Shankar Gangisetty

About

My current specific area of research interest include Vision based Mobility/Autonomous Driving and Multimodal Learning. Broader and earlier area of research works are 3D Vision, Point Cloud Processing, Machine/Deep Learning, Natural Language Processing and Data Science.

Employment

• International Institute of Information Technology, Hyderabad Applied Research Scientist
  2023 - Present
• International Institute of Information Technology, Hyderabad Postdoc
  2022 - 2023
• KLE Technological University Professor and Researcher
  2017 - 2022

Education

• B. V. B. College of Engineering and Technology Ph.D.
  2012 - 2019
• National Institute of Technology Karnataka M.Tech.
  2004 - 2006

Projects & Funding

Projects & funding information is unavailable.

Publications (42)

• Early Anticipation of Driving Maneuvers
  2025 DOI: 10.1007/978-3-031-72897-6_9
  +Save
• ICPR 2024 Competition on Rider Intention Prediction
  2025 DOI: 10.1007/978-3-031-80139-6_3
  +Save
• Enhancing Driving Visibility via Semantic-Guided Knowledge Distillation Framework for Adverse Weather Removal
  2025 DOI: 10.1145/3774521.3774599
  +Save
• American Sign Language Fingerspelling Recognition using Attention Model
  2023 IEEE 8th International Conference for Convergence in Technology, I2CT 2023 2023 DOI: 10.1109/I2CT57861.2023.10126277
  +Save
• Character and Word Level Gesture Recognition of Indian Sign Language
  2023 IEEE 8th International Conference for Convergence in Technology, I2CT 2023 2023 DOI: 10.1109/I2CT57861.2023.10126314
  +Save
• Making the V in Text-VQA Matter
  IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2023 DOI: 10.1109/CVPRW59228.2023.00590
  +Save
• Making the V in Text-VQA Matter
  arXiv 2023 DOI: 10.48550/arXiv.2308.00295
  +Save
• Weakly Supervised Visual Question Answer Generation
  IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops 2023 DOI: 10.1109/CVPRW59228.2023.00591
  +Save
• Weakly Supervised Visual Question Answer Generation
  arXiv 2023 DOI: 10.48550/arXiv.2306.06622
  +Save
• FloodNet: Underwater image restoration based on residual dense learning
  Signal Processing: Image Communication 2022 DOI: 10.1016/j.image.2022.116647
  +Save