{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"1904.03189","title":"Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?","created":"2019-04-05","cited_by_count":675},{"id":"1711.09577","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","created":"2017-11-27","cited_by_count":551},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"id":"1609.03552","title":"Generative Visual Manipulation on the Natural Image Manifold","created":"2016-09-12","cited_by_count":348},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2305.03027","title":"NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads","created":"2023-05-04","cited_by_count":194},{"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":"2312.01725","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","created":"2023-12-04","cited_by_count":175},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2407.15886","title":"CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models","created":"2024-07-21","cited_by_count":102},{"id":"2410.07971","title":"Generalizable and Animatable Gaussian Head Avatar","created":"2024-10-10","cited_by_count":97},{"id":"2403.15931","title":"X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention","created":"2024-03-23","cited_by_count":91},{"id":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88},{"id":"2504.16915","title":"DreamO: A Unified Framework for Image Customization","created":"2025-04-23","cited_by_count":83},{"id":"2201.08361","title":"Stitch it in Time: GAN-Based Facial Editing of Real Videos","created":"2022-01-20","cited_by_count":68},{"id":"2106.11895","title":"A Latent Transformer for Disentangled Face Editing in Images and Videos","created":"2021-06-22","cited_by_count":67},{"id":"2312.07409","title":"DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing","created":"2023-12-12","cited_by_count":67},{"id":"2504.15009","title":"Insert Anything: Image Insertion via In-Context Editing in DiT","created":"2025-04-21","cited_by_count":61},{"id":"2403.07764","title":"Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model","created":"2024-03-12","cited_by_count":45},{"id":"2405.11794","title":"ViViD: Video Virtual Try-on using Diffusion Models","created":"2024-05-20","cited_by_count":42},{"id":"2501.01427","title":"VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control","created":"2025-01-02","cited_by_count":42},{"id":"2212.02802","title":"Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding","created":"2022-12-06","cited_by_count":39},{"id":"2404.19026","title":"MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing","created":"2024-04-29","cited_by_count":38},{"id":"2407.14078","title":"Stable-Hair: Real-World Hair Transfer via Diffusion Model","created":"2024-07-19","cited_by_count":35},{"id":"2302.04868","title":"MEGANE: Morphable Eyeglass and Avatar Network","created":"2023-02-09","cited_by_count":24},{"id":"2405.18172","title":"AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario","created":"2024-05-28","cited_by_count":23},{"id":"2503.13327","title":"Edit Transfer: Learning Image Editing via Vision In-Context Relations","created":"2025-03-17","cited_by_count":23},{"id":"2401.12979","title":"GALA: Generating Animatable Layered Assets from a Single Scan","created":"2024-01-23","cited_by_count":21},{"id":"2412.21206","title":"PERSE: Personalized 3D Generative Avatars from A Single Portrait","created":"2024-12-30","cited_by_count":15},{"id":"2404.03632","title":"Reference-Based 3D-Aware Image Editing with Triplanes","created":"2024-04-04","cited_by_count":9},{"id":"2408.16450","title":"What to Preserve and What to Transfer: Faithful, Identity-Preserving Diffusion-based Hairstyle Transfer","created":"2024-08-29","cited_by_count":8},{"id":"2402.10636","title":"PEGASUS: Personalized Generative 3D Avatars with Composable Attributes","created":"2024-02-16","cited_by_count":7},{"id":"2507.19481","title":"HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars","created":"2025-07-25","cited_by_count":7},{"id":"2302.04871","title":"In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing","created":"2023-02-09","cited_by_count":4},{"id":"2503.19373","title":"DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image","created":"2025-03-25","cited_by_count":4}],"next_cursor":null}