Leveraging Temporal Information for 3D Detection and Domain Adaptation

Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-degree sweep, without extensively exploring the temporal information. In this re...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-06
Main Authors: Yu, Cunjun, Cai, Zhongang, Ren, Daxuan, Zhao, Haiyu
Format: Article
Language:English
Subjects:
Learning
Object recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Yu, Cunjun
Cai, Zhongang
Ren, Daxuan
Zhao, Haiyu
description Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-degree sweep, without extensively exploring the temporal information. In this report, we describe a simple way to pass such information in the learning pipeline by adding timestamps to the point clouds, which shows consistent improvements across all three classes.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2419237001</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2419237001</sourcerecordid><originalsourceid>FETCH-proquest_journals_24192370013</originalsourceid><addsrcrecordid>eNqNisEKgkAURYcgSMp_eNBaGN9o1jIyKWjpPh75FEVnbGbs-xPpA1qdy7lnJQJUKo6OCeJGhM51Uko8ZJimKhDFgz9sqWl1AyUPo7HUw13Xxg7kW6NhXqByyNnzaxGkK8jNQK2Gc0WjX7KdWNfUOw5_3Ip9cS0vt2i05j2x88_OTFbP1xOT-IQqkzJW_1Vfi_46wA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2419237001</pqid></control><display><type>article</type><title>Leveraging Temporal Information for 3D Detection and Domain Adaptation</title><source>Publicly Available Content Database</source><creator>Yu, Cunjun ; Cai, Zhongang ; Ren, Daxuan ; Zhao, Haiyu</creator><creatorcontrib>Yu, Cunjun ; Cai, Zhongang ; Ren, Daxuan ; Zhao, Haiyu</creatorcontrib><description>Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-degree sweep, without extensively exploring the temporal information. In this report, we describe a simple way to pass such information in the learning pipeline by adding timestamps to the point clouds, which shows consistent improvements across all three classes.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Learning ; Object recognition</subject><ispartof>arXiv.org, 2020-06</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2419237001?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25731,36989,44566</link.rule.ids></links><search><creatorcontrib>Yu, Cunjun</creatorcontrib><creatorcontrib>Cai, Zhongang</creatorcontrib><creatorcontrib>Ren, Daxuan</creatorcontrib><creatorcontrib>Zhao, Haiyu</creatorcontrib><title>Leveraging Temporal Information for 3D Detection and Domain Adaptation</title><title>arXiv.org</title><description>Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-degree sweep, without extensively exploring the temporal information. In this report, we describe a simple way to pass such information in the learning pipeline by adding timestamps to the point clouds, which shows consistent improvements across all three classes.</description><subject>Learning</subject><subject>Object recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNisEKgkAURYcgSMp_eNBaGN9o1jIyKWjpPh75FEVnbGbs-xPpA1qdy7lnJQJUKo6OCeJGhM51Uko8ZJimKhDFgz9sqWl1AyUPo7HUw13Xxg7kW6NhXqByyNnzaxGkK8jNQK2Gc0WjX7KdWNfUOw5_3Ip9cS0vt2i05j2x88_OTFbP1xOT-IQqkzJW_1Vfi_46wA</recordid><startdate>20200630</startdate><enddate>20200630</enddate><creator>Yu, Cunjun</creator><creator>Cai, Zhongang</creator><creator>Ren, Daxuan</creator><creator>Zhao, Haiyu</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200630</creationdate><title>Leveraging Temporal Information for 3D Detection and Domain Adaptation</title><author>Yu, Cunjun ; Cai, Zhongang ; Ren, Daxuan ; Zhao, Haiyu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24192370013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Learning</topic><topic>Object recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Yu, Cunjun</creatorcontrib><creatorcontrib>Cai, Zhongang</creatorcontrib><creatorcontrib>Ren, Daxuan</creatorcontrib><creatorcontrib>Zhao, Haiyu</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Database (Proquest)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yu, Cunjun</au><au>Cai, Zhongang</au><au>Ren, Daxuan</au><au>Zhao, Haiyu</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Leveraging Temporal Information for 3D Detection and Domain Adaptation</atitle><jtitle>arXiv.org</jtitle><date>2020-06-30</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>Ever since the prevalent use of the LiDARs in autonomous driving, tremendous improvements have been made to the learning on the point clouds. However, recent progress largely focuses on detecting objects in a single 360-degree sweep, without extensively exploring the temporal information. In this report, we describe a simple way to pass such information in the learning pipeline by adding timestamps to the point clouds, which shows consistent improvements across all three classes.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-06
issn 2331-8422
language eng
recordid cdi_proquest_journals_2419237001
source Publicly Available Content Database
subjects Learning
Object recognition
title Leveraging Temporal Information for 3D Detection and Domain Adaptation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T23%3A17%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Leveraging%20Temporal%20Information%20for%203D%20Detection%20and%20Domain%20Adaptation&rft.jtitle=arXiv.org&rft.au=Yu,%20Cunjun&rft.date=2020-06-30&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2419237001%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_24192370013%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2419237001&rft_id=info:pmid/&rfr_iscdi=true