{"list":"other","total":145,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"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":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"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":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","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":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1611.05358","title":"Lip Reading Sentences in the Wild","created":"2016-11-16","cited_by_count":228},{"id":"2209.00349","title":"FLAME: Free-form Language-based Motion Synthesis & Editing","created":"2022-09-01","cited_by_count":217},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"1807.10550","title":"X2Face: A network for controlling face generation by using images, audio, and pose codes","created":"2018-07-27","cited_by_count":189},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2008.08143","title":"How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language","created":"2020-08-18","cited_by_count":173},{"id":"1703.09452","title":"SEGAN: Speech Enhancement Generative Adversarial Network","created":"2017-03-28","cited_by_count":166},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151},{"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":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149},{"id":"2207.06389","title":"ProDiff: Progressive Fast Diffusion Model For High-Quality Text-to-Speech","created":"2022-07-13","cited_by_count":149},{"id":"1906.06337","title":"Realistic Speech-Driven Facial Animation with GANs","created":"2019-06-14","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":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"2211.01367","title":"Two-Stream Network for Sign Language Recognition and Translation","created":"2022-11-02","cited_by_count":123},{"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":"2004.14874","title":"Progressive Transformers for End-to-End Sign Language Production","created":"2020-04-30","cited_by_count":120},{"id":"2201.07786","title":"Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation","created":"2022-01-19","cited_by_count":119},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"1810.12541","title":"Robots Learn Social Skills: End-to-End Learning of Co-Speech Gesture Generation for Humanoid Robots","created":"2018-10-30","cited_by_count":110},{"id":"2108.06720","title":"Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders","created":"2021-08-15","cited_by_count":109},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"2101.11101","title":"Text2Gestures: A Transformer-Based Network for Generating Emotive Body Gestures for Virtual Agents","created":"2021-01-26","cited_by_count":106},{"id":"2001.08702","title":"Lipreading using Temporal Convolutional Networks","created":"2020-01-23","cited_by_count":102},{"id":"2207.11770","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","created":"2022-07-24","cited_by_count":97},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93},{"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":"2108.07938","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","created":"2021-08-18","cited_by_count":90},{"id":"1801.10111","title":"Video-based Sign Language Recognition without Temporal Segmentation","created":"2018-01-30","cited_by_count":88},{"id":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87},{"id":"1804.04786","title":"Talking Face Generation by Conditional Recurrent Adversarial Network","created":"2018-04-13","cited_by_count":84},{"id":"2104.02330","title":"Visual Alignment Constraint for Continuous Sign Language Recognition","created":"2021-04-06","cited_by_count":80},{"id":"2201.00791","title":"DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering","created":"2022-01-03","cited_by_count":80},{"id":"2009.00299","title":"Multi-channel Transformers for Multi-articulatory Sign Language Translation","created":"2020-09-01","cited_by_count":71},{"id":"2212.08062","title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation","created":"2022-12-15","cited_by_count":69},{"id":"2106.04185","title":"LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization","created":"2021-06-08","cited_by_count":67},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66},{"id":"1811.11436","title":"Neural Sign Language Translation based on Human Keypoint Estimation","created":"2018-11-28","cited_by_count":65},{"id":"2211.00924","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","created":"2022-11-02","cited_by_count":65},{"id":"1906.05571","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","created":"2019-06-13","cited_by_count":61},{"id":"2203.15354","title":"Signing at Scale: Learning to Co-Articulate Signs for Large-Scale Photo-Realistic Sign Language Production","created":"2022-03-29","cited_by_count":61},{"id":"2005.05592","title":"Discriminative Multi-modality Speech Recognition","created":"2020-05-12","cited_by_count":58},{"id":"2007.12402","title":"Fully Convolutional Networks for Continuous Sign Language Recognition","created":"2020-07-24","cited_by_count":58},{"id":"2108.00262","title":"Speech2AffectiveGestures: Synthesizing Co-Speech Gestures with Generative Adversarial Affective Expression Learning","created":"2021-07-31","cited_by_count":58},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58},{"id":"1807.05162","title":"Large-Scale Visual Speech Recognition","created":"2018-07-13","cited_by_count":57},{"id":"2008.12405","title":"Adversarial Training for Multi-Channel Sign Language Production","created":"2020-08-27","cited_by_count":57},{"id":"1905.09773","title":"Speech2Face: Learning the Face Behind a Voice","created":"2019-05-23","cited_by_count":55},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55},{"id":"1810.06990","title":"LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild","created":"2018-10-16","cited_by_count":51},{"id":"2008.09918","title":"Quantitative Survey of the State of the Art in Sign Language Recognition","created":"2020-08-22","cited_by_count":50},{"id":"2211.09809","title":"SPACE: Speech-driven Portrait Animation with Controllable Expression","created":"2022-11-17","cited_by_count":49},{"id":"2303.05725","title":"CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition with Variational Alignment","created":"2023-03-10","cited_by_count":45},{"id":"2005.03201","title":"What comprises a good talking-head video generation?: A Survey and Benchmark","created":"2020-05-07","cited_by_count":42},{"id":"2010.05264","title":"Boosting Continuous Sign Language Recognition via Cross Modality Augmentation","created":"2020-10-11","cited_by_count":40},{"id":"2208.10441","title":"The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation","created":"2022-08-22","cited_by_count":40},{"id":"1501.05396","title":"Deep Multimodal Learning for Audio-Visual Speech Recognition","created":"2015-01-22","cited_by_count":38},{"id":"2008.10428","title":"Global-local Enhancement Network for NMFs-aware Sign Language Recognition","created":"2020-08-24","cited_by_count":38},{"id":"2208.09141","title":"G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model","created":"2022-08-19","cited_by_count":38},{"id":"1808.09568","title":"ARBEE: Towards Automated Recognition of Bodily Expression of Emotion In the Wild","created":"2018-08-28","cited_by_count":34},{"id":"2011.09846","title":"Everybody Sign Now: Translating Spoken Language to Photo Realistic Sign Language Video","created":"2020-11-19","cited_by_count":34},{"id":"1701.04851","title":"Synthesizing Normalized Faces from Facial Identity Features","created":"2017-01-17","cited_by_count":33},{"id":"2211.17081","title":"Self-Emphasizing Network for Continuous Sign Language Recognition","created":"2022-11-30","cited_by_count":33},{"id":"2003.03206","title":"Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech Recognition","created":"2020-03-06","cited_by_count":30},{"id":"1812.06589","title":"Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning","created":"2018-12-17","cited_by_count":28},{"id":"1806.06053","title":"Deep Lip Reading: a comparison of models and an online application","created":"2018-06-15","cited_by_count":26},{"id":"2103.15910","title":"Sign Language Production: A Review","created":"2021-03-29","cited_by_count":26},{"id":"1910.00726","title":"Animating Face using Disentangled Audio Representations","created":"2019-10-02","cited_by_count":24}],"next_cursor":"100"}