{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"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":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"1908.09791","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","created":"2019-08-26","cited_by_count":787},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1705.03122","title":"Convolutional Sequence to Sequence Learning","created":"2017-05-08","cited_by_count":552},{"id":"1710.05006","title":"Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2017-10-13","cited_by_count":549},{"id":"2304.12620","title":"Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation","created":"2023-04-25","cited_by_count":490},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2004.08955","title":"ResNeSt: Split-Attention Networks","created":"2020-04-19","cited_by_count":445},{"id":"1903.06586","title":"Selective Kernel Networks","created":"2019-03-15","cited_by_count":403},{"id":"1704.06904","title":"Residual Attention Network for Image Classification","created":"2017-04-23","cited_by_count":386},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364},{"id":"1904.09925","title":"Attention Augmented Convolutional Networks","created":"2019-04-22","cited_by_count":363},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2006.03677","title":"Visual Transformers: Token-based Image Representation and Processing for Computer Vision","created":"2020-06-05","cited_by_count":334},{"id":"2004.13621","title":"Exploring Self-attention for Image Recognition","created":"2020-04-28","cited_by_count":313},{"id":"2304.13785","title":"Customized Segment Anything Model for Medical Image Segmentation","created":"2023-04-26","cited_by_count":280},{"id":"2207.10666","title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","created":"2022-07-21","cited_by_count":234},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212},{"id":"2003.11142","title":"BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models","created":"2020-03-24","cited_by_count":188},{"id":"2104.12099","title":"Visual Saliency Transformer","created":"2021-04-25","cited_by_count":175},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"1907.06781","title":"Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks","created":"2019-07-15","cited_by_count":133},{"id":"2101.07663","title":"Salient Object Detection via Integrity Learning","created":"2021-01-19","cited_by_count":133},{"id":"2007.08074","title":"Suppress and Balance: A Simple Gated Network for Salient Object Detection","created":"2020-07-16","cited_by_count":126},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124},{"id":"2304.05750","title":"Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications","created":"2023-04-12","cited_by_count":121},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107},{"id":"1411.5878","title":"Salient Object Detection: A Survey","created":"2014-11-18","cited_by_count":98},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86},{"id":"2108.03557","title":"Context-Aware Mixup for Domain Adaptive Semantic Segmentation","created":"2021-08-08","cited_by_count":79},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"2004.08514","title":"DMT: Dynamic Mutual Training for Semi-Supervised Learning","created":"2020-04-18","cited_by_count":77},{"id":"2304.06022","title":"SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything","created":"2023-04-12","cited_by_count":75},{"id":"2205.12853","title":"Deep Gradient Learning for Efficient Camouflaged Object Detection","created":"2022-05-25","cited_by_count":65},{"id":"2007.03380","title":"Re-thinking Co-Salient Object Detection","created":"2020-07-07","cited_by_count":54},{"id":"1803.06091","title":"Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground","created":"2018-03-16","cited_by_count":47},{"id":"2004.08878","title":"Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation","created":"2020-04-19","cited_by_count":45},{"id":"2304.05640","title":"Instance-Aware Domain Generalization for Face Anti-Spoofing","created":"2023-04-12","cited_by_count":42},{"id":"2312.06660","title":"EdgeSAM: Prompt-In-the-Loop Distillation for SAM","created":"2023-12-11","cited_by_count":41},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40},{"id":"2207.10015","title":"Generative Domain Adaptation for Face Anti-Spoofing","created":"2022-07-20","cited_by_count":33},{"id":"2108.07142","title":"PIT: Position-Invariant Transform for Cross-FoV Domain Adaptation","created":"2021-08-16","cited_by_count":30},{"id":"2108.03553","title":"Self-Adversarial Disentangling for Specific Domain Adaptation","created":"2021-08-08","cited_by_count":29},{"id":"2207.09868","title":"Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofing","created":"2022-07-20","cited_by_count":28},{"id":"2105.03053","title":"Salient Objects in Clutter","created":"2021-05-07","cited_by_count":19},{"id":"2110.05170","title":"Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization","created":"2021-10-11","cited_by_count":16},{"id":"2309.16483","title":"Rethinking Domain Generalization: Discriminability and Generalizability","created":"2023-09-28","cited_by_count":16},{"id":"2108.06649","title":"Semi-supervised 3D Object Detection via Adaptive Pseudo-Labeling","created":"2021-08-15","cited_by_count":14},{"id":"2205.11397","title":"Super Vision Transformer","created":"2022-05-23","cited_by_count":13},{"id":"2309.16460","title":"Diverse Target and Contribution Scheduling for Domain Generalization","created":"2023-09-28","cited_by_count":10},{"id":"2206.04170","title":"CASS: Cross Architectural Self-Supervision for Medical Image Analysis","created":"2022-06-08","cited_by_count":6},{"id":"2211.12040","title":"Rethinking Implicit Neural Representations for Vision Learners","created":"2022-11-22","cited_by_count":4}],"next_cursor":null}