{"list":"other","total":55,"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"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":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"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":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"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":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"1606.05814","title":"Eye Tracking for Everyone","created":"2016-06-18","cited_by_count":155},{"id":"1504.02863","title":"Appearance-Based Gaze Estimation in the Wild","created":"2015-04-11","cited_by_count":153},{"id":"1701.06659","title":"DSSD : Deconvolutional Single Shot Detector","created":"2017-01-23","cited_by_count":131},{"id":"1611.08860","title":"It's Written All Over Your Face: Full-Face Appearance-Based Gaze Estimation","created":"2016-11-27","cited_by_count":123},{"id":"1711.09017","title":"MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation","created":"2017-11-24","cited_by_count":118},{"id":"2003.02501","title":"Detecting Attended Visual Targets in Video","created":"2020-03-05","cited_by_count":77},{"id":"2105.14424","title":"Gaze Estimation using Transformer","created":"2021-05-30","cited_by_count":68},{"id":"1509.04874","title":"DenseBox: Unifying Landmark Localization with End to End Object Detection","created":"2015-09-16","cited_by_count":58},{"id":"1807.10437","title":"Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency","created":"2018-07-27","cited_by_count":53},{"id":"1807.10002","title":"Deep Pictorial Gaze Estimation","created":"2018-07-26","cited_by_count":49},{"id":"2203.10433","title":"End-to-End Human-Gaze-Target Detection with Transformers","created":"2022-03-20","cited_by_count":47},{"id":"2106.02277","title":"Glance-and-Gaze Vision Transformer","created":"2021-06-04","cited_by_count":42},{"id":"1805.04771","title":"Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings","created":"2018-05-12","cited_by_count":38},{"id":"1907.02364","title":"Believe It or Not, We Know What You Are Looking at!","created":"2019-07-04","cited_by_count":38},{"id":"2307.12612","title":"Less is More: Focus Attention for Efficient DETR","created":"2023-07-24","cited_by_count":38},{"id":"2105.10793","title":"GOO: A Dataset for Gaze Object Prediction in Retail Environments","created":"2021-05-22","cited_by_count":26},{"id":"2006.02474","title":"CircleNet: Anchor-free Detection with Circle Representation","created":"2020-06-03","cited_by_count":19},{"id":"2112.03549","title":"GaTector: A Unified Framework for Gaze Object Prediction","created":"2021-12-07","cited_by_count":18},{"id":"1910.07331","title":"A Generalized and Robust Method Towards Practical Gaze Estimation on Smart Phone","created":"2019-10-16","cited_by_count":11},{"id":"2212.14710","title":"NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation","created":"2022-12-30","cited_by_count":10},{"id":"1603.03669","title":"Learning Gaze Transitions from Depth to Improve Video Saliency Estimation","created":"2016-03-11","cited_by_count":9}],"next_cursor":null}