{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1803.10704","title":"End-to-End Multi-Task Learning with Attention","created":"2018-03-28","cited_by_count":534},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"2012.13392","title":"Deep Learning-Based Human Pose Estimation: A Survey","created":"2020-12-24","cited_by_count":207},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2312.01725","title":"StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On","created":"2023-12-04","cited_by_count":175},{"id":"2012.11866","title":"Human Action Recognition from Various Data Modalities: A Review","created":"2020-12-22","cited_by_count":163},{"id":"2307.04087","title":"SVIT: Scaling up Visual Instruction Tuning","created":"2023-07-09","cited_by_count":162},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141},{"id":"2206.14180","title":"High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions","created":"2022-06-28","cited_by_count":130},{"id":"2402.11530","title":"Efficient Multimodal Learning from Data-centric Perspective","created":"2024-02-18","cited_by_count":122},{"id":"2007.12342","title":"CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations","created":"2020-07-24","cited_by_count":109},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104},{"id":"2109.04425","title":"Talk-to-Edit: Fine-Grained Facial Editing via Dialog","created":"2021-09-09","cited_by_count":102},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86},{"id":"2103.13841","title":"Universal Representation Learning from Multiple Domains for Few-shot Classification","created":"2021-03-25","cited_by_count":56},{"id":"2403.16558","title":"Elysium: Exploring Object-level Perception in Videos via MLLM","created":"2024-03-25","cited_by_count":48},{"id":"2002.05907","title":"A Survey on 3D Skeleton-Based Action Recognition Using Learning Method","created":"2020-02-14","cited_by_count":47},{"id":"2406.08100","title":"Multimodal Table Understanding","created":"2024-06-12","cited_by_count":44},{"id":"2304.03195","title":"Micron-BERT: BERT-based Facial Micro-Expression Recognition","created":"2023-04-06","cited_by_count":43},{"id":"1705.00389","title":"Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation","created":"2017-04-30","cited_by_count":35},{"id":"2205.15996","title":"Text2Human: Text-Driven Controllable Human Image Generation","created":"2022-05-31","cited_by_count":31},{"id":"2406.17770","title":"MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning","created":"2024-06-25","cited_by_count":22},{"id":"2408.09530","title":"PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding","created":"2024-08-18","cited_by_count":16},{"id":"2407.08515","title":"15M Multimodal Facial Image-Text Dataset","created":"2024-07-11","cited_by_count":14},{"id":"2403.16528","title":"Open-Set Recognition in the Age of Vision-Language Models","created":"2024-03-25","cited_by_count":13},{"id":"2407.04287","title":"MARS: Paying more attention to visual attributes for text-based person search","created":"2024-07-05","cited_by_count":11},{"id":"2110.08934","title":"On the Effect of Selfie Beautification Filters on Face Detection and Recognition","created":"2021-10-17","cited_by_count":10},{"id":"2302.05576","title":"Sketch Less Face Image Retrieval: A New Challenge","created":"2023-02-11","cited_by_count":4},{"id":"2407.19178","title":"Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection","created":"2024-07-27","cited_by_count":3}],"next_cursor":null}