{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"2203.08679","title":"Decoupled Knowledge Distillation","created":"2022-03-16","cited_by_count":388},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2011.10043","title":"Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning","created":"2020-11-19","cited_by_count":297},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","cited_by_count":290},{"id":"2206.01191","title":"EfficientFormer: Vision Transformers at MobileNet Speed","created":"2022-06-02","cited_by_count":241},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2304.11968","title":"Track Anything: Segment Anything Meets Videos","created":"2023-04-24","cited_by_count":234},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"2305.06558","title":"Segment and Track Anything","created":"2023-05-11","cited_by_count":193},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"id":"2304.04155","title":"Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging","created":"2023-04-09","cited_by_count":161},{"id":"2304.04709","title":"Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection","created":"2023-04-10","cited_by_count":100},{"id":"1411.5878","title":"Salient Object Detection: A Survey","created":"2014-11-18","cited_by_count":98},{"id":"2304.10261","title":"Anything-3D: Towards Single-view Anything Reconstruction in the Wild","created":"2023-04-19","cited_by_count":92},{"id":"2208.06049","title":"MILAN: Masked Image Pretraining on Language Assisted Representation","created":"2022-08-11","cited_by_count":69},{"id":"2207.05501","title":"Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios","created":"2022-07-12","cited_by_count":65},{"id":"2207.07116","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","created":"2022-07-14","cited_by_count":60},{"id":"2305.10289","title":"Explain Any Concept: Segment Anything Meets Concept-Based Explanation","created":"2023-05-17","cited_by_count":37},{"id":"2208.12256","title":"Masked Autoencoders Enable Efficient Knowledge Distillers","created":"2022-08-25","cited_by_count":36},{"id":"2305.00278","title":"Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected","created":"2023-04-29","cited_by_count":34},{"id":"2211.10526","title":"Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference","created":"2022-11-18","cited_by_count":28},{"id":"2305.14207","title":"SAD: Segment Any RGBD","created":"2023-05-23","cited_by_count":14},{"id":"2307.07757","title":"Open Scene Understanding: Grounded Situation Recognition Meets Segment Anything for Helping People with Visual Impairments","created":"2023-07-15","cited_by_count":13},{"id":"2306.02094","title":"Segment Anything Meets Semantic Communication","created":"2023-06-03","cited_by_count":8},{"id":"2305.13093","title":"Restore Anything Pipeline: Segment Anything Meets Image Restoration","created":"2023-05-22","cited_by_count":6},{"id":"2309.11715","title":"Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal","created":"2023-09-21","cited_by_count":2}],"next_cursor":null}