{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"1607.08221","title":"MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition","created":"2016-07-27","cited_by_count":624},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1706.01427","title":"A simple neural network module for relational reasoning","created":"2017-06-05","cited_by_count":346},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"2006.02713","title":"Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID","created":"2020-06-04","cited_by_count":212},{"id":"1702.08720","title":"Learning Discrete Representations via Information Maximizing Self-Augmented Training","created":"2017-02-28","cited_by_count":149},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"2003.11982","title":"In defence of metric learning for speaker recognition","created":"2020-03-26","cited_by_count":126},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"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":"1504.03641","title":"Learning to Compare Image Patches via Convolutional Neural Networks","created":"2015-04-14","cited_by_count":109},{"id":"1901.01342","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","created":"2019-01-05","cited_by_count":83},{"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":"2012.14952","title":"Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks","created":"2020-12-29","cited_by_count":73},{"id":"2005.09921","title":"End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors","created":"2020-05-20","cited_by_count":71},{"id":"2005.07272","title":"Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario","created":"2020-05-14","cited_by_count":68},{"id":"1804.00326","title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","created":"2018-04-01","cited_by_count":60},{"id":"1805.00833","title":"Learnable PINs: Cross-Modal Embeddings for Person Identity","created":"2018-05-02","cited_by_count":60},{"id":"1809.08001","title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","created":"2018-09-21","cited_by_count":60},{"id":"1810.04719","title":"Fully Supervised Speaker Diarization","created":"2018-10-10","cited_by_count":47},{"id":"2007.09470","title":"Social Adaptive Module for Weakly-supervised Group Activity Recognition","created":"2020-07-18","cited_by_count":42},{"id":"1906.07839","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","created":"2019-06-18","cited_by_count":39},{"id":"1805.12174","title":"Video Summarization by Learning from Unpaired Data","created":"2018-05-30","cited_by_count":36},{"id":"1806.06053","title":"Deep Lip Reading: a comparison of models and an online application","created":"2018-06-15","cited_by_count":26},{"id":"2008.03894","title":"Audio-visual Speaker Recognition with a Cross-modal Discriminative Network","created":"2020-08-10","cited_by_count":24},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24},{"id":"1603.09725","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","created":"2016-03-31","cited_by_count":23},{"id":"2102.06291","title":"A Multi-View Approach To Audio-Visual Speaker Verification","created":"2021-02-11","cited_by_count":23},{"id":"1807.04836","title":"Disjoint Mapping Network for Cross-modal Matching of Voices and Faces","created":"2018-07-12","cited_by_count":22},{"id":"1906.10042","title":"Who said that?: Audio-visual speaker diarisation of real-world meetings","created":"2019-06-24","cited_by_count":22},{"id":"2103.07293","title":"Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association","created":"2021-03-12","cited_by_count":21},{"id":"2010.11458","title":"Microsoft Speaker Diarization System for the VoxCeleb Speaker Recognition Challenge 2020","created":"2020-10-22","cited_by_count":18},{"id":"1908.03381","title":"Video Face Clustering with Unknown Number of Clusters","created":"2019-08-09","cited_by_count":17},{"id":"2002.06220","title":"Speaker Diarization with Region Proposal Network","created":"2020-02-14","cited_by_count":16},{"id":"2010.11718","title":"Analysis of the BUT Diarization System for VoxConverse Challenge","created":"2020-10-22","cited_by_count":11},{"id":"2008.03546","title":"Online Multi-modal Person Search in Videos","created":"2020-08-08","cited_by_count":10},{"id":"1709.02458","title":"End-to-end Face Detection and Cast Grouping in Movies Using Erd\\H{o}s-R\\'{e}nyi Clustering","created":"2017-09-07","cited_by_count":5},{"id":"2106.01667","title":"APES: Audiovisual Person Search in Untrimmed Video","created":"2021-06-03","cited_by_count":3}],"next_cursor":null}