{"list":"other","total":63,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1610.02357","title":"Xception: Deep Learning with Depthwise Separable Convolutions","created":"2016-10-07","cited_by_count":2332},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"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":"2106.06103","title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","created":"2021-06-11","cited_by_count":561},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2007.09355","title":"Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues","created":"2020-07-18","cited_by_count":523},{"id":"1912.13458","title":"Face X-ray for More General Face Forgery Detection","created":"2019-12-31","cited_by_count":470},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"1809.00888","title":"MesoNet: a Compact Facial Video Forgery Detection Network","created":"2018-09-04","cited_by_count":409},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"2204.08376","title":"Detecting Deepfakes with Self-Blended Images","created":"2022-04-18","cited_by_count":338},{"id":"1811.00656","title":"Exposing DeepFake Videos By Detecting Face Warping Artifacts","created":"2018-11-01","cited_by_count":319},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1811.00661","title":"Exposing Deep Fakes Using Inconsistent Head Poses","created":"2018-11-01","cited_by_count":297},{"id":"1710.10467","title":"Generalized End-to-End Loss for Speaker Verification","created":"2017-10-28","cited_by_count":293},{"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":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278},{"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":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2304.09116","title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","created":"2023-04-18","cited_by_count":235},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"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":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"2301.03786","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","created":"2023-01-10","cited_by_count":136},{"id":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126},{"id":"2210.02437","title":"ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild","created":"2022-10-05","cited_by_count":121},{"id":"2104.09770","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","created":"2021-04-20","cited_by_count":114},{"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":"2310.13025","title":"Powerset multi-class cross entropy loss for neural speaker diarization","created":"2023-10-19","cited_by_count":111},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106},{"id":"2303.17480","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","created":"2023-03-29","cited_by_count":98},{"id":"2202.08433","title":"ADD 2022: the First Audio Deep Synthesis Detection Challenge","created":"2022-02-17","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":"2103.16076","title":"Face Forensics in the Wild","created":"2021-03-30","cited_by_count":87},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2107.02612","title":"Combining EfficientNet and Vision Transformers for Video Deepfake Detection","created":"2021-07-06","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":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57},{"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":"2309.14203","title":"Detecting and Grounding Multi-Modal Media Manipulation and Beyond","created":"2023-09-25","cited_by_count":56},{"id":"2306.03509","title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","created":"2023-06-06","cited_by_count":51},{"id":"2305.01979","title":"Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization","created":"2023-05-03","cited_by_count":43},{"id":"2308.14395","title":"UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization","created":"2023-08-28","cited_by_count":33},{"id":"2005.08484","title":"Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding","created":"2020-05-18","cited_by_count":27},{"id":"2210.02755","title":"Audio-Visual Face Reenactment","created":"2022-10-06","cited_by_count":18},{"id":"2309.12657","title":"Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding","created":"2023-09-22","cited_by_count":7}],"next_cursor":null}