{"list":"other","total":161,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"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":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"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":"1909.04939","title":"InceptionTime: Finding AlexNet for Time Series Classification","created":"2019-09-11","cited_by_count":387},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"1907.02665","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","created":"2019-07-05","cited_by_count":302},{"id":"2201.02973","title":"MAXIM: Multi-Axis MLP for Image Processing","created":"2022-01-09","cited_by_count":302},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"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":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"1811.11127","title":"Unprocessing Images for Learned Raw Denoising","created":"2018-11-27","cited_by_count":250},{"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":"1701.05923","title":"Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks","created":"2017-01-20","cited_by_count":242},{"id":"2308.03060","title":"TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment","created":"2023-08-06","cited_by_count":226},{"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":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"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":"2003.07761","title":"CycleISP: Real Image Restoration via Improved Data Synthesis","created":"2020-03-17","cited_by_count":213},{"id":"1511.02919","title":"Massive Online Crowdsourced Study of Subjective and Objective Picture Quality","created":"2015-11-09","cited_by_count":209},{"id":"2002.08871","title":"Fast Differentiable Sorting and Ranking","created":"2020-02-20","cited_by_count":197},{"id":"1308.3052","title":"Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index","created":"2013-08-14","cited_by_count":195},{"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":"2007.12142","title":"PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration","created":"2020-07-23","cited_by_count":178},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"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":"1908.00375","title":"Quality Assessment of In-the-Wild Videos","created":"2019-08-01","cited_by_count":164},{"id":"2311.06783","title":"Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models","created":"2023-11-12","cited_by_count":152},{"id":"2011.13544","title":"Patch-VQ: 'Patching Up' the Video Quality Problem","created":"2020-11-27","cited_by_count":147},{"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":"2204.14047","title":"A Deep Learning based No-reference Quality Assessment Model for UGC Videos","created":"2022-04-29","cited_by_count":129},{"id":"1803.01761","title":"Large-Scale Study of Perceptual Video Quality","created":"2018-03-05","cited_by_count":127},{"id":"1904.06457","title":"YouTube UGC Dataset for Video Compression Research","created":"2019-04-13","cited_by_count":124},{"id":"2311.01813","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","created":"2023-11-03","cited_by_count":122},{"id":"2101.10955","title":"RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content","created":"2021-01-26","cited_by_count":100},{"id":"2108.08505","title":"Blindly Assess Quality of In-the-Wild Videos via Quality-aware Pre-training and Motion Perception","created":"2021-08-19","cited_by_count":97},{"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":"2310.14918","title":"ARNIQA: Learning Distortion Manifold for Image Quality Assessment","created":"2023-10-20","cited_by_count":89},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85},{"id":"2111.11745","title":"Intriguing Findings of Frequency Selection for Image Deblurring","created":"2021-11-23","cited_by_count":81},{"id":"2101.01097","title":"Transformer for Image Quality Assessment","created":"2020-12-30","cited_by_count":76},{"id":"2011.04263","title":"Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training","created":"2020-11-09","cited_by_count":72},{"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":"2303.12618","title":"A Perceptual Quality Assessment Exploration for AIGC Images","created":"2023-03-22","cited_by_count":55},{"id":"2406.13527","title":"4K4DGen: Panoramic 4D Generation at 4K Resolution","created":"2024-06-19","cited_by_count":54},{"id":"2012.13936","title":"Learning Generalized Spatial-Temporal Deep Feature Representation for No-Reference Video Quality Assessment","created":"2020-12-27","cited_by_count":50},{"id":"2210.05357","title":"Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment","created":"2022-10-11","cited_by_count":50},{"id":"1804.01681","title":"Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning","created":"2018-04-05","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":"2303.14933","title":"MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos","created":"2023-03-27","cited_by_count":46},{"id":"1611.05916","title":"Squared Earth Mover's Distance-based Loss for Training Deep Neural Networks","created":"2016-11-17","cited_by_count":45},{"id":"1906.03973","title":"E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles","created":"2019-06-10","cited_by_count":45},{"id":"2305.12726","title":"Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach","created":"2023-05-22","cited_by_count":45},{"id":"2103.07666","title":"GraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment","created":"2021-03-13","cited_by_count":43},{"id":"2108.08119","title":"Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision","created":"2021-08-18","cited_by_count":43},{"id":"2206.09853","title":"DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment","created":"2022-06-20","cited_by_count":41},{"id":"2403.11956","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","created":"2024-03-18","cited_by_count":39}],"next_cursor":"100"}