Characterizing Datasets for Social Visual Question Answering, and the New TinySocial Dataset

被引:0
|
作者
Chen, Zhanwen [1 ]
Li, Shiyao [1 ]
Rashedi, Roxanne [1 ]
Zi, Xiaoman [1 ]
Elrod-Erickson, Morgan [2 ]
Hollis, Bryan [2 ]
Maliakal, Angela [1 ]
Shen, Xinyu [1 ]
Zhao, Simeng [1 ]
Kunda, Maithilee [1 ]
机构
[1] Vanderbilt Univ, Dept Elect Engn & Comp Sci, Creat Writing Program, 221 Kirkland Hall, Nashville, TN 37235 USA
[2] Vanderbilt Univ, Dept English, Creat Writing Program, 221 Kirkland Hall, Nashville, TN 37235 USA
关键词
MEDIATION;
D O I
10.1109/icdl-epirob48136.2020.9278057
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Modern social intelligence includes the ability to watch videos and answer questions about social and theory-of-mind-related content, e.g., for a scene in Harry Potter, "Is the father really upset about the boys flying the car?" Social visual question answering (social VQA) is emerging as a valuable methodology for studying social reasoning in both humans (e.g., children with autism) and AI agents. However, this problem space spans enormous variations in both videos and questions. We discuss methods for creating and characterizing social VQA datasets, including 1) crowdsourcing versus in-house authoring, including sample comparisons of two new datasets that we created (TinySocial-Crowd and TinySocial-InHouse) and the previously existing Social-IQ dataset; 2) a new rubric for characterizing the difficulty and content of a given video; and 3) a new rubric for characterizing question types. We close by describing how having well-characterized social VQA datasets will enhance the explainability of AI agents and can also inform assessments and educational interventions for people.
引用
收藏
页数:6
相关论文
共 50 条
  • [41] Event-Oriented Visual Question Answering: The E-VQA Dataset and Benchmark
    Yang, Zhenguo
    Xiang, Jiale
    You, Jiuxiang
    Li, Qing
    Liu, Wenyin
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (10) : 10210 - 10223
  • [42] VQA: Visual Question Answering
    Agrawal, Aishwarya
    Lu, Jiasen
    Antol, Stanislaw
    Mitchell, Margaret
    Zitnick, C. Lawrence
    Parikh, Devi
    Batra, Dhruv
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2017, 123 (01) : 4 - 31
  • [43] Visual Question Answering A tutorial
    Teney, Damien
    Wu, Qi
    van den Hengel, Anton
    [J]. IEEE SIGNAL PROCESSING MAGAZINE, 2017, 34 (06) : 63 - 75
  • [44] Question and Answer Classification in Czech Question Answering Benchmark Dataset
    Kusnirakova, Dasa
    Medved, Marek
    Horak, Ales
    [J]. PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE (ICAART), VOL 2, 2019, : 701 - 706
  • [45] PubMedQA: A Dataset for Biomedical Research Question Answering
    Jin, Qiao
    Dhingra, Bhuwan
    Liu, Zhengping
    Cohen, William W.
    Lu, Xinghua
    [J]. 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 2567 - 2577
  • [46] Visual Question Generation as Dual Task of Visual Question Answering
    Li, Yikang
    Duan, Nan
    Zhou, Bolei
    Chu, Xiao
    Ouyang, Wanli
    Wang, Xiaogang
    Zhou, Ming
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 6116 - 6124
  • [47] ArabicaQA: A Comprehensive Dataset for Arabic Question Answering
    Abdallah, Abdelrahman
    Kasem, Mahmoud
    Abdalla, Mahmoud
    Mahmoud, Mohamed
    Elkasaby, Mohamed
    Elbendary, Yasser
    Jatowt, Adam
    [J]. PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 2049 - 2059
  • [48] VQuAD: Video Question Answering Diagnostic Dataset
    Gupta, Vivek
    Patro, Badri N.
    Parihar, Hemant
    Namboodiri, Vinay P.
    [J]. 2022 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW 2022), 2022, : 282 - 291
  • [49] PerCQA: Persian Community Question Answering Dataset
    Jamali, Naghme
    Yaghoobzadeh, Yadollah
    Faili, Heshaam
    [J]. LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 6083 - 6092
  • [50] MemoriQA: A Question-Answering Lifelog Dataset
    Tran, Quang-Linh
    Nguyen, Binh
    Jones, Gareth J. F.
    Gurrin, Cathal
    [J]. PROCEEDINGS OF THE FIRST ACM WORKSHOP ON AI-POWERED QUESTION ANSWERING SYSTEMS FOR MULTIMEDIA, AIQAM 2024, 2024, : 7 - 12