{"list":"other","total":57,"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":"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"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":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1604.03540","title":"Training Region-based Object Detectors with Online Hard Example Mining","created":"2016-04-12","cited_by_count":579},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1611.07715","title":"Deep Feature Flow for Video Recognition","created":"2016-11-23","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":"1506.04878","title":"End-to-end people detection in crowded scenes","created":"2015-06-16","cited_by_count":140},{"id":"1710.03958","title":"Detect to Track and Track to Detect","created":"2017-10-11","cited_by_count":131},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"1907.06390","title":"Sequence Level Semantics Aggregation for Video Object Detection","created":"2019-07-15","cited_by_count":87},{"id":"1908.09511","title":"Relation Distillation Networks for Video Object Detection","created":"2019-08-26","cited_by_count":77},{"id":"1602.08465","title":"Seq-NMS for Video Object Detection","created":"2016-02-26","cited_by_count":68},{"id":"1604.02532","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","created":"2016-04-09","cited_by_count":67},{"id":"1711.11577","title":"Towards High Performance Video Object Detection","created":"2017-11-30","cited_by_count":60},{"id":"1803.05549","title":"Object Detection in Video with Spatiotemporal Sampling Networks","created":"2018-03-15","cited_by_count":57},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44},{"id":"1712.06317","title":"Video Object Detection with an Aligned Spatial-Temporal Memory","created":"2017-12-18","cited_by_count":42},{"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":"2108.05821","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","created":"2021-08-12","cited_by_count":37},{"id":"1903.09126","title":"Progressive Sparse Local Attention for Video object detection","created":"2019-03-21","cited_by_count":30},{"id":"1902.02910","title":"AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling","created":"2019-02-08","cited_by_count":27},{"id":"1804.05472","title":"Optimizing Video Object Detection via a Scale-Time Lattice","created":"2018-04-16","cited_by_count":25},{"id":"1903.10172","title":"Looking Fast and Slow: Memory-Guided Mobile Video Object Detection","created":"2019-03-25","cited_by_count":22},{"id":"1809.09294","title":"Object Detection from Scratch with Deep Supervision","created":"2018-09-25","cited_by_count":21},{"id":"2009.11050","title":"Robust and efficient post-processing for video object detection","created":"2020-09-23","cited_by_count":16},{"id":"1904.01784","title":"Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams","created":"2019-04-03","cited_by_count":13},{"id":"2107.13155","title":"Improving Video Instance Segmentation via Temporal Pyramid Routing","created":"2021-07-28","cited_by_count":13},{"id":"2009.07498","title":"Dual Semantic Fusion Network for Video Object Detection","created":"2020-09-16","cited_by_count":12},{"id":"1604.04339","title":"High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks","created":"2016-04-15","cited_by_count":9},{"id":"2009.09660","title":"Feature Flow: In-network Feature Flow Estimation for Video Object Detection","created":"2020-09-21","cited_by_count":6},{"id":"1907.04988","title":"Object Detection in Video with Spatial-temporal Context Aggregation","created":"2019-07-11","cited_by_count":5}],"next_cursor":null}