{"list":"other","total":55,"rows":[{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"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":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"1709.05424","title":"NIMA: Neural Image Assessment","created":"2017-09-15","cited_by_count":389},{"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":"1907.02665","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","created":"2019-07-05","cited_by_count":302},{"id":"2311.07575","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","created":"2023-11-13","cited_by_count":286},{"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":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248},{"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":"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":"2005.13983","title":"Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild","created":"2020-05-28","cited_by_count":134},{"id":"1606.01621","title":"Photo Aesthetics Ranking Network with Attributes and Content Adaptation","created":"2016-06-06","cited_by_count":125},{"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":"2208.06857","title":"Underwater Ranker: Learn Which Is Better and How to Be Better","created":"2022-08-14","cited_by_count":67},{"id":"1904.01382","title":"Effective Aesthetics Prediction with Multi-level Spatially Pooled Features","created":"2019-04-02","cited_by_count":53},{"id":"1610.00838","title":"Image Aesthetic Assessment: An Experimental Survey","created":"2016-10-04","cited_by_count":50},{"id":"2303.15166","title":"Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Method","created":"2023-03-27","cited_by_count":49},{"id":"2304.04952","title":"Data-Efficient Image Quality Assessment with Attention-Panel Decoder","created":"2023-04-11","cited_by_count":49},{"id":"1904.08632","title":"Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data","created":"2019-04-18","cited_by_count":21},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21},{"id":"2404.15655","title":"Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering","created":"2024-04-24","cited_by_count":21},{"id":"2308.01587","title":"Consistency Regularization for Generalizable Source-free Domain Adaptation","created":"2023-08-03","cited_by_count":17},{"id":"1908.11310","title":"Aesthetic Image Captioning From Weakly-Labelled Photographs","created":"2019-08-29","cited_by_count":12},{"id":"2206.00809","title":"Distilling Knowledge from Object Classification to Aesthetics Assessment","created":"2022-06-02","cited_by_count":12},{"id":"2312.04838","title":"Learning Generalizable Perceptual Representations for Data-Efficient No-Reference Image Quality Assessment","created":"2023-12-08","cited_by_count":11},{"id":"2312.05897","title":"PSCR: Patches Sampling-based Contrastive Regression for AIGC Image Quality Assessment","created":"2023-12-10","cited_by_count":10},{"id":"2111.04647","title":"Composition and Style Attributes Guided Image Aesthetic Assessment","created":"2021-11-08","cited_by_count":9},{"id":"2309.13242","title":"UniHead: Unifying Multi-Perception for Detection Heads","created":"2023-09-23","cited_by_count":9},{"id":"2302.05940","title":"SemanticAC: Semantics-Assisted Framework for Audio Classification","created":"2023-02-12","cited_by_count":7},{"id":"1708.04890","title":"A deep architecture for unified aesthetic prediction","created":"2017-08-16","cited_by_count":6},{"id":"2403.11529","title":"Video Object Segmentation with Dynamic Query Modulation","created":"2024-03-18","cited_by_count":2}],"next_cursor":null}