{"list":"other","total":95,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"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":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"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":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184},{"id":"1511.07571","title":"DenseCap: Fully Convolutional Localization Networks for Dense Captioning","created":"2015-11-24","cited_by_count":176},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"1511.02251","title":"Learning Visual Features from Large Weakly Supervised Data","created":"2015-11-06","cited_by_count":165},{"id":"1810.12440","title":"TallyQA: Answering Complex Counting Questions","created":"2018-10-29","cited_by_count":153},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2008.01392","title":"Learning Visual Representations with Caption Annotations","created":"2020-08-04","cited_by_count":123},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"1702.00824","title":"YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video","created":"2017-02-02","cited_by_count":109},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"1612.09161","title":"Learning Visual N-Grams from Web Data","created":"2016-12-29","cited_by_count":95},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89},{"id":"2007.09554","title":"Referring Expression Comprehension: A Survey of Methods and Datasets","created":"2020-07-19","cited_by_count":79},{"id":"1902.09506","title":"GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering","created":"2019-02-25","cited_by_count":78},{"id":"2301.02229","title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","created":"2023-01-05","cited_by_count":52},{"id":"1712.02310","title":"From Lifestyle Vlogs to Everyday Interactions","created":"2017-12-06","cited_by_count":42},{"id":"2302.08242","title":"Tuning computer vision models with task rewards","created":"2023-02-16","cited_by_count":37},{"id":"1904.01410","title":"Context and Attribute Grounded Dense Captioning","created":"2019-04-02","cited_by_count":31},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24},{"id":"2312.09237","title":"Pixel Aligned Language Models","created":"2023-12-14","cited_by_count":17},{"id":"2303.17376","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","created":"2023-03-30","cited_by_count":10},{"id":"2403.12026","title":"FlexCap: Describe Anything in Images in Controllable Detail","created":"2024-03-18","cited_by_count":7}],"next_cursor":null}