Vijayasri Iyer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vijayasri Iyer has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- A. M. Hima Vyshnavi
Computational Chemistry Group (CCG), Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore 641112, India
1 shared publication - Bhargava Ganti
AMMAS Research Lab Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore 641112, Tamil Nadu, India
1 shared publication - Maahin Rathinagiriswaran1 shared publication
- P. K. Krishnan Namboori
Amrita Vishwa Vidyapeetham University
1 shared publication - S. Jyothikamalesh
Sri Eshwar College of Engineering
1 shared publication - Sriram Iyer
Dorian Technology Solutions, Mumbai 400034, Maharashtra, India
1 shared publication
Latest Publications
- Open Access
RoadscapesQA: A Multitask, Multimodal Dataset for Visual Question Answering on Indian Roads
Understanding road scenes is essential for autonomous driving, as it enables systems to interpret visual surroundings to aid in effective decision-making. We present Roadscapes, a multitask multimodal dataset consisting of upto 9,000 images captured in diverse Indian driving environments, accompanied by manually verified bounding boxes. To facilitate scalable scene understanding, we employ rule-based heuristics to infer various scene attributes, which are subsequently used to generate question-answer (QA) pairs for tasks such as object grounding, reasoning, and scene understanding. The dataset includes a variety of scenes from urban and rural India, encompassing highways, service roads, village paths, and congested city streets, captured in both daytime and nighttime settings. Roadscapes has been curated to advance research on visual scene understanding in unstructured environments. In this paper, we describe the data collection and annotation process, present key dataset statistics, and provide initial baselines for image QA tasks using vision-language models.
Open AccessRoadscapesQA: A Multitask, Multimodal Dataset for Visual Question Answering on Indian Roads
Understanding road scenes is essential for autonomous driving, as it enables systems to interpret visual surroundings to aid in effective decision-making. We present Roadscapes, a multitask multimodal dataset consisting of upto 9,000 images captured in diverse Indian driving environments, accompanied by manually verified bounding boxes. To facilitate scalable scene understanding, we employ rule-based heuristics to infer various scene attributes, which are subsequently used to generate question-answer (QA) pairs for tasks such as object grounding, reasoning, and scene understanding. The dataset includes a variety of scenes from urban and rural India, encompassing highways, service roads, village paths, and congested city streets, captured in both daytime and nighttime settings. Roadscapes has been curated to advance research on visual scene understanding in unstructured environments. In this paper, we describe the data collection and annotation process, present key dataset statistics, and provide initial baselines for image QA tasks using vision-language models.
- 17 February 2020
- Published by Taru Publications in Journal of Interdisciplinary Mathematics
- Vol. 23 (2) , 347-355
Hybrid quantum computing based early detection of skin cancer
As image processing techniques constantly grow in complexity & volume, meeting the required demand for data storage and computational power is a challenge. Using hybrid quantum-mechanical systems to encode and process image information could help overcome such challenges. We propose to implement a hybrid quantum mechanical system with 2 qubits operation for the purpose of classifying between cancerous and non-cancerous pigmented skin-lesions in the HAM10000 dataset. In view of the ever-increasing number of skin cancer deaths, such a system could have potential for the early diagnosis of the disease. Until fully scalable quantum hardware becomes available, the hybrid model could be a viable alternative to overcome the limitations of classical computing systems.
- 17 February 2020
- Published by Taru Publications in Journal of Interdisciplinary Mathematics
- Vol. 23 (2) , 347-355
Hybrid quantum computing based early detection of skin cancer
As image processing techniques constantly grow in complexity & volume, meeting the required demand for data storage and computational power is a challenge. Using hybrid quantum-mechanical systems to encode and process image information could help overcome such challenges. We propose to implement a hybrid quantum mechanical system with 2 qubits operation for the purpose of classifying between cancerous and non-cancerous pigmented skin-lesions in the HAM10000 dataset. In view of the ever-increasing number of skin cancer deaths, such a system could have potential for the early diagnosis of the disease. Until fully scalable quantum hardware becomes available, the hybrid model could be a viable alternative to overcome the limitations of classical computing systems.