{"list":"other","total":95,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1706.02690","title":"Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks","created":"2017-06-08","cited_by_count":1328},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"1812.04606","title":"Deep Anomaly Detection with Outlier Exposure","created":"2018-12-11","cited_by_count":942},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1912.11035","title":"CNN-generated images are surprisingly easy to spot... for now","created":"2019-12-23","cited_by_count":847},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"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":"1703.05921","title":"Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery","created":"2017-03-17","cited_by_count":566},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"1703.07332","title":"How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)","created":"2017-03-21","cited_by_count":525},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"2003.08685","title":"Leveraging Frequency Analysis for Deep Fake Image Recognition","created":"2020-03-19","cited_by_count":504},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1801.10198","title":"Generating Wikipedia by Summarizing Long Sequences","created":"2018-01-30","cited_by_count":335},{"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":"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":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"1906.02694","title":"Deep Semi-Supervised Anomaly Detection","created":"2019-06-06","cited_by_count":291},{"id":"2012.07657","title":"Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection","created":"2020-12-14","cited_by_count":287},{"id":"1806.04558","title":"Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis","created":"2018-06-12","cited_by_count":282},{"id":"2003.01826","title":"Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions","created":"2020-03-03","cited_by_count":280},{"id":"2008.10588","title":"What makes fake images detectable? Understanding properties that generalize","created":"2020-08-24","cited_by_count":273},{"id":"1712.06651","title":"Objects that Sound","created":"2017-12-18","cited_by_count":256},{"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":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1710.10766","title":"PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples","created":"2017-10-30","cited_by_count":244},{"id":"2002.00133","title":"Global Texture Enhancement for Fake Face Detection in the Wild","created":"2020-02-01","cited_by_count":220},{"id":"1802.09088","title":"Adversarially Learned One-Class Classifier for Novelty Detection","created":"2018-02-25","cited_by_count":202},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2012.09311","title":"Learning Self-Consistency for Deepfake Detection","created":"2020-12-16","cited_by_count":179},{"id":"1811.04110","title":"Reducing Network Agnostophobia","created":"2018-11-09","cited_by_count":165},{"id":"2108.06693","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","created":"2021-08-15","cited_by_count":159},{"id":"1708.05237","title":"S$^3$FD: Single Shot Scale-invariant Face Detector","created":"2017-08-17","cited_by_count":142},{"id":"1805.04096","title":"Fighting Fake News: Image Splice Detection via Learned Self-Consistency","created":"2018-05-10","cited_by_count":136},{"id":"2104.02939","title":"OpenGAN: Open-Set Recognition via Open Data Generation","created":"2021-04-07","cited_by_count":135},{"id":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130},{"id":"1405.3531","title":"Return of the Devil in the Details: Delving Deep into Convolutional Nets","created":"2014-05-14","cited_by_count":122},{"id":"1611.09577","title":"Fast Face-swap Using Convolutional Neural Networks","created":"2016-11-29","cited_by_count":119},{"id":"1812.02288","title":"Adversarially Learned Anomaly Detection","created":"2018-12-06","cited_by_count":115},{"id":"1808.08396","title":"Noiseprint: a CNN-based camera model fingerprint","created":"2018-08-25","cited_by_count":114},{"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":"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":"2003.12506","title":"Hybrid Models for Open Set Recognition","created":"2020-03-27","cited_by_count":109},{"id":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106},{"id":"2001.08702","title":"Lipreading using Temporal Convolutional Networks","created":"2020-01-23","cited_by_count":102},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"1807.02588","title":"Generative Probabilistic Novelty Detection with Adversarial Autoencoders","created":"2018-07-06","cited_by_count":99},{"id":"2003.00418","title":"Towards Automatic Face-to-Face Translation","created":"2020-03-01","cited_by_count":96},{"id":"2002.10137","title":"Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose","created":"2020-02-24","cited_by_count":92},{"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":"1911.12747","title":"ASR is all you need: cross-modal distillation for lip reading","created":"2019-11-28","cited_by_count":88},{"id":"2103.16076","title":"Face Forensics in the Wild","created":"2021-03-30","cited_by_count":87},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2103.10094","title":"KoDF: A Large-scale Korean DeepFake Detection Dataset","created":"2021-03-18","cited_by_count":80},{"id":"1809.10816","title":"Generative Adversarial Active Learning for Unsupervised Outlier Detection","created":"2018-09-28","cited_by_count":65},{"id":"1809.08001","title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","created":"2018-09-21","cited_by_count":60},{"id":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","cited_by_count":55},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"id":"2109.00162","title":"Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces","created":"2021-09-01","cited_by_count":48},{"id":"2007.06504","title":"Towards Practical Lipreading with Distilled and Efficient Models","created":"2020-07-13","cited_by_count":45},{"id":"2204.03083","title":"Audio-Visual Person-of-Interest DeepFake Detection","created":"2022-04-06","cited_by_count":43},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36},{"id":"2209.15490","title":"Learning Second Order Local Anomaly for General Face Forgery Detection","created":"2022-09-30","cited_by_count":36},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35},{"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":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18},{"id":"1904.08241","title":"Deep Anomaly Detection for Generalized Face Anti-Spoofing","created":"2019-04-17","cited_by_count":17},{"id":"1802.04881","title":"Satellite Image Forgery Detection and Localization Using GAN and One-Class Classifier","created":"2018-02-13","cited_by_count":14},{"id":"1708.08754","title":"Autoencoder with recurrent neural networks for video forgery detection","created":"2017-08-29","cited_by_count":10},{"id":"2005.10360","title":"VideoForensicsHQ: Detecting High-quality Manipulated Face Videos","created":"2020-05-20","cited_by_count":8}],"next_cursor":null}