{"list":"other","total":124,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"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":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"1808.06601","title":"Video-to-Video Synthesis","created":"2018-08-20","cited_by_count":390},{"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":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"2401.09603","title":"Rethinking FID: Towards a Better Evaluation Metric for Image Generation","created":"2023-11-30","cited_by_count":310},{"id":"2012.02181","title":"BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond","created":"2020-12-03","cited_by_count":304},{"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":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2306.07954","title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","created":"2023-06-13","cited_by_count":253},{"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":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"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":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201},{"id":"1611.06624","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","created":"2016-11-21","cited_by_count":198},{"id":"1806.02067","title":"PieAPP: Perceptual Image-Error Assessment through Pairwise Preference","created":"2018-06-06","cited_by_count":160},{"id":"2311.04287","title":"Holistic Evaluation of Text-To-Image Models","created":"2023-11-07","cited_by_count":160},{"id":"2011.13544","title":"Patch-VQ: 'Patching Up' the Video Quality Problem","created":"2020-11-27","cited_by_count":147},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"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":"2308.09388","title":"Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey","created":"2023-08-18","cited_by_count":109},{"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":"2101.10955","title":"RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content","created":"2021-01-26","cited_by_count":100},{"id":"2212.10015","title":"Benchmarking Spatial Relationships in Text-to-Image Generation","created":"2022-12-20","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":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79},{"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":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61},{"id":"1904.01121","title":"HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models","created":"2019-04-01","cited_by_count":59},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59},{"id":"2303.12618","title":"A Perceptual Quality Assessment Exploration for AIGC Images","created":"2023-03-22","cited_by_count":55},{"id":"2012.11895","title":"Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Metric","created":"2020-12-22","cited_by_count":53},{"id":"1510.00477","title":"Learning a Discriminative Model for the Perception of Realism in Composite Images","created":"2015-10-02","cited_by_count":52},{"id":"1906.03973","title":"E-LPIPS: Robust Perceptual Image Similarity via Random Transformation Ensembles","created":"2019-06-10","cited_by_count":45},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44},{"id":"2304.03271","title":"Making AI Less \"Thirsty\": Uncovering and Addressing the Secret Water Footprint of AI Models","created":"2023-04-06","cited_by_count":44},{"id":"2403.10854","title":"A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment","created":"2024-03-16","cited_by_count":43},{"id":"2312.13834","title":"Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis","created":"2023-12-20","cited_by_count":39},{"id":"2403.11956","title":"Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment","created":"2024-03-18","cited_by_count":39},{"id":"2112.02851","title":"No-Reference Point Cloud Quality Assessment via Domain Adaptation","created":"2021-12-06","cited_by_count":38},{"id":"2406.11802","title":"PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models","created":"2024-06-17","cited_by_count":36},{"id":"2404.03407","title":"AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment","created":"2024-04-04","cited_by_count":33},{"id":"2307.04749","title":"Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback","created":"2023-07-10","cited_by_count":32},{"id":"2402.17403","title":"Sora Generates Videos with Stunning Geometrical Consistency","created":"2024-02-27","cited_by_count":31},{"id":"2210.00933","title":"Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop","created":"2022-10-03","cited_by_count":30},{"id":"2305.10843","title":"X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models","created":"2023-05-18","cited_by_count":28},{"id":"2307.15157","title":"R-LPIPS: An Adversarially Robust Perceptual Similarity Metric","created":"2023-07-27","cited_by_count":28},{"id":"2401.01651","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","created":"2024-01-03","cited_by_count":27},{"id":"2404.17762","title":"Large Multi-modality Model Assisted AI-Generated Image Quality Assessment","created":"2024-04-27","cited_by_count":24},{"id":"2309.08009","title":"Measuring the Quality of Text-to-Video Model Outputs: Metrics and Dataset","created":"2023-09-14","cited_by_count":23}],"next_cursor":"100"}