total":56,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"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":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"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":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1608.08242","title":"Temporal Convolutional Networks: A Unified Approach to Action Segmentation","created":"2016-08-29","cited_by_count":199},{"id":"1808.00158","title":"Speaker Recognition from Raw Waveform with SincNet","created":"2018-07-29","cited_by_count":166},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"1808.04444","title":"Character-Level Language Modeling with Deeper Self-Attention","created":"2018-08-09","cited_by_count":138},{"id":"2107.06592","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","created":"2021-07-14","cited_by_count":113},{"id":"1808.05174","title":"Recycle-GAN: Unsupervised Video Retargeting","created":"2018-08-15","cited_by_count":89},{"id":"1901.01342","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","created":"2019-01-05","cited_by_count":83},{"id":"2008.09586","title":"An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation","created":"2020-08-21","cited_by_count":81},{"id":"2007.01216","title":"Spot the conversation: speaker diarisation in the wild","created":"2020-07-02","cited_by_count":79},{"id":"1710.10468","title":"Speaker Diarization with LSTM","created":"2017-10-28","cited_by_count":73},{"id":"2005.09812","title":"Active Speakers in Context","created":"2020-05-20","cited_by_count":41},{"id":"2003.14401","title":"TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting","created":"2020-03-31","cited_by_count":36},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36},{"id":"2112.11749","title":"Class-aware Sounding Objects Localization via Audiovisual Correspondence","created":"2021-12-22","cited_by_count":32},{"id":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31},{"id":"2207.07783","title":"Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection","created":"2022-07-15","cited_by_count":30},{"id":"2108.02607","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","created":"2021-08-05","cited_by_count":28},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25},{"id":"2203.14250","title":"End-to-End Active Speaker Detection","created":"2022-03-27","cited_by_count":25},{"id":"1603.09725","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","created":"2016-03-31","cited_by_count":23},{"id":"1603.08907","title":"Cross-modal Supervision for Learning Active Speaker Detection in Video","created":"2016-03-29","cited_by_count":21},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21},{"id":"2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","created":"2022-03-04","cited_by_count":20},{"id":"2002.05314","title":"Self-supervised learning for audio-visual speaker diarization","created":"2020-02-13","cited_by_count":14},{"id":"2105.06107","title":"Multi-target DoA Estimation with an Audio-visual Fusion Mechanism","created":"2021-05-13","cited_by_count":14},{"id":"2206.10421","title":"Rethinking Audio-visual Synchronization for Active Speaker Detection","created":"2022-06-21","cited_by_count":9},{"id":"2210.07764","title":"Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization","created":"2022-10-14","cited_by_count":9},{"id":"1802.07860","title":"Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics","created":"2018-02-22","cited_by_count":7},{"id":"2112.11547","title":"Decompose the Sounds and Pixels, Recompose the Events","created":"2021-12-21","cited_by_count":4}],"next_cursor":null}