{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439},{"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":"1709.03410","title":"One-Shot Learning for Semantic Segmentation","created":"2017-09-11","cited_by_count":337},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"1909.04349","title":"FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images","created":"2019-09-10","cited_by_count":271},{"id":"1703.10896","title":"BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth","created":"2017-03-31","cited_by_count":225},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"2104.01538","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","created":"2021-04-04","cited_by_count":193},{"id":"1902.11020","title":"DPOD: 6D Pose Object Detector and Refiner","created":"2019-02-28","cited_by_count":189},{"id":"2203.04967","title":"UNeXt: MLP-based Rapid Medical Image Segmentation Network","created":"2022-03-09","cited_by_count":185},{"id":"1806.03535","title":"Cell Detection with Star-convex Polygons","created":"2018-06-09","cited_by_count":183},{"id":"2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","created":"2023-09-07","cited_by_count":164},{"id":"2104.08391","title":"Learning To Count Everything","created":"2021-04-16","cited_by_count":150},{"id":"2108.12617","title":"AP-10K: A Benchmark for Animal Pose Estimation in the Wild","created":"2021-08-28","cited_by_count":123},{"id":"1912.03432","title":"Improved Few-Shot Visual Classification","created":"2019-12-07","cited_by_count":115},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"2208.13721","title":"CounTR: Transformer-based Generalised Visual Counting","created":"2022-08-29","cited_by_count":79},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78},{"id":"2006.11702","title":"A Universal Representation Transformer Layer for Few-Shot Image Classification","created":"2020-06-21","cited_by_count":65},{"id":"2211.08217","title":"A Low-Shot Object Counting Network With Iterative Prototype Adaptation","created":"2022-11-15","cited_by_count":65},{"id":"2203.15021","title":"Few-Shot Object Detection with Fully Cross-Transformer","created":"2022-03-28","cited_by_count":64},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59},{"id":"2211.09808","title":"Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks","created":"2022-11-17","cited_by_count":57},{"id":"2212.06826","title":"Look Before You Match: Instance Understanding Matters in Video Object Segmentation","created":"2022-12-13","cited_by_count":34},{"id":"2211.00692","title":"Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks","created":"2022-11-01","cited_by_count":30},{"id":"2303.14969","title":"Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching","created":"2023-03-27","cited_by_count":29},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24},{"id":"2306.13411","title":"Neural Algorithmic Reasoning Without Intermediate Supervision","created":"2023-06-23","cited_by_count":17},{"id":"1901.10802","title":"Automated Skin Lesion Classification Using Ensemble of Deep Neural Networks in ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection Challenge","created":"2019-01-30","cited_by_count":16}],"next_cursor":null}