{"list":"other","total":60,"rows":[{"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"id":"2204.04676","title":"Simple Baselines for Image Restoration","created":"2022-04-10","cited_by_count":708},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"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":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"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":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388},{"id":"2104.13371","title":"BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment","created":"2021-04-27","cited_by_count":342},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326},{"id":"2311.16518","title":"SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution","created":"2023-11-27","cited_by_count":315},{"id":"2406.08177","title":"One-Step Effective Diffusion Network for Real-World Image Super-Resolution","created":"2024-06-12","cited_by_count":246},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"2011.06294","title":"Real-Time Intermediate Flow Estimation for Video Frame Interpolation","created":"2020-11-12","cited_by_count":213},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186},{"id":"2408.05211","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","created":"2024-08-09","cited_by_count":173},{"id":"2206.02146","title":"Recurrent Video Restoration Transformer with Guided Deformable Attention","created":"2022-06-05","cited_by_count":170},{"id":"1704.02738","title":"Detail-revealing Deep Video Super-resolution","created":"2017-04-10","cited_by_count":148},{"id":"2204.04627","title":"Stripformer: Strip Transformer for Fast Image Deblurring","created":"2022-04-10","cited_by_count":140},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"2312.06640","title":"Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution","created":"2023-12-11","cited_by_count":132},{"id":"2404.05225","title":"LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding","created":"2024-04-08","cited_by_count":95},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93},{"id":"2002.10215","title":"On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering","created":"2020-02-24","cited_by_count":78},{"id":"2409.17058","title":"Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors","created":"2024-09-25","cited_by_count":69},{"id":"2206.10810","title":"A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift","created":"2022-06-22","cited_by_count":68},{"id":"2406.06007","title":"CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models","created":"2024-06-10","cited_by_count":64},{"id":"2312.00853","title":"Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution","created":"2023-12-01","cited_by_count":59},{"id":"2411.13383","title":"Adversarial Diffusion Compression for Real-World Image Super-Resolution","created":"2024-11-20","cited_by_count":52},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44},{"id":"2412.15206","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","created":"2024-12-19","cited_by_count":35},{"id":"2407.13987","title":"RealViformer: Investigating Attention for Real-World Video Super-Resolution","created":"2024-07-19","cited_by_count":33},{"id":"2505.16239","title":"DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution","created":"2025-05-22","cited_by_count":31},{"id":"2106.16028","title":"Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network","created":"2021-06-30","cited_by_count":26},{"id":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","cited_by_count":23},{"id":"2211.05588","title":"Watching the News: Towards VideoQA Models that can Read","created":"2022-11-10","cited_by_count":20},{"id":"2212.05342","title":"Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution","created":"2022-12-10","cited_by_count":20},{"id":"2505.21333","title":"MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios","created":"2025-05-27","cited_by_count":18},{"id":"2308.03262","title":"A Benchmark for Chinese-English Scene Text Image Super-resolution","created":"2023-08-07","cited_by_count":17},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5}],"next_cursor":null}