{"list":"other","total":58,"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":"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"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":"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":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"1807.02758","title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","created":"2018-07-08","cited_by_count":1264},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2103.14006","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","created":"2021-03-25","cited_by_count":529},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"1904.00523","title":"Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model","created":"2019-04-01","cited_by_count":403},{"id":"1608.00367","title":"Accelerating the Super-Resolution Convolutional Neural Network","created":"2016-08-01","cited_by_count":394},{"id":"1804.02815","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","created":"2018-04-09","cited_by_count":371},{"id":"2003.03808","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","created":"2020-03-08","cited_by_count":358},{"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":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"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":"2008.01928","title":"Component Divide-and-Conquer for Real-World Image Super-Resolution","created":"2020-08-05","cited_by_count":246},{"id":"1712.06116","title":"Learning a Single Convolutional Super-Resolution Network for Multiple Degradations","created":"2017-12-17","cited_by_count":228},{"id":"1904.03377","title":"Blind Super-Resolution With Iterative Kernel Correction","created":"2019-04-06","cited_by_count":203},{"id":"1912.07116","title":"Image Processing Using Multi-Code GAN Prior","created":"2019-12-15","cited_by_count":185},{"id":"2012.00739","title":"GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution","created":"2020-12-01","cited_by_count":158},{"id":"2311.04155","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","created":"2023-11-07","cited_by_count":122},{"id":"2203.09195","title":"Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution","created":"2022-03-17","cited_by_count":114},{"id":"2312.08962","title":"Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models","created":"2023-12-14","cited_by_count":105},{"id":"2202.13142","title":"Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors","created":"2022-02-26","cited_by_count":100},{"id":"2103.15295","title":"Best-Buddy GANs for Highly Detailed Image Super-Resolution","created":"2021-03-29","cited_by_count":30},{"id":"2311.14282","title":"Image Super-Resolution with Text Prompt Diffusion","created":"2023-11-24","cited_by_count":23},{"id":"2305.18107","title":"Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution","created":"2023-05-29","cited_by_count":21},{"id":"2308.00729","title":"Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment","created":"2023-08-01","cited_by_count":20},{"id":"2106.04428","title":"Noise Conditional Flow Model for Learning the Super-Resolution Space","created":"2021-06-06","cited_by_count":19},{"id":"2307.16813","title":"Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment","created":"2023-07-31","cited_by_count":18}],"next_cursor":null}