{"list":"other","total":63,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"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":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"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":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","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":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2411.15098","title":"OminiControl: Minimal and Universal Control for Diffusion Transformer","created":"2024-11-22","cited_by_count":340},{"id":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287},{"id":"1711.08447","title":"VITON: An Image-based Virtual Try-on Network","created":"2017-11-22","cited_by_count":286},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"1807.07688","title":"Toward Characteristic-Preserving Image-based Virtual Try-On Network","created":"2018-07-20","cited_by_count":192},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"id":"2204.08532","title":"Dress Code: High-Resolution Multi-Category Virtual Try-On","created":"2022-04-18","cited_by_count":162},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158},{"id":"2003.12267","title":"Controllable Person Image Synthesis with Attribute-Decomposed GAN","created":"2020-03-27","cited_by_count":150},{"id":"2003.05863","title":"Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\\leftrightarrow$Preserving Image Content","created":"2020-03-12","cited_by_count":149},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141},{"id":"2012.02780","title":"Few-shot Image Generation with Elastic Weight Consolidation","created":"2020-12-04","cited_by_count":122},{"id":"2303.13756","title":"GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning","created":"2023-03-24","cited_by_count":120},{"id":"2007.02721","title":"Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On","created":"2020-07-03","cited_by_count":77},{"id":"2207.09161","title":"Single Stage Virtual Try-on via Deformable Attention Flows","created":"2022-07-19","cited_by_count":65},{"id":"2406.07547","title":"Zero-shot Image Editing with Reference Imitation","created":"2024-06-11","cited_by_count":65},{"id":"2403.12965","title":"Wear-Any-Way: Manipulable Virtual Try-on via Sparse Correspondence Alignment","created":"2024-03-19","cited_by_count":43},{"id":"2111.10544","title":"Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN","created":"2021-11-20","cited_by_count":40},{"id":"2412.08486","title":"Learning Flow Fields in Attention for Controllable Person Image Generation","created":"2024-12-11","cited_by_count":27},{"id":"2410.05259","title":"GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting","created":"2024-10-07","cited_by_count":13},{"id":"2503.12165","title":"VTON 360: High-Fidelity Virtual Try-On from Any Viewing Direction","created":"2025-03-15","cited_by_count":10},{"id":"2501.06230","title":"BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation","created":"2025-01-08","cited_by_count":7}],"next_cursor":null}