{"list":"other","total":56,"rows":[{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"2201.00520","title":"Vision Transformer with Deformable Attention","created":"2022-01-03","cited_by_count":295},{"id":"2107.00641","title":"Focal Self-attention for Local-Global Interactions in Vision Transformers","created":"2021-07-01","cited_by_count":288},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"2206.09959","title":"Global Context Vision Transformers","created":"2022-06-20","cited_by_count":98},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91},{"id":"2102.05644","title":"Training Vision Transformers for Image Retrieval","created":"2021-02-10","cited_by_count":90},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90},{"id":"2105.02723","title":"Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet","created":"2021-05-06","cited_by_count":61},{"id":"2206.07990","title":"Patch-level Representation Learning for Self-supervised Vision Transformers","created":"2022-06-16","cited_by_count":60},{"id":"2205.12785","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","created":"2022-05-25","cited_by_count":55},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50},{"id":"2107.14467","title":"DPT: Deformable Patch-based Transformer for Visual Recognition","created":"2021-07-30","cited_by_count":43},{"id":"2108.06747","title":"SOTR: Segmenting Objects with Transformers","created":"2021-08-15","cited_by_count":42},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40},{"id":"2104.08698","title":"A Simple and Effective Positional Encoding for Transformers","created":"2021-04-18","cited_by_count":37},{"id":"2107.02561","title":"Rethinking Positional Encoding","created":"2021-07-06","cited_by_count":37},{"id":"2112.14000","title":"Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention","created":"2021-12-28","cited_by_count":36},{"id":"2204.02964","title":"Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection","created":"2022-04-06","cited_by_count":33},{"id":"2303.04989","title":"ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection","created":"2023-03-09","cited_by_count":32},{"id":"2303.16940","title":"T-FFTRadNet: Object Detection with Swin Vision Transformers from Raw ADC Radar Signals","created":"2023-03-29","cited_by_count":24},{"id":"2208.09885","title":"HST: Hierarchical Swin Transformer for Compressed Image Super-resolution","created":"2022-08-21","cited_by_count":20},{"id":"2210.11909","title":"Boosting vision transformers for image retrieval","created":"2022-10-21","cited_by_count":19},{"id":"2212.07593","title":"Enhanced Training of Query-Based Object Detection via Selective Query Recollection","created":"2022-12-15","cited_by_count":18},{"id":"2109.10948","title":"T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression","created":"2021-09-22","cited_by_count":16},{"id":"1911.12950","title":"Deep Object Co-segmentation via Spatial-Semantic Network Modulation","created":"2019-11-29","cited_by_count":15},{"id":"2108.00045","title":"Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning","created":"2021-07-30","cited_by_count":12},{"id":"2309.12594","title":"DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image","created":"2023-09-22","cited_by_count":12},{"id":"2101.03771","title":"Investigating the Vision Transformer Model for Image Retrieval Tasks","created":"2021-01-11","cited_by_count":11},{"id":"2203.10247","title":"HIPA: Hierarchical Patch Transformer for Single Image Super Resolution","created":"2022-03-19","cited_by_count":11},{"id":"2205.02101","title":"Dynamic Sparse R-CNN","created":"2022-05-04","cited_by_count":11},{"id":"2207.08319","title":"Defect Transformer: An Efficient Hybrid Transformer Architecture for Surface Defect Detection","created":"2022-07-17","cited_by_count":6},{"id":"2402.16370","title":"DEYO: DETR with YOLO for End-to-End Object Detection","created":"2024-02-26","cited_by_count":6},{"id":"2212.07890","title":"Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation","created":"2022-12-15","cited_by_count":5},{"id":"2112.12748","title":"Assessing the Impact of Attention and Self-Attention Mechanisms on the Classification of Skin Lesions","created":"2021-12-23","cited_by_count":4},{"id":"2206.04981","title":"Positional Label for Self-Supervised Vision Transformer","created":"2022-06-10","cited_by_count":4},{"id":"2312.17686","title":"Multiscale Vision Transformers meet Bipartite Matching for efficient single-stage Action Localization","created":"2023-12-29","cited_by_count":4},{"id":"2309.02676","title":"Efficient Training for Visual Tracking with Deformable Transformer","created":"2023-09-06","cited_by_count":1}],"next_cursor":null}