{"list":"other","total":70,"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"1903.07071","title":"Bag of Tricks and A Strong Baseline for Deep Person Re-identification","created":"2019-03-17","cited_by_count":430},{"id":"1904.07220","title":"Learning Discriminative Model Prediction for Tracking","created":"2019-04-15","cited_by_count":344},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"1905.00953","title":"Omni-Scale Feature Learning for Person Re-Identification","created":"2019-05-02","cited_by_count":295},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"id":"1611.09224","title":"ECO: Efficient Convolution Operators for Tracking","created":"2016-11-28","cited_by_count":239},{"id":"2006.09214","title":"FCOS: A simple and strong anchor-free object detector","created":"2020-06-14","cited_by_count":171},{"id":"1904.08008","title":"Clustered Object Detection in Aerial Images","created":"2019-04-16","cited_by_count":83},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70},{"id":"2003.12949","title":"AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization","created":"2020-03-29","cited_by_count":62},{"id":"1912.10664","title":"Scale Match for Tiny Person Detection","created":"2019-12-23","cited_by_count":61},{"id":"1804.06882","title":"Pelee: A Real-Time Object Detection System on Mobile Devices","created":"2018-04-18","cited_by_count":56},{"id":"2004.05520","title":"Density Map Guided Object Detection in Aerial Images","created":"2020-04-12","cited_by_count":56},{"id":"1711.08561","title":"Adversarial Feature Augmentation for Unsupervised Domain Adaptation","created":"2017-11-23","cited_by_count":48},{"id":"1908.02231","title":"Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking","created":"2019-08-06","cited_by_count":47},{"id":"1706.03038","title":"Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection","created":"2017-06-09","cited_by_count":46},{"id":"2011.02298","title":"Effective Fusion Factor in FPN for Tiny Object Detection","created":"2020-11-04","cited_by_count":44},{"id":"2012.00914","title":"MEVA: A Large-Scale Multiview, Multimodal Video Dataset for Activity Detection","created":"2020-12-02","cited_by_count":44},{"id":"1912.07148","title":"Predicting the Future: A Jointly Learnt Model for Action Anticipation","created":"2019-12-16","cited_by_count":41},{"id":"1803.02988","title":"Rethinking Feature Distribution for Loss Functions in Image Classification","created":"2018-03-08","cited_by_count":39},{"id":"1908.05024","title":"Person Re-identification in Aerial Imagery","created":"2019-08-14","cited_by_count":36},{"id":"2108.11765","title":"Physical Adversarial Attacks on an Aerial Imagery Object Detector","created":"2021-08-26","cited_by_count":35},{"id":"2105.02440","title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","created":"2021-05-06","cited_by_count":31},{"id":"2103.01451","title":"Explainable Person Re-Identification with Attribute-guided Metric Distillation","created":"2021-03-02","cited_by_count":24},{"id":"1806.00746","title":"Eye in the Sky: Real-time Drone Surveillance System (DSS) for Violent Individuals Identification using ScatterNet Hybrid Deep Learning Network","created":"2018-06-03","cited_by_count":20},{"id":"2009.08835","title":"Search and Rescue with Airborne Optical Sectioning","created":"2020-09-18","cited_by_count":20},{"id":"2011.03822","title":"Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection","created":"2020-11-07","cited_by_count":20},{"id":"1901.02602","title":"UAV-GESTURE: A Dataset for UAV Control and Gesture Recognition","created":"2019-01-09","cited_by_count":19},{"id":"2007.07355","title":"TinyVIRAT: Low-resolution Video Action Recognition","created":"2020-07-14","cited_by_count":16},{"id":"2009.07506","title":"The 1st Tiny Object Detection Challenge:Methods and Results","created":"2020-09-16","cited_by_count":14},{"id":"1902.07327","title":"Video Face Recognition: Component-wise Feature Aggregation Network (C-FAN)","created":"2019-02-19","cited_by_count":13},{"id":"2110.04119","title":"A Multi-viewpoint Outdoor Dataset for Human Action Recognition","created":"2021-10-07","cited_by_count":11},{"id":"1909.02959","title":"Discriminative and Robust Online Learning for Siamese Visual Tracking","created":"2019-09-06","cited_by_count":10},{"id":"1909.12743","title":"MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery","created":"2019-09-27","cited_by_count":10},{"id":"2006.02597","title":"COMET: Context-Aware IoU-Guided Network for Small Object Tracking","created":"2020-06-04","cited_by_count":10},{"id":"1910.10027","title":"Human Action Recognition in Drone Videos using a Few Aerial Training Examples","created":"2019-10-22","cited_by_count":9},{"id":"2012.12991","title":"SyNet: An Ensemble Network for Object Detection in UAV Images","created":"2020-12-23","cited_by_count":9},{"id":"2004.02782","title":"The P-DESTRE: A Fully Annotated Dataset for Pedestrian Detection, Tracking, Re-Identification and Search from Aerial Devices","created":"2020-04-06","cited_by_count":8},{"id":"2011.11304","title":"Space-based Global Maritime Surveillance. Part I: Satellite Technologies","created":"2020-11-23","cited_by_count":8},{"id":"2101.12694","title":"Gaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizing","created":"2021-01-29","cited_by_count":8},{"id":"1808.01106","title":"Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification","created":"2018-08-03","cited_by_count":6},{"id":"1710.02039","title":"Integrating Boundary and Center Correlation Filters for Visual Tracking with Aspect Ratio Variation","created":"2017-10-05","cited_by_count":5},{"id":"1812.06408","title":"Human Pose and Path Estimation from Aerial Video using Dynamic Classifier Selection","created":"2018-12-16","cited_by_count":5},{"id":"1905.09481","title":"Constrained Design of Deep Iris Networks","created":"2019-05-23","cited_by_count":4},{"id":"1904.12019","title":"Recurrent Embedding Aggregation Network for Video Face Recognition","created":"2019-04-26","cited_by_count":3},{"id":"2012.03265","title":"Towards Better Object Detection in Scale Variation with Adaptive Feature Selection","created":"2020-12-06","cited_by_count":3}],"next_cursor":null}