{"list":"other","total":67,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"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":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"1606.09549","title":"Fully-Convolutional Siamese Networks for Object Tracking","created":"2016-06-30","cited_by_count":568},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1812.11703","title":"SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks","created":"2018-12-31","cited_by_count":446},{"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":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"1809.02165","title":"Deep Learning for Generic Object Detection: A Survey","created":"2018-09-06","cited_by_count":392},{"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":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"2003.06957","title":"Frustratingly Simple Few-Shot Object Detection","created":"2020-03-16","cited_by_count":282},{"id":"1812.01866","title":"Few-shot Object Detection via Feature Reweighting","created":"2018-12-05","cited_by_count":265},{"id":"1904.11490","title":"RepPoints: Point Set Representation for Object Detection","created":"2019-04-25","cited_by_count":264},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"id":"2103.11681","title":"Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking","created":"2021-03-22","cited_by_count":220},{"id":"1908.01998","title":"Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector","created":"2019-08-06","cited_by_count":206},{"id":"1808.06048","title":"Distractor-aware Siamese Networks for Visual Object Tracking","created":"2018-08-18","cited_by_count":187},{"id":"1909.13032","title":"Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning","created":"2019-09-28","cited_by_count":182},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"1911.12836","title":"Siam R-CNN: Visual Tracking by Re-Detection","created":"2019-11-28","cited_by_count":174},{"id":"1908.08207","title":"Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes","created":"2019-08-22","cited_by_count":171},{"id":"1901.01660","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","created":"2019-01-07","cited_by_count":156},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"2007.12107","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","created":"2020-07-23","cited_by_count":142},{"id":"1711.07767","title":"Receptive Field Block Net for Accurate and Fast Object Detection","created":"2017-11-21","cited_by_count":141},{"id":"1711.06897","title":"Single-Shot Refinement Neural Network for Object Detection","created":"2017-11-18","cited_by_count":129},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128},{"id":"2003.04668","title":"Incremental Few-Shot Object Detection","created":"2020-03-10","cited_by_count":102},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98},{"id":"2103.15158","title":"Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection","created":"2021-03-28","cited_by_count":77},{"id":"1811.04533","title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","created":"2018-11-12","cited_by_count":76},{"id":"1911.12529","title":"One-Shot Object Detection with Co-Attention and Co-Excitation","created":"2019-11-28","cited_by_count":67},{"id":"1802.08817","title":"A Twofold Siamese Network for Real-Time Object Tracking","created":"2018-02-24","cited_by_count":62},{"id":"1605.05863","title":"Siamese Instance Search for Tracking","created":"2016-05-19","cited_by_count":60},{"id":"2203.06883","title":"Accelerating DETR Convergence via Semantic-Aligned Matching","created":"2022-03-14","cited_by_count":58},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52},{"id":"1908.06290","title":"Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Network","created":"2019-08-17","cited_by_count":51},{"id":"2110.03921","title":"ViDT: An Efficient and Effective Fully Transformer-based Object Detector","created":"2021-10-08","cited_by_count":46},{"id":"2103.11731","title":"Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation","created":"2021-03-22","cited_by_count":44},{"id":"1903.00857","title":"CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery","created":"2019-03-03","cited_by_count":43},{"id":"2003.05905","title":"Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses","created":"2020-03-12","cited_by_count":43},{"id":"1811.07487","title":"Re-Identification with Consistent Attentive Siamese Networks","created":"2018-11-19","cited_by_count":40},{"id":"2007.08508","title":"RepPoints V2: Verification Meets Regression for Object Detection","created":"2020-07-16","cited_by_count":40},{"id":"1711.00164","title":"Improving Object Localization with Fitness NMS and Bounded IoU Loss","created":"2017-11-01","cited_by_count":31},{"id":"1708.03918","title":"Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals","created":"2017-08-13","cited_by_count":23},{"id":"1808.01911","title":"Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification","created":"2018-08-03","cited_by_count":14}],"next_cursor":null}