VQAPT: A New visual question answering model for personality traits in social media images | |
Biswas, Kunal1; Shivakumara, Palaiahnakote2; Pal, Umapada1; Liu, Cheng-Lin3,4; Lu, Yue5 | |
刊名 | PATTERN RECOGNITION LETTERS |
2023-11-01 | |
卷号 | 175页码:66-73 |
关键词 | Personality trait images Multimodal concept Text recognition Social media images Natural language processing Visual question answering |
ISSN号 | 0167-8655 |
DOI | 10.1016/j.patrec.2023.10.016 |
通讯作者 | Shivakumara, Palaiahnakote(shiva@um.edu.my) |
英文摘要 | Visual Question Answering (VQA) for personality trait images on social media is challenging because of multiple emotions and actions with complex backgrounds in social media images. This work aims at developing a new VQA model for different personality traits (VQAPT) identification in a single image. This work considers the Big Five Factors (BFF) for personality traits namely, Openness, Conscientiousness, Extraversion, Agreeableness and Neuroticism. VQA is proposed based on the observation that multiple personality traits can be seen in a single image. We propose a model integrating text recognition and person/face recognition to derive the unique relationship between the text and the person's action in the image. Furthermore, a dynamic text-object graph for personality traits identification is constructed according to the query. For understanding a query, we explore the Contrastive Language-Image Pre-trained (CLIP) transformer encoder in this work. Since it is the first work of its kind, we have created a new dataset under this work for evaluation and the dataset is available publicly as mentioned in Section 4. The effectiveness of the proposed method is also evaluated on two benchmark datasets, namely TextVQA for VQA and PTI for personality traits identification. |
资助项目 | Ministry of Higher Education Malaysia[FRGS/1/2020/ICT02/UM/02/4] ; University Grants Commission (UGC) , India |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ELSEVIER |
WOS记录号 | WOS:001102930500001 |
资助机构 | Ministry of Higher Education Malaysia ; University Grants Commission (UGC) , India |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/55234] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Shivakumara, Palaiahnakote |
作者单位 | 1.Indian Stat Inst, Comp Vis & Pattern Recognit Unit, Kolkata, India 2.Univ Malaya, Fac Comp Sci & Informat Technol, Kuala Lumpur, Malaysia 3.Univ Chinese Acad Sci, Inst Automat, Chinese Acad Sci, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 5.East China Normal Univ, Shangahi Key Lab Multidimens Informat Proc, Shanghai, Peoples R China |
推荐引用方式 GB/T 7714 | Biswas, Kunal,Shivakumara, Palaiahnakote,Pal, Umapada,et al. VQAPT: A New visual question answering model for personality traits in social media images[J]. PATTERN RECOGNITION LETTERS,2023,175:66-73. |
APA | Biswas, Kunal,Shivakumara, Palaiahnakote,Pal, Umapada,Liu, Cheng-Lin,&Lu, Yue.(2023).VQAPT: A New visual question answering model for personality traits in social media images.PATTERN RECOGNITION LETTERS,175,66-73. |
MLA | Biswas, Kunal,et al."VQAPT: A New visual question answering model for personality traits in social media images".PATTERN RECOGNITION LETTERS 175(2023):66-73. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论