{"list":"other","total":58,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"1909.12962","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","created":"2019-09-27","cited_by_count":575},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"1703.10135","title":"Tacotron: Towards End-to-End Speech Synthesis","created":"2017-03-29","cited_by_count":490},{"id":"1809.00888","title":"MesoNet: a Compact Facial Video Forgery Detection Network","created":"2018-09-04","cited_by_count":409},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1908.05932","title":"FSGAN: Subject Agnostic Face Swapping and Reenactment","created":"2019-08-16","cited_by_count":320},{"id":"1811.00656","title":"Exposing DeepFake Videos By Detecting Face Warping Artifacts","created":"2018-11-01","cited_by_count":319},{"id":"1811.00661","title":"Exposing Deep Fakes Using Inconsistent Head Poses","created":"2018-11-01","cited_by_count":297},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"2001.03024","title":"DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection","created":"2020-01-09","cited_by_count":254},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2004.11138","title":"The Creation and Detection of Deepfakes: A Survey","created":"2020-04-23","cited_by_count":247},{"id":"1604.06182","title":"The THUMOS Challenge on Action Recognition for Videos \"in the Wild\"","created":"2016-04-21","cited_by_count":213},{"id":"1812.08685","title":"DeepFakes: a New Threat to Face Recognition? Assessment and Detection","created":"2018-12-20","cited_by_count":209},{"id":"2101.01456","title":"WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection","created":"2021-01-05","cited_by_count":209},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"1611.09577","title":"Fast Face-swap Using Convolutional Neural Networks","created":"2016-11-29","cited_by_count":119},{"id":"2104.09770","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","created":"2021-04-20","cited_by_count":114},{"id":"1703.06189","title":"TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals","created":"2017-03-17","cited_by_count":113},{"id":"1703.01515","title":"CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos","created":"2017-03-04","cited_by_count":112},{"id":"2003.06711","title":"Emotions Don't Lie: An Audio-Visual Deepfake Detection Method Using Affective Cues","created":"2020-03-14","cited_by_count":111},{"id":"2003.00418","title":"Towards Automatic Face-to-Face Translation","created":"2020-03-01","cited_by_count":96},{"id":"2005.14405","title":"Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization","created":"2020-05-29","cited_by_count":89},{"id":"2109.01860","title":"Spatiotemporal Inconsistency Learning for DeepFake Video Detection","created":"2021-09-04","cited_by_count":88},{"id":"2107.02612","title":"Combining EfficientNet and Vision Transformers for Video Deepfake Detection","created":"2021-07-06","cited_by_count":82},{"id":"2004.10448","title":"DeepFake Detection by Analyzing Convolutional Traces","created":"2020-04-22","cited_by_count":81},{"id":"2102.11126","title":"Deepfake Video Detection Using Convolutional Vision Transformer","created":"2021-02-22","cited_by_count":79},{"id":"2009.07641","title":"BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation","created":"2020-09-15","cited_by_count":65},{"id":"2104.05557","title":"SC-GlowTTS: an Efficient Zero-Shot Multi-Speaker Text-To-Speech Model","created":"2021-04-02","cited_by_count":56},{"id":"2012.09434","title":"Multi-shot Temporal Event Localization: a Benchmark","created":"2020-12-17","cited_by_count":52},{"id":"2107.14480","title":"OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild","created":"2021-07-30","cited_by_count":50},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"1807.04821","title":"CTAP: Complementary Temporal Action Proposal Generation","created":"2018-07-12","cited_by_count":46},{"id":"2004.12027","title":"Deepfakes Detection with Automatic Face Weighting","created":"2020-04-25","cited_by_count":35},{"id":"2006.14749","title":"Deepfake Detection using Spatiotemporal Convolutional Networks","created":"2020-06-26","cited_by_count":32},{"id":"2109.02993","title":"Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors","created":"2021-09-07","cited_by_count":32},{"id":"2104.01353","title":"Deepfake Detection Scheme Based on Vision Transformer and Distillation","created":"2021-04-03","cited_by_count":22},{"id":"2106.14118","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","created":"2021-06-27","cited_by_count":21},{"id":"1708.03280","title":"Exploring Temporal Preservation Networks for Precise Temporal Action Localization","created":"2017-08-10","cited_by_count":11},{"id":"2102.00151","title":"Expressive Neural Voice Cloning","created":"2021-01-30","cited_by_count":11}],"next_cursor":null}