{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"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":"1806.05622","title":"VoxCeleb2: Deep Speaker Recognition","created":"2018-06-14","cited_by_count":875},{"id":"1909.12962","title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics","created":"2019-09-27","cited_by_count":575},{"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":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"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":"2204.08376","title":"Detecting Deepfakes with Self-Blended Images","created":"2022-04-18","cited_by_count":338},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"1811.00661","title":"Exposing Deep Fakes Using Inconsistent Head Poses","created":"2018-11-01","cited_by_count":297},{"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":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"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":"2004.11138","title":"The Creation and Detection of Deepfakes: A Survey","created":"2020-04-23","cited_by_count":247},{"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":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181},{"id":"2108.06693","title":"Exploring Temporal Coherence for More General Video Face Forgery Detection","created":"2021-08-15","cited_by_count":159},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130},{"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":"1909.11573","title":"Deep Learning for Deepfakes Creation and Detection: A Survey","created":"2019-09-25","cited_by_count":102},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95},{"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":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2103.00484","title":"Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forward","created":"2021-02-25","cited_by_count":82},{"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":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80},{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67},{"id":"2406.02951","title":"AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection","created":"2024-06-05","cited_by_count":59},{"id":"2101.08540","title":"Activity Graph Transformer for Temporal Action Localization","created":"2021-01-21","cited_by_count":48},{"id":"2203.02195","title":"Voice-Face Homogeneity Tells Deepfake","created":"2022-03-04","cited_by_count":44},{"id":"2204.03083","title":"Audio-Visual Person-of-Interest DeepFake Detection","created":"2022-04-06","cited_by_count":43},{"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":"2309.11131","title":"Locate and Verify: A Two-Stream Network for Improved Deepfake Detection","created":"2023-09-20","cited_by_count":26},{"id":"2401.05746","title":"Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection","created":"2024-01-11","cited_by_count":24},{"id":"2106.14118","title":"Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization","created":"2021-06-27","cited_by_count":21},{"id":"2311.01458","title":"Detecting Deepfakes Without Seeing Any","created":"2023-11-02","cited_by_count":17},{"id":"2406.07854","title":"Zero-Shot Fake Video Detection by Audio-Visual Consistency","created":"2024-06-12","cited_by_count":11},{"id":"1805.02934","title":"Phoneme-to-viseme mappings: the good, the bad, and the ugly","created":"2018-05-08","cited_by_count":7},{"id":"2408.01532","title":"Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization","created":"2024-08-02","cited_by_count":6}],"next_cursor":null}