{"list":"other","total":86,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"1901.08971","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","created":"2019-01-25","cited_by_count":1101},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"1711.09020","title":"StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation","created":"2017-11-24","cited_by_count":1039},{"id":"1801.09414","title":"CosFace: Large Margin Cosine Loss for Deep Face Recognition","created":"2018-01-29","cited_by_count":971},{"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":"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":"2007.14808","title":"Face2Face: Real-time Face Capture and Reenactment of RGB Videos","created":"2020-07-29","cited_by_count":632},{"id":"2012.03065","title":"Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction","created":"2020-12-05","cited_by_count":467},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"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":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1712.00981","title":"Feature Generating Networks for Zero-Shot Learning","created":"2017-12-04","cited_by_count":257},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255},{"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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250},{"id":"1612.01887","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","created":"2016-12-06","cited_by_count":232},{"id":"2112.07471","title":"I M Avatar: Implicit Morphable Head Avatars from Videos","created":"2021-12-14","cited_by_count":231},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","cited_by_count":208},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203},{"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":"2104.07452","title":"Audio-Driven Emotional Video Portraits","created":"2021-04-15","cited_by_count":180},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169},{"id":"1710.00925","title":"Fine-Grained Head Pose Estimation Without Keypoints","created":"2017-10-02","cited_by_count":163},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"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":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131},{"id":"1611.06067","title":"An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data","created":"2016-11-18","cited_by_count":126},{"id":"2206.08343","title":"Realistic One-shot Mesh-based Head Avatars","created":"2022-06-16","cited_by_count":119},{"id":"2008.10174","title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","created":"2020-08-24","cited_by_count":118},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"2012.08261","title":"HeadGAN: One-shot Neural Head Synthesis and Editing","created":"2020-12-15","cited_by_count":105},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"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":"2106.09965","title":"HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping","created":"2021-06-18","cited_by_count":92},{"id":"1911.08139","title":"MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets","created":"2019-11-19","cited_by_count":90},{"id":"2108.07938","title":"FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning","created":"2021-08-18","cited_by_count":90},{"id":"2207.11243","title":"Multiface: A Dataset for Neural Face Rendering","created":"2022-07-22","cited_by_count":87},{"id":"1807.11079","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","created":"2018-07-29","cited_by_count":85},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"1909.07061","title":"Motion Guided Attention for Video Salient Object Detection","created":"2019-09-16","cited_by_count":72},{"id":"2304.05097","title":"One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field","created":"2023-04-11","cited_by_count":68},{"id":"1904.09135","title":"Data Augmentation Using GANs","created":"2019-04-19","cited_by_count":58},{"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":"1712.09382","title":"Audio to Body Dynamics","created":"2017-12-19","cited_by_count":48},{"id":"2104.07995","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","created":"2021-04-16","cited_by_count":47},{"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":"2304.10168","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","created":"2023-04-20","cited_by_count":42},{"id":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34},{"id":"2011.04439","title":"FACEGAN: Facial Attribute Controllable rEenactment GAN","created":"2020-11-09","cited_by_count":32},{"id":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32},{"id":"1902.00267","title":"ColorNet: Investigating the importance of color spaces for image classification","created":"2019-02-01","cited_by_count":31},{"id":"2008.07783","title":"Mesh Guided One-shot Face Reenactment using Graph Convolutional Networks","created":"2020-08-18","cited_by_count":30},{"id":"2202.00046","title":"Finding Directions in GAN's Latent Space for Neural Face Reenactment","created":"2022-01-31","cited_by_count":27},{"id":"2206.04790","title":"Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition","created":"2022-06-09","cited_by_count":27},{"id":"2111.04928","title":"SAFA: Structure Aware Face Animation","created":"2021-11-09","cited_by_count":20},{"id":"2305.06225","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2023-05-10","cited_by_count":20},{"id":"2210.02755","title":"Audio-Visual Face Reenactment","created":"2022-10-06","cited_by_count":18},{"id":"2209.13375","title":"StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face Reenactment","created":"2022-09-27","cited_by_count":17},{"id":"2208.10922","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","created":"2022-08-23","cited_by_count":14},{"id":"2303.11548","title":"Emotionally Enhanced Talking Face Generation","created":"2023-03-21","cited_by_count":14},{"id":"2304.02846","title":"Synthetic Sample Selection for Generalized Zero-Shot Learning","created":"2023-04-06","cited_by_count":14},{"id":"2210.01559","title":"Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis","created":"2022-10-02","cited_by_count":10},{"id":"2210.05825","title":"Controllable Radiance Fields for Dynamic Face Synthesis","created":"2022-10-11","cited_by_count":8}],"next_cursor":null}