{"list":"other","total":78,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"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":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"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":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1906.09756","title":"Cascade R-CNN: High Quality Object Detection and Instance Segmentation","created":"2019-06-24","cited_by_count":429},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"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":"1809.03327","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","created":"2018-09-06","cited_by_count":383},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"1912.03458","title":"Dynamic Convolution: Attention over Convolution Kernels","created":"2019-12-07","cited_by_count":356},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"id":"1903.05134","title":"Universally Slimmable Networks and Improved Training Techniques","created":"2019-03-12","cited_by_count":221},{"id":"2106.08322","title":"Dynamic Head: Unifying Object Detection Heads with Attentions","created":"2021-06-15","cited_by_count":187},{"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":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"2006.09214","title":"FCOS: A simple and strong anchor-free object detector","created":"2020-06-14","cited_by_count":171},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"id":"2003.12063","title":"Memory Enhanced Global-Local Aggregation for Video Object Detection","created":"2020-03-26","cited_by_count":128},{"id":"2104.01318","title":"Efficient DETR: Improving End-to-End Object Detector with Dense Prior","created":"2021-04-03","cited_by_count":128},{"id":"2004.06002","title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","created":"2020-04-13","cited_by_count":103},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98},{"id":"1907.06390","title":"Sequence Level Semantics Aggregation for Video Object Detection","created":"2019-07-15","cited_by_count":87},{"id":"2103.10284","title":"SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentation","created":"2021-03-18","cited_by_count":87},{"id":"2103.13258","title":"Dynamic Slimmable Network","created":"2021-03-24","cited_by_count":83},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79},{"id":"2201.05047","title":"TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2022-01-13","cited_by_count":78},{"id":"2012.04150","title":"Dynamic Anchor Learning for Arbitrary-Oriented Object Detection","created":"2020-12-08","cited_by_count":70},{"id":"1602.08465","title":"Seq-NMS for Video Object Detection","created":"2016-02-26","cited_by_count":68},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","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":"1904.03629","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","created":"2019-04-07","cited_by_count":66},{"id":"1906.04423","title":"NAS-FCOS: Fast Neural Architecture Search for Object Detection","created":"2019-06-11","cited_by_count":53},{"id":"2105.00637","title":"ISTR: End-to-End Instance Segmentation with Transformers","created":"2021-05-03","cited_by_count":52},{"id":"2109.03495","title":"Temporal RoI Align for Video Object Recognition","created":"2021-09-08","cited_by_count":44},{"id":"1604.04053","title":"Object Detection from Video Tubelets with Convolutional Neural Networks","created":"2016-04-14","cited_by_count":40},{"id":"2105.10920","title":"End-to-End Video Object Detection with Spatial-Temporal Transformers","created":"2021-05-23","cited_by_count":40},{"id":"2108.05821","title":"TF-Blender: Temporal Feature Blender for Video Object Detection","created":"2021-08-12","cited_by_count":37},{"id":"2012.02366","title":"DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation","created":"2020-12-04","cited_by_count":33},{"id":"1709.05943","title":"Fast YOLO: A Fast You Only Look Once System for Real-time Embedded Object Detection in Video","created":"2017-09-18","cited_by_count":30},{"id":"2203.15935","title":"Graph Neural Networks in IoT: A Survey","created":"2022-03-29","cited_by_count":28},{"id":"1911.09929","title":"SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection","created":"2019-11-22","cited_by_count":25},{"id":"1711.05187","title":"Dynamic Zoom-in Network for Fast Object Detection in Large Images","created":"2017-11-14","cited_by_count":23},{"id":"2008.05678","title":"Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze","created":"2020-08-13","cited_by_count":18},{"id":"2209.02242","title":"PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection","created":"2022-09-06","cited_by_count":17},{"id":"2009.11050","title":"Robust and efficient post-processing for video object detection","created":"2020-09-23","cited_by_count":16},{"id":"2012.03519","title":"Fine-Grained Dynamic Head for Object Detection","created":"2020-12-07","cited_by_count":16},{"id":"2205.10706","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","created":"2022-05-22","cited_by_count":16},{"id":"2007.13816","title":"Corner Proposal Network for Anchor-free, Two-stage Object Detection","created":"2020-07-27","cited_by_count":14},{"id":"2205.02101","title":"Dynamic Sparse R-CNN","created":"2022-05-04","cited_by_count":11},{"id":"2110.07790","title":"DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception","created":"2021-10-15","cited_by_count":10},{"id":"2012.00779","title":"Dynamic Feature Pyramid Networks for Object Detection","created":"2020-12-01","cited_by_count":8},{"id":"2110.12423","title":"NAS-FCOS: Efficient Search for Object Detection Architectures","created":"2021-10-24","cited_by_count":6},{"id":"2207.05252","title":"Dynamic Proposals for Efficient Object Detection","created":"2022-07-12","cited_by_count":6},{"id":"2210.00588","title":"DFA: Dynamic Feature Aggregation for Efficient Video Object Detection","created":"2022-10-02","cited_by_count":5}],"next_cursor":null}