{"list":"other","total":54,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"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":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"1707.02921","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","created":"2017-07-10","cited_by_count":1552},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"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":"1802.08797","title":"Residual Dense Network for Image Super-Resolution","created":"2018-02-24","cited_by_count":799},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"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":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"1712.04143","title":"Benchmarking Single Image Dehazing and Beyond","created":"2017-12-12","cited_by_count":447},{"id":"2205.04437","title":"Activating More Pixels in Image Super-Resolution Transformer","created":"2022-05-09","cited_by_count":438},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403},{"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":"2307.12348","title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","created":"2023-07-23","cited_by_count":365},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"1510.04389","title":"Sketch-based Manga Retrieval using Manga109 Dataset","created":"2015-10-15","cited_by_count":329},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"2303.09472","title":"DiffIR: Efficient Diffusion Model for Image Restoration","created":"2023-03-16","cited_by_count":255},{"id":"2304.01247","title":"Generative Diffusion Prior for Unified Image Restoration and Enhancement","created":"2023-04-03","cited_by_count":199},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2212.11548","title":"Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method","created":"2022-12-22","cited_by_count":174},{"id":"2303.00748","title":"Efficient and Explicit Modelling of Image Hierarchies for Image Restoration","created":"2023-03-01","cited_by_count":145},{"id":"2401.16468","title":"InstructIR: High-Quality Image Restoration Following Human Instructions","created":"2024-01-29","cited_by_count":140},{"id":"2308.03364","title":"Dual Aggregation Transformer for Image Super-Resolution","created":"2023-08-07","cited_by_count":124},{"id":"2306.13090","title":"PromptIR: Prompting for All-in-One Blind Image Restoration","created":"2023-06-22","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":"2411.15269","title":"MambaIRv2: Attentive State Space Restoration","created":"2024-11-22","cited_by_count":94},{"id":"2306.13653","title":"ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration","created":"2023-06-23","cited_by_count":77},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73},{"id":"2402.19387","title":"SeD: Semantic-Aware Discriminator for Image Super-Resolution","created":"2024-02-29","cited_by_count":26},{"id":"2401.01117","title":"Q-Refine: A Perceptual Quality Refiner for AI-Generated Image","created":"2024-01-02","cited_by_count":21},{"id":"2407.10833","title":"MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration","created":"2024-07-15","cited_by_count":15},{"id":"2405.15734","title":"LM4LV: A Frozen Large Language Model for Low-level Vision Tasks","created":"2024-05-24","cited_by_count":13},{"id":"2407.13108","title":"UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt","created":"2024-07-18","cited_by_count":8},{"id":"2309.17014","title":"FreqAlign: Excavating Perception-oriented Transferability for Blind Image Quality Assessment from A Frequency Perspective","created":"2023-09-29","cited_by_count":6}],"next_cursor":null}