{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"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":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1706.08612","title":"VoxCeleb: a large-scale speaker identification dataset","created":"2017-06-26","cited_by_count":732},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"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":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1907.11922","title":"MaskGAN: Towards Diverse and Interactive Facial Image Manipulation","created":"2019-07-27","cited_by_count":628},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"1903.08527","title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","created":"2019-03-20","cited_by_count":482},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"2004.00288","title":"CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition","created":"2020-04-01","cited_by_count":321},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"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":"1905.03079","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","created":"2019-05-08","cited_by_count":259},{"id":"2106.06340","title":"SimSwap: An Efficient Framework For High Fidelity Face Swapping","created":"2021-06-11","cited_by_count":243},{"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":"2302.01329","title":"Dreamix: Video Diffusion Models are General Video Editors","created":"2023-02-02","cited_by_count":191},{"id":"2104.08223","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","created":"2021-04-16","cited_by_count":190},{"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":"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":"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":"2212.14704","title":"Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models","created":"2022-12-28","cited_by_count":151},{"id":"2005.05535","title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","created":"2020-05-12","cited_by_count":131},{"id":"2212.03293","title":"Diffusion-SDF: Text-to-Shape via Voxelized Diffusion","created":"2022-12-06","cited_by_count":128},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"2004.12000","title":"Neural Head Reenactment with Latent Pose Descriptors","created":"2020-04-24","cited_by_count":106},{"id":"2012.08261","title":"HeadGAN: One-shot Neural Head Synthesis and Editing","created":"2020-12-15","cited_by_count":105},{"id":"2105.04932","title":"One Shot Face Swapping on Megapixels","created":"2021-05-11","cited_by_count":105},{"id":"2207.11770","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","created":"2022-07-24","cited_by_count":97},{"id":"2106.09965","title":"HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping","created":"2021-06-18","cited_by_count":92},{"id":"2104.14754","title":"Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing","created":"2021-04-30","cited_by_count":91},{"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":"1807.11079","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","created":"2018-07-29","cited_by_count":85},{"id":"2212.13344","title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance","created":"2022-12-27","cited_by_count":77},{"id":"2208.13753","title":"Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis","created":"2022-08-29","cited_by_count":75},{"id":"1803.11182","title":"Towards Open-Set Identity Preserving Face Synthesis","created":"2018-03-29","cited_by_count":74},{"id":"2203.15958","title":"High-resolution Face Swapping via Latent Semantics Disentanglement","created":"2022-03-30","cited_by_count":57},{"id":"1804.03447","title":"RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces","created":"2018-04-10","cited_by_count":50},{"id":"2104.07995","title":"Write-a-speaker: Text-based Emotional and Rhythmic Talking-head Generation","created":"2021-04-16","cited_by_count":47},{"id":"2203.04564","title":"Region-Aware Face Swapping","created":"2022-03-09","cited_by_count":45},{"id":"2209.13514","title":"StyleSwap: Style-Based Generator Empowers Robust Face Swapping","created":"2022-09-27","cited_by_count":39},{"id":"1805.04771","title":"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings","created":"2018-05-12","cited_by_count":38},{"id":"2109.10595","title":"Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation","created":"2021-09-22","cited_by_count":36},{"id":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34},{"id":"2003.12957","title":"Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose","created":"2020-03-29","cited_by_count":26},{"id":"1803.09803","title":"Generating Talking Face Landmarks from Speech","created":"2018-03-26","cited_by_count":15},{"id":"2208.10922","title":"StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation","created":"2022-08-23","cited_by_count":14},{"id":"2212.02797","title":"FlowFace: Semantic Flow-guided Shape-aware Face Swapping","created":"2022-12-06","cited_by_count":6},{"id":"1910.08685","title":"Real-Time Lip Sync for Live 2D Animation","created":"2019-10-19","cited_by_count":4}],"next_cursor":null}