{"list":"other","total":68,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1704.04861","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","created":"2017-04-17","cited_by_count":3845},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1804.03999","title":"Attention U-Net: Learning Where to Look for the Pancreas","created":"2018-04-11","cited_by_count":1435},{"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":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1808.00897","title":"BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation","created":"2018-08-02","cited_by_count":645},{"id":"1511.08458","title":"An Introduction to Convolutional Neural Networks","created":"2015-11-26","cited_by_count":514},{"id":"1810.11981","title":"GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild","created":"2018-10-29","cited_by_count":475},{"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":"1612.00137","title":"RMPE: Regional Multi-person Pose Estimation","created":"2016-12-01","cited_by_count":340},{"id":"1701.07717","title":"Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro","created":"2017-01-26","cited_by_count":281},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"1711.08848","title":"Real-Time Seamless Single Shot 6D Object Pose Prediction","created":"2017-11-24","cited_by_count":210},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167},{"id":"2006.02631","title":"FastReID: A Pytorch Toolbox for General Instance Re-identification","created":"2020-06-04","cited_by_count":166},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131},{"id":"1506.08959","title":"A Large-Scale Car Dataset for Fine-Grained Categorization and Verification","created":"2015-06-30","cited_by_count":130},{"id":"2104.00946","title":"UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles","created":"2021-04-02","cited_by_count":96},{"id":"1909.06043","title":"End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization","created":"2019-09-13","cited_by_count":65},{"id":"1506.03607","title":"P-CNN: Pose-based CNN Features for Action Recognition","created":"2015-06-11","cited_by_count":58},{"id":"2001.11737","title":"AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance","created":"2020-01-31","cited_by_count":56},{"id":"2004.05021","title":"Parsing-based View-aware Embedding Network for Vehicle Re-Identification","created":"2020-04-10","cited_by_count":53},{"id":"2107.05475","title":"GiT: Graph Interactive Transformer for Vehicle Re-identification","created":"2021-07-12","cited_by_count":49},{"id":"1611.05720","title":"Hard-Aware Deeply Cascaded Embedding","created":"2016-11-17","cited_by_count":44},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43},{"id":"2202.12361","title":"RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessment","created":"2022-02-24","cited_by_count":40},{"id":"2004.06271","title":"The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification","created":"2020-04-14","cited_by_count":39},{"id":"2106.08816","title":"SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking","created":"2021-06-16","cited_by_count":38},{"id":"2005.14684","title":"Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification","created":"2020-05-29","cited_by_count":37},{"id":"2312.10114","title":"FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring","created":"2023-12-15","cited_by_count":31},{"id":"1806.09283","title":"RAM: A Region-Aware Deep Model for Vehicle Re-Identification","created":"2018-06-25","cited_by_count":30},{"id":"2101.08446","title":"All-Day Object Tracking for Unmanned Aerial Vehicle","created":"2021-01-21","cited_by_count":28},{"id":"1904.01400","title":"Vehicle Re-identification in Aerial Imagery: Dataset and Approach","created":"2019-04-02","cited_by_count":25},{"id":"1906.08716","title":"Deep-Learning-Based Aerial Image Classification for Emergency Response Applications Using Unmanned Aerial Vehicles","created":"2019-06-20","cited_by_count":25},{"id":"2107.14389","title":"DarkLighter: Light Up the Darkness for UAV Tracking","created":"2021-07-30","cited_by_count":24},{"id":"2303.10951","title":"Tracker Meets Night: A Transformer Enhancer for UAV Tracking","created":"2023-03-20","cited_by_count":23},{"id":"1907.09658","title":"Make Skeleton-based Action Recognition Model Smaller, Faster and Better","created":"2019-07-23","cited_by_count":22},{"id":"1901.01015","title":"Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding","created":"2019-01-04","cited_by_count":21},{"id":"2309.01279","title":"FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees","created":"2023-09-03","cited_by_count":21},{"id":"2201.03080","title":"The State of Aerial Surveillance: A Survey","created":"2022-01-09","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":"2001.11394","title":"ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos","created":"2020-01-30","cited_by_count":18},{"id":"2104.14006","title":"EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion","created":"2021-04-28","cited_by_count":18},{"id":"2202.13073","title":"Global Instance Tracking: Locating Target More Like Humans","created":"2022-02-26","cited_by_count":18},{"id":"2309.10491","title":"DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs","created":"2023-09-19","cited_by_count":16},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13},{"id":"2311.02559","title":"Rotation Invariant Transformer for Recognizing Object in UAVs","created":"2023-11-05","cited_by_count":11},{"id":"1812.04239","title":"Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification","created":"2018-12-11","cited_by_count":6},{"id":"2008.08823","title":"DronePose: Photorealistic UAV-Assistant Dataset Synthesis for 3D Pose Estimation via a Smooth Silhouette Loss","created":"2020-08-20","cited_by_count":5},{"id":"2209.08686","title":"Uncertainty Aware Multitask Pyramid Vision Transformer For UAV-Based Object Re-Identification","created":"2022-09-19","cited_by_count":4},{"id":"1704.03986","title":"2D-3D Pose Consistency-based Conditional Random Fields for 3D Human Pose Estimation","created":"2017-04-13","cited_by_count":3},{"id":"1907.01195","title":"Kite: Automatic speech recognition for unmanned aerial vehicles","created":"2019-07-02","cited_by_count":2}],"next_cursor":null}