{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"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":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"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":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2406.14515","title":"MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding","created":"2024-06-20","cited_by_count":182},{"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":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"1908.00375","title":"Quality Assessment of In-the-Wild Videos","created":"2019-08-01","cited_by_count":164},{"id":"1703.07514","title":"Video Frame Interpolation via Adaptive Convolution","created":"2017-03-22","cited_by_count":158},{"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":"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":"2312.08962","title":"Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models","created":"2023-12-14","cited_by_count":105},{"id":"2303.00440","title":"Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation","created":"2023-03-01","cited_by_count":98},{"id":"2304.00451","title":"Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild","created":"2023-04-02","cited_by_count":97},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93},{"id":"2210.05357","title":"Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment","created":"2022-10-11","cited_by_count":50},{"id":"2303.14933","title":"MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos","created":"2023-03-27","cited_by_count":46},{"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":"2409.20063","title":"Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs","created":"2024-09-30","cited_by_count":39},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38},{"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},{"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},{"id":"2303.00521","title":"Quality-aware Pre-trained Models for Blind Image Quality Assessment","created":"2023-03-01","cited_by_count":15},{"id":"2411.03795","title":"VQA$^2$: Visual Question Answering for Video Quality Assessment","created":"2024-11-06","cited_by_count":15},{"id":"2307.12774","title":"Fast Full-frame Video Stabilization with Iterative Optimization","created":"2023-07-24","cited_by_count":8},{"id":"2407.16541","title":"QPT V2: Masked Image Modeling Advances Visual Scoring","created":"2024-07-23","cited_by_count":8},{"id":"2401.14718","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","created":"2024-01-26","cited_by_count":7}],"next_cursor":null}