@inproceedings{wang-etal-2021-ocid,
title = "{OCID}-Ref: A 3{D} Robotic Dataset With Embodied Language For Clutter Scene Grounding",
author = "Wang, Ke-Jyun and
Liu, Yun-Hsuan and
Su, Hung-Ting and
Wang, Jen-Wei and
Wang, Yu-Siang and
Hsu, Winston and
Chen, Wen-Chin",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.419",
doi = "10.18653/v1/2021.naacl-main.419",
pages = "5333--5338",
abstract = "To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded objects. However, current VG works are limited in working environments, such as offices and warehouses, where objects are usually occluded due to space utilization issues. In our work, we propose a novel OCID-Ref dataset featuring a referring expression segmentation task with referring expressions of occluded objects. OCID-Ref consists of 305,694 referring expressions from 2,300 scenes with providing RGB image and point cloud inputs. To resolve challenging occlusion issues, we argue that it{'}s crucial to take advantage of both 2D and 3D signals to resolve challenging occlusion issues. Our experimental results demonstrate the effectiveness of aggregating 2D and 3D signals but referring to occluded objects still remains challenging for the modern visual grounding systems. OCID-Ref is publicly available at \url{https://github.com/lluma/OCID-Ref}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-ocid">
<titleInfo>
<title>OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ke-Jyun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Hsuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hung-Ting</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jen-Wei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Siang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Winston</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Chin</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded objects. However, current VG works are limited in working environments, such as offices and warehouses, where objects are usually occluded due to space utilization issues. In our work, we propose a novel OCID-Ref dataset featuring a referring expression segmentation task with referring expressions of occluded objects. OCID-Ref consists of 305,694 referring expressions from 2,300 scenes with providing RGB image and point cloud inputs. To resolve challenging occlusion issues, we argue that it’s crucial to take advantage of both 2D and 3D signals to resolve challenging occlusion issues. Our experimental results demonstrate the effectiveness of aggregating 2D and 3D signals but referring to occluded objects still remains challenging for the modern visual grounding systems. OCID-Ref is publicly available at https://github.com/lluma/OCID-Ref</abstract>
<identifier type="citekey">wang-etal-2021-ocid</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.419</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.419</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>5333</start>
<end>5338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding
%A Wang, Ke-Jyun
%A Liu, Yun-Hsuan
%A Su, Hung-Ting
%A Wang, Jen-Wei
%A Wang, Yu-Siang
%A Hsu, Winston
%A Chen, Wen-Chin
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F wang-etal-2021-ocid
%X To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded objects. However, current VG works are limited in working environments, such as offices and warehouses, where objects are usually occluded due to space utilization issues. In our work, we propose a novel OCID-Ref dataset featuring a referring expression segmentation task with referring expressions of occluded objects. OCID-Ref consists of 305,694 referring expressions from 2,300 scenes with providing RGB image and point cloud inputs. To resolve challenging occlusion issues, we argue that it’s crucial to take advantage of both 2D and 3D signals to resolve challenging occlusion issues. Our experimental results demonstrate the effectiveness of aggregating 2D and 3D signals but referring to occluded objects still remains challenging for the modern visual grounding systems. OCID-Ref is publicly available at https://github.com/lluma/OCID-Ref
%R 10.18653/v1/2021.naacl-main.419
%U https://aclanthology.org/2021.naacl-main.419
%U https://doi.org/10.18653/v1/2021.naacl-main.419
%P 5333-5338
Markdown (Informal)
[OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding](https://aclanthology.org/2021.naacl-main.419) (Wang et al., NAACL 2021)
ACL
- Ke-Jyun Wang, Yun-Hsuan Liu, Hung-Ting Su, Jen-Wei Wang, Yu-Siang Wang, Winston Hsu, and Wen-Chin Chen. 2021. OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5333–5338, Online. Association for Computational Linguistics.