{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T09:43:56Z","timestamp":1762508636655,"version":"3.37.3"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000140","name":"United States Department of Transportation","doi-asserted-by":"publisher","award":["69A3551747111"],"award-info":[{"award-number":["69A3551747111"]}],"id":[{"id":"10.13039\/100000140","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1109\/iv48863.2021.9575392","type":"proceedings-article","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T20:59:16Z","timestamp":1635800356000},"page":"1095-1101","source":"Crossref","is-referenced-by-count":3,"title":["Temp-Frustum Net: 3D Object Detection with Temporal Fusion"],"prefix":"10.1109","author":[{"given":"Emec","family":"Ercelik","sequence":"first","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich,Garching b.München,Germany,85748"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ekim","family":"Yurtsever","sequence":"additional","affiliation":[{"name":"Ohio State University,Columbus,OH,USA,43212"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alois","family":"Knoll","sequence":"additional","affiliation":[{"name":"Chair of Robotics, Artificial Intelligence and Real-time Systems, Technical University of Munich,Garching b.München,Germany,85748"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Lidar-based online 3d video object detection with graph-based message passing and spatiotemporal transformer attention","author":"junbo","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref32","article-title":"An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds","author":"rui","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref31","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"kyunghyun","year":"2014","journal-title":"ArXiv Preprint"},{"key":"ref30","article-title":"FlowNet3D++: Geometric losses for deep scene flow estimation","author":"zirui","year":"0","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"ref34","article-title":"3d Object Detection For Autonomous Driving Using Temporal Lidar Data","author":"scott","year":"0","journal-title":"2020 IEEE International Conference on Image Processing (ICIP)"},{"key":"ref10","article-title":"GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking With 2D-3D Multi-Feature Learning","author":"xinshuo","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref11","article-title":"Voxelnet: End-to-end learning for point cloud based 3d object detection","author":"yin","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref12","article-title":"Joint 3d proposal generation and object detection from view aggregation","author":"jason","year":"0","journal-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref13","article-title":"Pv-rcnn: Point-voxel feature set abstraction for 3d object detection","author":"shaoshuai","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref14","article-title":"Seq-nms for video object detection","author":"wei","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"2896","article-title":"T-cnn: Tubelets with convolutional neural networks for object detection from videos","volume":"28 10","author":"kai","year":"2017","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"ref16","article-title":"Spatially supervised recurrent convolutional neural networks for visual object tracking","author":"guanghan","year":"0","journal-title":"2017 IEEE International Symposium on Circuits and Systems (ISCAS)"},{"key":"ref17","article-title":"Flow-guided feature aggregation for video object detection","author":"xizhou","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref18","article-title":"Retinatrack: Online single stage joint detection and tracking","author":"zhichao","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref19","article-title":"You only watch once: A unified cnn architecture for real-time spatiotemporal action localization","author":"k\u00f6p\u00fckl\u00fc","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"Std: Sparse-to-dense 3d object detector for point cloud","author":"zetong","year":"0","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref4","article-title":"Context matters: Refining object detection in video with recurrent neural networks","author":"subarna","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref27","article-title":"3dssd: Point-based 3d single stage object detector","author":"zetong","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00102"},{"key":"ref6","article-title":"Mobile video object detection with temporally-aware feature maps","author":"mason","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref29","article-title":"Flownet3d: Learning scene flow in 3d point clouds","author":"xingyu","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref5","article-title":"Online video object detection using association LSTM","author":"yongyi","year":"0","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref8","article-title":"Tracking Objects as Points","author":"xingyi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Center-based 3d object detection and tracking","author":"tianwei","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref9","article-title":"A Simple Baseline for Multi-Object Tracking","author":"yifu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"andreas","year":"0","journal-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref20","article-title":"Con-volutional two-stream network fusion for video action recognition","author":"christoph","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref22","article-title":"Quo vadis, action recognition? a new model and the kinetics dataset","author":"joao","year":"0","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref21","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"limin","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"ref24","article-title":"Stm: Spatiotemporal and motion encoding for action recognition","author":"boyuan","year":"0","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref23","article-title":"Eco: Efficient convolutional network for online video understanding","author":"mohammadreza","year":"0","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"ref26","article-title":"Structure aware single-stage 3d object detection from point cloud","author":"chenhang","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref25","article-title":"Temporal pyramid network for action recognition","author":"ceyuan","year":"0","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"}],"event":{"name":"2021 IEEE Intelligent Vehicles Symposium (IV)","start":{"date-parts":[[2021,7,11]]},"location":"Nagoya, Japan","end":{"date-parts":[[2021,7,17]]}},"container-title":["2021 IEEE Intelligent Vehicles Symposium (IV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9575127\/9575130\/09575392.pdf?arnumber=9575392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:20:30Z","timestamp":1659486030000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9575392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iv48863.2021.9575392","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]}}}