Is GPT-3 all you need for visual question answering in cultural heritage?

P Bongini, F Becattini, A Del Bimbo - European Conference on Computer …, 2022 - Springer
Abstract The use of Deep Learning and Computer Vision in the Cultural Heritage domain is
becoming highly relevant in the last few years with lots of applications about audio smart …

VISCOUNTH: a large-scale multilingual visual question answering dataset for cultural heritage

F Becattini, P Bongini, L Bulla, AD Bimbo… - ACM Transactions on …, 2023 - dl.acm.org
Visual question answering has recently been settled as a fundamental multi-modal
reasoning task of artificial intelligence that allows users to get information about visual …

CIDOC-CRM and machine learning: a survey and future research

Y Tzitzikas, M Mountantonakis, P Fafalios, Y Marketakis - Heritage, 2022 - mdpi.com
The CIDOC Conceptual Reference Model (CIDOC-CRM) is an ISO Standard ontology for the
cultural domain that is used for enabling semantic interoperability between museums …

Cric: A vqa dataset for compositional reasoning on vision and commonsense

D Gao, R Wang, S Shan, X Chen - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Alternatively inferring on the visual facts and commonsense is fundamental for an advanced
visual question answering (VQA) system. This ability requires models to go beyond the …

Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference

W Thorne, A Robinson, B Peng, C Lin… - arxiv preprint arxiv …, 2024 - arxiv.org
As the cultural heritage sector increasingly adopts technologies like Retrieval-Augmented
Generation (RAG) to provide more personalised search experiences and enable …

Increasing the Difficulty of Automatically Generated Questions via Reinforcement Learning with Synthetic Preference for Cost-Effective Cultural Heritage Dataset …

W Thorne, A Robinson, B Peng, C Lin… - Proceedings of the 4th …, 2024 - aclanthology.org
As the cultural heritage sector increasingly adopts technologies like Retrieval-Augmented
Generation (RAG) to provide more personalised search experiences and enable …

[PDF][PDF] CIDOC-CRM and Machine Learning: A Survey and Future Research. Heritage 2022, 5, 1612–1636

The CIDOC Conceptual Reference Model (CIDOC-CRM) is an ISO Standard ontology for the
cultural domain that is used for enabling semantic interoperability between museums …

Vision and Language tasks: Applications to real scenarios and Image Quality Assessment

P Bongini - 2023 - flore.unifi.it
The human brain has always been one of the most fascinating fields of study. The first
theories and research results about machine learning date back to around fifty years ago …

[CITÁCIA][C] Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?