{"list":"other","total":67,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"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":"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":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"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":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2311.04257","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","created":"2023-11-07","cited_by_count":547},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"1709.05424","title":"NIMA: Neural Image Assessment","created":"2017-09-15","cited_by_count":389},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"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":"2401.16420","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","created":"2024-01-29","cited_by_count":326},{"id":"1907.02665","title":"Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network","created":"2019-07-05","cited_by_count":302},{"id":"2408.04840","title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","created":"2024-08-09","cited_by_count":291},{"id":"2402.17245","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","created":"2024-02-27","cited_by_count":256},{"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":"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":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195},{"id":"1806.02067","title":"PieAPP: Perceptual Image-Error Assessment through Pairwise Preference","created":"2018-06-06","cited_by_count":160},{"id":"2012.02310","title":"BoxInst: High-Performance Instance Segmentation with Box Annotations","created":"2020-12-03","cited_by_count":151},{"id":"2306.04717","title":"AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment","created":"2023-06-07","cited_by_count":142},{"id":"2007.03034","title":"Nonlinear Transform Coding","created":"2020-07-06","cited_by_count":136},{"id":"2011.08612","title":"Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things","created":"2020-11-17","cited_by_count":111},{"id":"2310.14918","title":"ARNIQA: Learning Distortion Manifold for Image Quality Assessment","created":"2023-10-20","cited_by_count":89},{"id":"2207.13038","title":"Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models","created":"2022-07-26","cited_by_count":64},{"id":"2204.10485","title":"Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network","created":"2022-04-22","cited_by_count":57},{"id":"2203.14713","title":"Image-text Retrieval: A Survey on Recent Research and Development","created":"2022-03-28","cited_by_count":55},{"id":"2303.12618","title":"A Perceptual Quality Assessment Exploration for AIGC Images","created":"2023-03-22","cited_by_count":55},{"id":"2401.02677","title":"Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss","created":"2024-01-05","cited_by_count":52},{"id":"2108.07948","title":"Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","created":"2021-08-18","cited_by_count":41},{"id":"2206.11695","title":"NTIRE 2022 Challenge on Perceptual Image Quality Assessment","created":"2022-06-23","cited_by_count":41},{"id":"2012.10150","title":"SCNet: Training Inference Sample Consistency for Instance Segmentation","created":"2020-12-18","cited_by_count":38},{"id":"2109.04760","title":"ReconfigISP: Reconfigurable Camera Image Processing Pipeline","created":"2021-09-10","cited_by_count":30},{"id":"2402.16749","title":"MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model","created":"2024-02-26","cited_by_count":30},{"id":"2211.01146","title":"DynamicISP: Dynamically Controlled Image Signal Processor for Image Recognition","created":"2022-11-02","cited_by_count":23},{"id":"2112.04719","title":"Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision","created":"2021-12-09","cited_by_count":22},{"id":"2303.09290","title":"VDPVE: VQA Dataset for Perceptual Video Enhancement","created":"2023-03-16","cited_by_count":22},{"id":"2104.10315","title":"Visual Analysis Motivated Rate-Distortion Model for Image Coding","created":"2021-04-21","cited_by_count":21},{"id":"2303.08050","title":"Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images","created":"2023-03-14","cited_by_count":21},{"id":"2401.01117","title":"Q-Refine: A Perceptual Quality Refiner for AI-Generated Image","created":"2024-01-02","cited_by_count":21},{"id":"2404.16687","title":"NTIRE 2024 Quality Assessment of AI-Generated Content Challenge","created":"2024-04-25","cited_by_count":20},{"id":"2003.07848","title":"Learning to Structure an Image with Few Colors","created":"2020-03-17","cited_by_count":9},{"id":"2404.18343","title":"G-Refine: A General Quality Refiner for Text-to-Image Generation","created":"2024-04-29","cited_by_count":8},{"id":"2211.06797","title":"Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling","created":"2022-11-13","cited_by_count":7},{"id":"2406.09356","title":"CMC-Bench: Towards a New Paradigm of Visual Signal Compression","created":"2024-06-13","cited_by_count":6},{"id":"2412.17477","title":"Predicting Satisfied User and Machine Ratio for Compressed Images: A Unified Approach","created":"2024-12-23","cited_by_count":1}],"next_cursor":null}