{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1709.05424","title":"NIMA: Neural Image Assessment","created":"2017-09-15","cited_by_count":389},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379},{"id":"1910.06180","title":"KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment","created":"2019-10-14","cited_by_count":355},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"1907.02665","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","created":"2019-07-05","cited_by_count":302},{"id":"2303.14420","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","created":"2023-03-25","cited_by_count":287},{"id":"2303.14968","title":"Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective","created":"2023-03-27","cited_by_count":280},{"id":"2309.14181","title":"Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision","created":"2023-09-25","cited_by_count":249},{"id":"1612.01697","title":"Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment","created":"2016-12-06","cited_by_count":225},{"id":"1912.10088","title":"From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality","created":"2019-12-20","cited_by_count":223},{"id":"1511.02919","title":"Massive Online Crowdsourced Study of Subjective and Objective Picture Quality","created":"2015-11-09","cited_by_count":209},{"id":"2303.06555","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","created":"2023-03-12","cited_by_count":187},{"id":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179},{"id":"2108.06858","title":"No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency","created":"2021-08-16","cited_by_count":166},{"id":"2004.05508","title":"MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment","created":"2020-04-11","cited_by_count":144},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"id":"2005.14354","title":"UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content","created":"2020-05-29","cited_by_count":140},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128},{"id":"1606.01621","title":"Photo Aesthetics Ranking Network with Attributes and Content Adaptation","created":"2016-06-06","cited_by_count":125},{"id":"2101.10955","title":"RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content","created":"2021-01-26","cited_by_count":100},{"id":"2304.00451","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","created":"2023-04-02","cited_by_count":97},{"id":"2110.13266","title":"Image Quality Assessment using Contrastive Learning","created":"2021-10-25","cited_by_count":95},{"id":"2101.01097","title":"Transformer for Image Quality Assessment","created":"2020-12-30","cited_by_count":76},{"id":"1609.04757","title":"Perceptual Quality Prediction on Authentically Distorted Images Using a Bag of Features Approach","created":"2016-09-15","cited_by_count":71},{"id":"2105.14550","title":"Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training","created":"2021-05-30","cited_by_count":71},{"id":"2307.00211","title":"AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence","created":"2023-07-01","cited_by_count":61},{"id":"1904.01382","title":"Effective Aesthetics Prediction with Multi-level Spatially Pooled Features","created":"2019-04-02","cited_by_count":53},{"id":"2304.14298","title":"Instance Segmentation in the Dark","created":"2023-04-27","cited_by_count":46},{"id":"2402.03413","title":"Perceptual Video Quality Assessment: A Survey","created":"2024-02-05","cited_by_count":43},{"id":"2204.04900","title":"Confusing Image Quality Assessment: Towards Better Augmented Reality Experience","created":"2022-04-11","cited_by_count":32},{"id":"1708.08190","title":"A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction","created":"2017-08-28","cited_by_count":28},{"id":"2004.03015","title":"Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment","created":"2020-04-06","cited_by_count":28},{"id":"2204.08308","title":"Saliency in Augmented Reality","created":"2022-04-18","cited_by_count":17},{"id":"2404.01024","title":"AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Images","created":"2024-04-01","cited_by_count":16},{"id":"1904.08879","title":"No-Reference Quality Assessment of Contrast-Distorted Images using Contrast Enhancement","created":"2019-04-18","cited_by_count":14},{"id":"2302.06298","title":"Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance","created":"2023-02-13","cited_by_count":13},{"id":"2201.01492","title":"FAVER: Blind Quality Prediction of Variable Frame Rate Videos","created":"2022-01-05","cited_by_count":10},{"id":"2404.15163","title":"Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment","created":"2024-04-23","cited_by_count":10},{"id":"2404.07537","title":"How is Visual Attention Influenced by Text Guidance? Database and Model","created":"2024-04-11","cited_by_count":7}],"next_cursor":null}