{"total":164,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503,"area":null},{"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,"area":null},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"area":null},{"id":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179,"area":null},{"id":"2203.15086","title":"X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval","created":"2022-03-28","cited_by_count":128,"area":null},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"area":null},{"id":"2101.10955","title":"RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content","created":"2021-01-26","cited_by_count":100,"area":null},{"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,"area":null},{"id":"2402.16641","title":"Towards Open-ended Visual Quality Comparison","created":"2024-02-26","cited_by_count":85,"area":null},{"id":"2407.16124","title":"Fr\\'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos","created":"2024-07-23","cited_by_count":58,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51,"area":null},{"id":"2210.05357","title":"Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment","created":"2022-10-11","cited_by_count":50,"area":null},{"id":"2303.14933","title":"MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos","created":"2023-03-27","cited_by_count":46,"area":null},{"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,"area":null},{"id":"2206.09853","title":"DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment","created":"2022-06-20","cited_by_count":41,"area":null},{"id":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39,"area":"mllm"},{"id":"2307.13981","title":"Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models","created":"2023-07-26","cited_by_count":38,"area":null},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38,"area":null},{"id":"2406.06087","title":"GAIA: Rethinking Action Quality Assessment for AI-Generated Videos","created":"2024-06-10","cited_by_count":30,"area":null},{"id":"2404.11313","title":"NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results","created":"2024-04-17","cited_by_count":29,"area":null},{"id":"2408.14008","title":"LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models","created":"2024-08-26","cited_by_count":28,"area":"mllm"},{"id":"2412.19238","title":"FineVQ: Fine-Grained User Generated Content Video Quality Assessment","created":"2024-12-26","cited_by_count":28,"area":null},{"id":"2106.01111","title":"Deep Learning based Full-reference and No-reference Quality Assessment Models for Compressed UGC Videos","created":"2021-06-02","cited_by_count":27,"area":null},{"id":"2211.12109","title":"Video compression dataset and benchmark of learning-based video-quality metrics","created":"2022-11-22","cited_by_count":27,"area":null},{"id":"2207.03723","title":"Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment","created":"2022-07-08","cited_by_count":25,"area":null},{"id":"2206.05054","title":"A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2411.17221","title":"AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM","created":"2024-11-26","cited_by_count":24,"area":"mllm"},{"id":"2302.13269","title":"Exploring Opinion-unaware Video Quality Assessment with Semantic Affinity Criterion","created":"2023-02-26","cited_by_count":23,"area":null},{"id":"2402.19276","title":"Modular Blind Video Quality Assessment","created":"2024-02-29","cited_by_count":23,"area":null},{"id":"2208.14085","title":"Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metric","created":"2022-08-30","cited_by_count":22,"area":null},{"id":"2312.15300","title":"Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models","created":"2023-12-23","cited_by_count":22,"area":null},{"id":"2304.06440","title":"Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment","created":"2023-04-13","cited_by_count":21,"area":null},{"id":"2308.00729","title":"Ada-DQA: Adaptive Diverse Quality-aware Feature Acquisition for Video Quality Assessment","created":"2023-08-01","cited_by_count":20,"area":null},{"id":"2206.14713","title":"CONVIQT: Contrastive Video Quality Estimator","created":"2022-06-29","cited_by_count":19,"area":null},{"id":"2405.08745","title":"Enhancing Blind Video Quality Assessment with Rich Quality-aware Features","created":"2024-05-14","cited_by_count":19,"area":null},{"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,"area":null},{"id":"2211.00366","title":"Universal Perturbation Attack on Differentiable No-Reference Image- and Video-Quality Metrics","created":"2022-11-01","cited_by_count":17,"area":null},{"id":"2405.17765","title":"PTM-VQA: Efficient Video Quality Assessment Leveraging Diverse PreTrained Models from the Wild","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2304.14672","title":"Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment","created":"2023-04-28","cited_by_count":16,"area":null},{"id":"2108.09635","title":"StarVQA: Space-Time Attention for Video Quality Assessment","created":"2021-08-22","cited_by_count":15,"area":null},{"id":"2210.01879","title":"A Perceptual Quality Metric for Video Frame Interpolation","created":"2022-10-04","cited_by_count":15,"area":null},{"id":"2303.00521","title":"Quality-aware Pre-trained Models for Blind Image Quality Assessment","created":"2023-03-01","cited_by_count":15,"area":null},{"id":"2308.04904","title":"StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2411.03795","title":"VQA$^2$: Visual Question Answering for Video Quality Assessment","created":"2024-11-06","cited_by_count":15,"area":"mllm"},{"id":"2412.04508","title":"Video Quality Assessment: A Comprehensive Survey","created":"2024-12-04","cited_by_count":15,"area":null},{"id":"2203.12824","title":"Subjective and Objective Analysis of Streamed Gaming Videos","created":"2022-03-24","cited_by_count":14,"area":null},{"id":"2310.06958","title":"Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2401.02614","title":"Scaling and Masking: A New Paradigm of Data Sampling for Image and Video Quality Assessment","created":"2024-01-05","cited_by_count":13,"area":null},{"id":"2404.13573","title":"Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap","created":"2024-04-21","cited_by_count":13,"area":null},{"id":"2407.21408","title":"Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model","created":"2024-07-31","cited_by_count":13,"area":null},{"id":"2504.09255","title":"FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment","created":"2025-04-12","cited_by_count":13,"area":null},{"id":"2305.09512","title":"Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement","created":"2023-05-16","cited_by_count":12,"area":null},{"id":"2309.13609","title":"Vulnerabilities in Video Quality Assessment Models: The Challenge of Adversarial Attacks","created":"2023-09-24","cited_by_count":12,"area":null},{"id":"2510.08508","title":"MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restoration","created":"2025-10-09","cited_by_count":12,"area":null},{"id":"2311.07090","title":"CLiF-VQA: Enhancing Video Quality Assessment by Incorporating High-Level Semantic Information related to Human Feelings","created":"2023-11-13","cited_by_count":11,"area":null},{"id":"2406.09754","title":"LAVIB: A Large-scale Video Interpolation Benchmark","created":"2024-06-14","cited_by_count":11,"area":null},{"id":"2407.04928","title":"CLIPVQA:Video Quality Assessment via CLIP","created":"2024-07-06","cited_by_count":11,"area":null},{"id":"2503.10259","title":"KVQ: Boosting Video Quality Assessment via Saliency-guided Local Perception","created":"2025-03-13","cited_by_count":11,"area":null},{"id":"2505.19535","title":"TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2201.01492","title":"FAVER: Blind Quality Prediction of Variable Frame Rate Videos","created":"2022-01-05","cited_by_count":10,"area":null},{"id":"2305.17260","title":"Study of Subjective and Objective Quality Assessment of Mobile Cloud Gaming Videos","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2505.12098","title":"LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation","created":"2025-05-17","cited_by_count":10,"area":"mllm"},{"id":"2508.06051","title":"VQAThinker: Exploring Generalizable and Explainable Video Quality Assessment via Reinforcement Learning","created":"2025-08-08","cited_by_count":10,"area":"lr"},{"id":"2207.14489","title":"StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessment","created":"2022-07-29","cited_by_count":9,"area":null},{"id":"2208.13717","title":"StableFace: Analyzing and Improving Motion Stability for Talking Face Generation","created":"2022-08-29","cited_by_count":9,"area":null},{"id":"2212.12734","title":"DDH-QA: A Dynamic Digital Humans Quality Assessment Database","created":"2022-12-24","cited_by_count":9,"area":null},{"id":"2501.08415","title":"Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics","created":"2025-01-14","cited_by_count":9,"area":null},{"id":"2506.01061","title":"AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation","created":"2025-06-01","cited_by_count":9,"area":null},{"id":"2404.09003","title":"THQA: A Perceptual Quality Assessment Database for Talking Heads","created":"2024-04-13","cited_by_count":8,"area":null},{"id":"2407.16541","title":"QPT V2: Masked Image Modeling Advances Visual Scoring","created":"2024-07-23","cited_by_count":8,"area":null},{"id":"2305.15544","title":"Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics","created":"2023-05-24","cited_by_count":7,"area":null},{"id":"2310.15984","title":"Geometry-Aware Video Quality Assessment for Dynamic Digital Human","created":"2023-10-24","cited_by_count":7,"area":null},{"id":"2311.11059","title":"HIDRO-VQA: High Dynamic Range Oracle for Video Quality Assessment","created":"2023-11-18","cited_by_count":7,"area":null},{"id":"2312.15425","title":"Knowledge Guided Semi-Supervised Learning for Quality Assessment of User Generated Videos","created":"2023-12-24","cited_by_count":7,"area":null},{"id":"2408.11982","title":"AIM 2024 Challenge on Compressed Video Quality Assessment: Methods and Results","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2504.20466","title":"LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs","created":"2025-04-29","cited_by_count":7,"area":null},{"id":"2109.00347","title":"A survey on IQA","created":"2021-08-29","cited_by_count":6,"area":null},{"id":"2304.13092","title":"Making Video Quality Assessment Models Robust to Bit Depth","created":"2023-04-25","cited_by_count":6,"area":null},{"id":"2305.02422","title":"GAMIVAL: Video Quality Prediction on Mobile Cloud Gaming Content","created":"2023-05-03","cited_by_count":6,"area":null},{"id":"2307.09729","title":"NTIRE 2023 Quality Assessment of Video Enhancement Challenge","created":"2023-07-19","cited_by_count":6,"area":null},{"id":"2405.03333","title":"Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance","created":"2024-05-06","cited_by_count":6,"area":null},{"id":"2509.02969","title":"VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2210.04158","title":"HVS Revisited: A Comprehensive Video Quality Assessment Framework","created":"2022-10-09","cited_by_count":5,"area":null},{"id":"2505.03631","title":"Generalizable Video Quality Assessment via Weak-to-Strong Learning","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2505.22543","title":"Scaling-up Perceptual Video Quality Assessment","created":"2025-05-28","cited_by_count":5,"area":"mllm"},{"id":"2507.11900","title":"CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos","created":"2025-07-16","cited_by_count":5,"area":null},{"id":"2102.00155","title":"Regression or Classification? New Methods to Evaluate No-Reference Picture and Video Quality Models","created":"2021-01-30","cited_by_count":4,"area":null},{"id":"2111.09503","title":"Blind VQA on 360{\\deg} Video via Progressively Learning from Pixels, Frames and Video","created":"2021-11-18","cited_by_count":4,"area":null},{"id":"2207.09956","title":"Telepresence Video Quality Assessment","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2303.07489","title":"MRET: Multi-resolution Transformer for Video Quality Assessment","created":"2023-03-13","cited_by_count":4,"area":null},{"id":"2304.13156","title":"HDR-ChipQA: No-Reference Quality Assessment on High Dynamic Range Videos","created":"2023-04-25","cited_by_count":4,"area":null},{"id":"2406.08845","title":"Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2407.11496","title":"ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment","created":"2024-07-16","cited_by_count":4,"area":null},{"id":"2410.00289","title":"Delving Deep into Engagement Prediction of Short Videos","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2412.18060","title":"An Ensemble Approach to Short-form Video Quality Assessment Using Multimodal LLM","created":"2024-12-24","cited_by_count":4,"area":"mllm"},{"id":"2501.07087","title":"Video Quality Assessment for Online Processing: From Spatial to Temporal Sampling","created":"2025-01-13","cited_by_count":4,"area":null},{"id":"2506.23852","title":"RGC-VQA: An Exploration Database for Robotic-Generated Video Quality Assessment","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2508.02516","title":"Engagement Prediction of Short Videos with Large Multimodal Models","created":"2025-08-04","cited_by_count":4,"area":"mllm"}],"next_cursor":"100"}