{"list":"other","total":62,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"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":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2302.13848","title":"ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation","created":"2023-02-27","cited_by_count":416},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328},{"id":"2004.00288","title":"CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition","created":"2020-04-01","cited_by_count":321},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"id":"1910.09777","title":"Self-Correction for Human Parsing","created":"2019-10-22","cited_by_count":180},{"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":"2204.11823","title":"StyleGAN-Human: A Data-Centric Odyssey of Human Generation","created":"2022-04-25","cited_by_count":144},{"id":"2404.16022","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","created":"2024-04-24","cited_by_count":144},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131},{"id":"2402.03286","title":"Training-Free Consistent Text-to-Image Generation","created":"2024-02-05","cited_by_count":125},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2310.08825","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","created":"2023-10-13","cited_by_count":98},{"id":"2204.01046","title":"Style-Based Global Appearance Flow for Virtual Try-On","created":"2022-04-03","cited_by_count":88},{"id":"2406.04485","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","created":"2024-06-06","cited_by_count":82},{"id":"2306.06638","title":"Face0: Instantaneously Conditioning a Text-to-Image Model on a Face","created":"2023-06-11","cited_by_count":78},{"id":"2310.01596","title":"ImagenHub: Standardizing the evaluation of conditional image generation models","created":"2023-10-02","cited_by_count":77},{"id":"2401.01952","title":"Instruct-Imagen: Image Generation with Multi-modal Instruction","created":"2024-01-03","cited_by_count":65},{"id":"2105.09180","title":"PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency","created":"2021-05-19","cited_by_count":59},{"id":"2411.10499","title":"FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on","created":"2024-11-15","cited_by_count":40},{"id":"2404.01089","title":"Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On","created":"2024-04-01","cited_by_count":38},{"id":"2406.04542","title":"M&M VTO: Multi-Garment Virtual Try-On and Editing","created":"2024-06-06","cited_by_count":29},{"id":"2409.12576","title":"StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation","created":"2024-09-19","cited_by_count":29},{"id":"2412.08486","title":"Learning Flow Fields in Attention for Controllable Person Image Generation","created":"2024-12-11","cited_by_count":27},{"id":"2401.04728","title":"Morphable Diffusion: 3D-Consistent Diffusion for Single-image Avatar Creation","created":"2024-01-09","cited_by_count":23},{"id":"2305.19094","title":"Diffusion Model for Dense Matching","created":"2023-05-30","cited_by_count":21},{"id":"2404.16035","title":"MaGGIe: Masked Guided Gradual Human Instance Matting","created":"2024-04-24","cited_by_count":18},{"id":"2312.04534","title":"PICTURE: PhotorealistIC virtual Try-on from UnconstRained dEsigns","created":"2023-12-07","cited_by_count":14},{"id":"2403.19144","title":"MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation","created":"2024-03-28","cited_by_count":10},{"id":"2409.11904","title":"Finding the Subjective Truth: Collecting 2 Million Votes for Comprehensive Gen-AI Model Evaluation","created":"2024-09-18","cited_by_count":7},{"id":"2106.12154","title":"Neural Fashion Image Captioning : Accounting for Data Diversity","created":"2021-06-23","cited_by_count":5},{"id":"2403.17631","title":"AniArtAvatar: Animatable 3D Art Avatar from a Single Image","created":"2024-03-26","cited_by_count":2}],"next_cursor":null}