{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"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":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"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":"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":"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":"2207.02595","title":"FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling","created":"2022-07-06","cited_by_count":179},{"id":"1908.00375","title":"Quality Assessment of In-the-Wild Videos","created":"2019-08-01","cited_by_count":164},{"id":"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":"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":"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":"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":"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":"2402.03413","title":"Perceptual Video Quality Assessment: A Survey","created":"2024-02-05","cited_by_count":43},{"id":"2307.13981","title":"Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models","created":"2023-07-26","cited_by_count":38},{"id":"2402.07220","title":"KVQ: Kwai Video Quality Assessment for Short-form Videos","created":"2024-02-11","cited_by_count":38},{"id":"2405.18842","title":"Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset","created":"2024-05-29","cited_by_count":38},{"id":"2204.04900","title":"Confusing Image Quality Assessment: Towards Better Augmented Reality Experience","created":"2022-04-11","cited_by_count":32},{"id":"2309.09958","title":"An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models","created":"2023-09-18","cited_by_count":32},{"id":"2408.14008","title":"LMM-VQA: Advancing Video Quality Assessment with Large Multimodal Models","created":"2024-08-26","cited_by_count":28},{"id":"2207.03723","title":"Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment","created":"2022-07-08","cited_by_count":25},{"id":"2407.20928","title":"UniProcessor: A Text-induced Unified Low-level Image Processor","created":"2024-07-30","cited_by_count":22},{"id":"2004.02943","title":"Predicting the Quality of Compressed Videos with Pre-Existing Distortions","created":"2020-04-06","cited_by_count":21},{"id":"1908.11517","title":"UGC-VIDEO: perceptual quality assessment of user-generated videos","created":"2019-08-30","cited_by_count":19},{"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":"2203.12824","title":"Subjective and Objective Analysis of Streamed Gaming Videos","created":"2022-03-24","cited_by_count":14},{"id":"2207.06148","title":"Multiview Contrastive Learning for Completely Blind Video Quality Assessment of User Generated Content","created":"2022-07-13","cited_by_count":5}],"next_cursor":null}