{"list":"other","total":51,"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":"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":"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"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":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1809.02165","title":"Deep Learning for Generic Object Detection: A Survey","created":"2018-09-06","cited_by_count":392},{"id":"1812.08156","title":"Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion","created":"2018-12-19","cited_by_count":307},{"id":"1904.08245","title":"End-to-End Learning of Representations for Asynchronous Event-Based Data","created":"2019-04-17","cited_by_count":217},{"id":"1911.07013","title":"Understanding and Improving Layer Normalization","created":"2019-11-16","cited_by_count":217},{"id":"1804.01310","title":"Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars","created":"2018-04-04","cited_by_count":200},{"id":"1904.08298","title":"Events-to-Video: Bringing Modern Computer Vision to Event Cameras","created":"2019-04-17","cited_by_count":193},{"id":"2009.13436","title":"Learning to Detect Objects with a 1 Megapixel Event Camera","created":"2020-09-28","cited_by_count":186},{"id":"1703.10025","title":"Flow-Guided Feature Aggregation for Video Object Detection","created":"2017-03-29","cited_by_count":177},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"2106.07286","title":"TimeLens: Event-based Video Frame Interpolation","created":"2021-06-14","cited_by_count":151},{"id":"1709.06310","title":"Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios","created":"2017-09-19","cited_by_count":150},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"1807.09713","title":"Asynchronous, Photometric Feature Tracking using Events and Frames","created":"2018-07-25","cited_by_count":118},{"id":"1909.00169","title":"Imbalance Problems in Object Detection: A Review","created":"2019-08-31","cited_by_count":118},{"id":"1811.04256","title":"Scene Text Detection and Recognition: The Deep Learning Era","created":"2018-11-10","cited_by_count":114},{"id":"1705.02950","title":"Learning non-maximum suppression","created":"2017-05-08","cited_by_count":113},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2001.08499","title":"A Large Scale Event-based Detection Dataset for Automotive","created":"2020-01-23","cited_by_count":109},{"id":"2102.09320","title":"Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction","created":"2021-02-18","cited_by_count":90},{"id":"2109.09052","title":"Object Tracking by Jointly Exploiting Frame and Event Domain","created":"2021-09-19","cited_by_count":84},{"id":"1811.02291","title":"MDLatLRR: A novel decomposition method for infrared and visible image fusion","created":"2018-11-06","cited_by_count":54},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52},{"id":"2207.01404","title":"VECtor: A Versatile Event-Centric Benchmark for Multi-Sensor SLAM","created":"2022-07-04","cited_by_count":45},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40},{"id":"1711.06368","title":"Mobile Video Object Detection with Temporally-Aware Feature Maps","created":"2017-11-17","cited_by_count":39},{"id":"2109.02618","title":"Bridging the Gap between Events and Frames through Unsupervised Domain Adaptation","created":"2021-09-06","cited_by_count":37},{"id":"2202.02556","title":"DEVO: Depth-Event Camera Visual Odometry in Challenging Conditions","created":"2022-02-05","cited_by_count":36},{"id":"2011.09170","title":"TJU-DHD: A Diverse High-Resolution Dataset for Object Detection","created":"2020-11-18","cited_by_count":31},{"id":"2010.08278","title":"Real-Time Face & Eye Tracking and Blink Detection using Event Cameras","created":"2020-10-16","cited_by_count":27},{"id":"2011.14448","title":"Improved Handling of Motion Blur in Online Object Detection","created":"2020-11-29","cited_by_count":18},{"id":"2005.01864","title":"Streaming Object Detection for 3-D Point Clouds","created":"2020-05-04","cited_by_count":17},{"id":"2303.09919","title":"Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation","created":"2023-03-17","cited_by_count":16},{"id":"1910.12100","title":"FAB: A Robust Facial Landmark Detection Framework for Motion-Blurred Videos","created":"2019-10-26","cited_by_count":13},{"id":"2207.10433","title":"StreamYOLO: Real-time Object Detection for Streaming Perception","created":"2022-07-21","cited_by_count":7},{"id":"2102.12319","title":"GEM: Glare or Gloom, I Can Still See You -- End-to-End Multimodal Object Detection","created":"2021-02-24","cited_by_count":6},{"id":"2208.08721","title":"Temporal Up-Sampling for Asynchronous Events","created":"2022-08-18","cited_by_count":4}],"next_cursor":null}