{"list":"other","total":78,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"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":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"1911.07069","title":"Kvasir-SEG: A Segmented Polyp Dataset","created":"2019-11-16","cited_by_count":589},{"id":"1608.03665","title":"Learning Structured Sparsity in Deep Neural Networks","created":"2016-08-12","cited_by_count":541},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2102.04378","title":"TransReID: Transformer-based Object Re-Identification","created":"2021-02-08","cited_by_count":435},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1811.00250","title":"Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration","created":"2018-11-01","cited_by_count":367},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2006.04139","title":"Learning Texture Transformer Network for Image Super-Resolution","created":"2020-06-07","cited_by_count":347},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"1808.06866","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","created":"2018-08-21","cited_by_count":315},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2305.07027","title":"EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention","created":"2023-05-11","cited_by_count":172},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144},{"id":"2106.02852","title":"Patch Slimming for Efficient Vision Transformers","created":"2021-06-05","cited_by_count":133},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94},{"id":"2102.05644","title":"Training Vision Transformers for Image Retrieval","created":"2021-02-10","cited_by_count":90},{"id":"2204.07154","title":"MiniViT: Compressing Vision Transformers with Weight Multiplexing","created":"2022-04-14","cited_by_count":88},{"id":"2007.03260","title":"ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting","created":"2020-07-07","cited_by_count":85},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2104.08500","title":"Vision Transformer Pruning","created":"2021-04-17","cited_by_count":79},{"id":"2203.08243","title":"Unified Visual Transformer Compression","created":"2022-03-15","cited_by_count":79},{"id":"2110.04869","title":"Global Vision Transformer Pruning with Hessian-Aware Saliency","created":"2021-10-10","cited_by_count":70},{"id":"2106.00515","title":"KVT: k-NN Attention for Boosting Vision Transformers","created":"2021-05-28","cited_by_count":65},{"id":"2212.04246","title":"ViTPose++: Vision Transformer for Generic Body Pose Estimation","created":"2022-12-07","cited_by_count":65},{"id":"2203.04570","title":"CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction","created":"2022-03-09","cited_by_count":39},{"id":"2112.14000","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","created":"2021-12-28","cited_by_count":36},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36},{"id":"2207.04976","title":"Dual Vision Transformer","created":"2022-07-11","cited_by_count":29},{"id":"2303.08685","title":"Making Vision Transformers Efficient from A Token Sparsification View","created":"2023-03-15","cited_by_count":29},{"id":"2106.15754","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","created":"2021-06-29","cited_by_count":27},{"id":"2111.12624","title":"Self-slimmed Vision Transformer","created":"2021-11-24","cited_by_count":27},{"id":"2111.11802","title":"Pruning Self-attentions into Convolutional Layers in Single Path","created":"2021-11-23","cited_by_count":24},{"id":"2109.10948","title":"T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression","created":"2021-09-22","cited_by_count":16},{"id":"2201.00043","title":"Multi-Dimensional Model Compression of Vision Transformer","created":"2021-12-31","cited_by_count":13}],"next_cursor":null}