Enabling Multimodal Understanding: Lidar Data Meets VQA

DOI

10.2991/978-94-6463-784-7_11How to use a DOI?

Keywords

LiDAR; Visual Question Answering (VQA); VQA Applications; Multimodality; Computer Vision; Natural Language Processing

Abstract

This chapter explores the integration of Light Detection and Ranging (LiDAR) data with multimodal systems such as Visual Question Answering (VQA) to enable robust contextual understanding. The chapter begins with an overview of VQA, including its architecture, various modeling approaches, and practical applications. The chapter then introduces LiDAR data, particularly point clouds, and highlights how this 3D information enhances traditional visual input in machine learning tasks. Special attention is given to recent efforts in combining point cloud data with VQA, examining relevant datasets, deep learning models, and fusion techniques. The chapter concludes by outlining current limitations and future directions for advancing LiDAR-based multimodal understanding in VQA.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Muhammad Zeeshan Khan
AU  - Anuroop Gaddam
AU  - Dhananjay Thiruvady
AU  - N. K. Suryadevara
PY  - 2025
DA  - 2025/07/28
TI  - Enabling Multimodal Understanding: Lidar Data Meets VQA
BT  - Proceedings of the IoT AND LiDAR Technologies in Healthcare Workshop (ILTH 2024)
PB  - Atlantis Press
SP  - 110
EP  - 127
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-784-7_11
DO  - 10.2991/978-94-6463-784-7_11
ID  - Khan2025
ER  -