{"list":"other","total":120,"rows":[{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.00915","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","created":"2016-06-02","cited_by_count":3241},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1511.00561","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","created":"2015-11-02","cited_by_count":1487},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"1809.02983","title":"Dual Attention Network for Scene Segmentation","created":"2018-09-09","cited_by_count":1003},{"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":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2004.01888","title":"FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking","created":"2020-04-04","cited_by_count":490},{"id":"2004.01177","title":"Tracking Objects as Points","created":"2020-04-02","cited_by_count":483},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"1810.08462","title":"Fully Convolutional Siamese Networks for Change Detection","created":"2018-10-19","cited_by_count":306},{"id":"2103.00208","title":"Remote Sensing Image Change Detection with Transformers","created":"2021-02-27","cited_by_count":306},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2004.02147","title":"BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation","created":"2020-04-05","cited_by_count":294},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"id":"2201.01293","title":"A Transformer-Based Siamese Network for Change Detection","created":"2022-01-04","cited_by_count":244},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"2104.06399","title":"Co-Scale Conv-Attentional Image Transformers","created":"2021-04-13","cited_by_count":224},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213},{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2008.09397","title":"Align Deep Features for Oriented Object Detection","created":"2020-08-21","cited_by_count":187},{"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":"1908.03930","title":"ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks","created":"2019-08-11","cited_by_count":178},{"id":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169},{"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":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"2103.08808","title":"Track to Detect and Segment: An Online Multi-Object Tracker","created":"2021-03-16","cited_by_count":156},{"id":"2003.02437","title":"Drone-based RGB-Infrared Cross-Modality Vehicle Detection via Uncertainty-Aware Learning","created":"2020-03-05","cited_by_count":152},{"id":"2208.03987","title":"Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model","created":"2022-08-08","cited_by_count":149},{"id":"2207.13532","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","created":"2022-07-27","cited_by_count":133},{"id":"2302.11813","title":"Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identification","created":"2023-02-23","cited_by_count":132},{"id":"2007.14557","title":"Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking","created":"2020-07-29","cited_by_count":115},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2003.13017","title":"Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement","created":"2020-03-29","cited_by_count":105},{"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":"2204.04120","title":"Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline","created":"2022-04-08","cited_by_count":91},{"id":"1904.08008","title":"Clustered Object Detection in Aerial Images","created":"2019-04-16","cited_by_count":83},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83},{"id":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77},{"id":"2103.09136","title":"QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection","created":"2021-03-16","cited_by_count":70},{"id":"2105.11595","title":"SiamMOT: Siamese Multi-Object Tracking","created":"2021-05-25","cited_by_count":62},{"id":"2105.01922","title":"SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Water","created":"2021-05-05","cited_by_count":61},{"id":"2205.10063","title":"Uniform Masking: Enabling MAE Pre-training for Pyramid-based Vision Transformers with Locality","created":"2022-05-20","cited_by_count":57},{"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":"2005.11643","title":"Robust Object Detection under Occlusion with Context-Aware CompositionalNets","created":"2020-05-24","cited_by_count":54},{"id":"2205.13515","title":"Green Hierarchical Vision Transformer for Masked Image Modeling","created":"2022-05-26","cited_by_count":50},{"id":"2304.09670","title":"CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding","created":"2023-04-19","cited_by_count":48},{"id":"2205.13137","title":"MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers","created":"2022-05-26","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":"2204.04716","title":"TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning","created":"2022-04-10","cited_by_count":35},{"id":"2112.10415","title":"UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery","created":"2021-12-20","cited_by_count":34},{"id":"2105.02440","title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","created":"2021-05-06","cited_by_count":31}],"next_cursor":"100"}