Mahta Rafiee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mahta Rafiee has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Hamed Zamani
Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA
3 shared publications - Alireza Salemi
Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA
1 shared publication - Faegheh Hasibi
Radboud University, Nijmegen, Netherlands
1 shared publication - Heydar Soudani
Radboud University, Nijmegen, Netherlands
1 shared publication - Julian Killingback
University of Massachusetts Amherst, Amherst, MA, USA
1 shared publication - Madine Manas
Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 790-800
Scaling Laws for Embedding Dimension in Information Retrieval
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 790-800
Open AccessScaling Laws for Embedding Dimension in Information Retrieval
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3365-3373
Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 3365-3373
Open AccessTotal Recall QA: A Verifiable Evaluation Suite for Deep Research Agents
- Open Access
- 9 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 169-176
Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering
This paper studies a category of visual question answering tasks, in which accessing external knowledge is necessary for answering the questions. This category is called outside-knowledge visual question answering (OK-VQA). A major step in developing OK-VQA systems is to retrieve relevant documents for the given multi-modal query. Current state-of-the-art asymmetric dense retrieval model for this task uses an architecture with a multi-modal query encoder and a uni-modal document encoder. Such an architecture requires a large amount of training data for effective performance. We propose an automatic data generation pipeline for pre-training passage retrieval models for OK-VQA tasks. The proposed approach leads to 26.9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture. Additionally, the proposed pre-training approach exhibits a good ability in zero-shot retrieval scenarios.
- 9 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 169-176
Open AccessPre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering
This paper studies a category of visual question answering tasks, in which accessing external knowledge is necessary for answering the questions. This category is called outside-knowledge visual question answering (OK-VQA). A major step in developing OK-VQA systems is to retrieve relevant documents for the given multi-modal query. Current state-of-the-art asymmetric dense retrieval model for this task uses an architecture with a multi-modal query encoder and a uni-modal document encoder. Such an architecture requires a large amount of training data for effective performance. We propose an automatic data generation pipeline for pre-training passage retrieval models for OK-VQA tasks. The proposed approach leads to 26.9% Precision@5 improvements compared to the current state-of-the-art asymmetric architecture. Additionally, the proposed pre-training approach exhibits a good ability in zero-shot retrieval scenarios.