{"list":"other","total":87,"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":"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"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":"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":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"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":"1812.03506","title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale","created":"2018-12-09","cited_by_count":559},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"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":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"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":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"1912.04488","title":"SOLO: Segmenting Objects by Locations","created":"2019-12-10","cited_by_count":289},{"id":"1611.05198","title":"One-Shot Video Object Segmentation","created":"2016-11-16","cited_by_count":235},{"id":"1902.03604","title":"MOTS: Multi-Object Tracking and Segmentation","created":"2019-02-10","cited_by_count":223},{"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":"1505.00487","title":"Sequence to Sequence -- Video to Text","created":"2015-05-03","cited_by_count":158},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"2001.00309","title":"BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation","created":"2020-01-02","cited_by_count":145},{"id":"2006.11339","title":"Video Panoptic Segmentation","created":"2020-06-19","cited_by_count":142},{"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":"2011.01461","title":"Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation","created":"2020-11-03","cited_by_count":121},{"id":"2007.14772","title":"SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation","created":"2020-07-29","cited_by_count":108},{"id":"2106.03299","title":"Video Instance Segmentation using Inter-Frame Communication Transformers","created":"2021-06-07","cited_by_count":105},{"id":"1802.01218","title":"Efficient Video Object Segmentation via Network Modulation","created":"2018-02-04","cited_by_count":98},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98},{"id":"2112.08275","title":"SeqFormer: Sequential Transformer for Video Instance Segmentation","created":"2021-12-15","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":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","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":"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":"1904.03629","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","created":"2019-04-07","cited_by_count":66},{"id":"1711.11577","title":"Towards High Performance Video Object Detection","created":"2017-11-30","cited_by_count":60},{"id":"2204.08412","title":"Temporally Efficient Vision Transformer for Video Instance Segmentation","created":"2022-04-18","cited_by_count":55},{"id":"1908.10072","title":"Controllable Video Captioning with POS Sequence Guidance Based on Gated Fusion Network","created":"2019-08-27","cited_by_count":48},{"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":"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":"2012.02366","title":"DenserNet: Weakly Supervised Visual Localization Using Multi-scale Feature Aggregation","created":"2020-12-04","cited_by_count":33},{"id":"2203.01853","title":"Efficient Video Instance Segmentation via Tracklet Query and Proposal","created":"2022-03-03","cited_by_count":33},{"id":"2112.04632","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","created":"2021-12-09","cited_by_count":21},{"id":"1811.05340","title":"Detect or Track: Towards Cost-Effective Video Object Detection/Tracking","created":"2018-11-13","cited_by_count":18},{"id":"2008.02973","title":"Exploring Rich and Efficient Spatial Temporal Interactions for Real Time Video Salient Object Detection","created":"2020-08-07","cited_by_count":18},{"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":"2007.03200","title":"ReMOTS: Self-Supervised Refining Multi-Object Tracking and Segmentation","created":"2020-07-07","cited_by_count":17},{"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":"2205.10706","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","created":"2022-05-22","cited_by_count":16},{"id":"2009.07498","title":"Dual Semantic Fusion Network for Video Object Detection","created":"2020-09-16","cited_by_count":12},{"id":"2303.08319","title":"FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectors","created":"2023-03-15","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":"2102.09186","title":"Hierarchical Attention Fusion for Geo-Localization","created":"2021-02-18","cited_by_count":9},{"id":"2311.00987","title":"CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentation","created":"2023-11-02","cited_by_count":9},{"id":"2207.05252","title":"Dynamic Proposals for Efficient Object Detection","created":"2022-07-12","cited_by_count":6},{"id":"2307.12239","title":"Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation","created":"2023-07-23","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},{"id":"2402.09241","title":"Efficient One-stage Video Object Detection by Exploiting Temporal Consistency","created":"2024-02-14","cited_by_count":5},{"id":"2002.04597","title":"WatchDog: Real-time Vehicle Tracking on Geo-distributed Edge Nodes","created":"2020-02-11","cited_by_count":3}],"next_cursor":null}