Dr. Ananya Pandey

About

I am Dr. Ananya Pandey, an Assistant Professor in the Department of Computer Science and Engineering at Thapar University (Deemed-to-be-University). My academic journey has been driven by a deep passion for advancing the field of Computer Vision. I hold a PhD in Information and Technology from Delhi Technological University, New Delhi, an M.Tech in Computer Engineering from Jamia Millia Islamia University, and a B.Tech in Computer Science and Engineering from Jamia Hamdard University, New Delhi.

Over the years, I have focused my research on deep learning, pattern recognition, AI-driven visual perception, and adversarial robustness in multimodal learning. My goal is to find innovative solutions that bridge the gap between academia and industry, applying AI-driven advancements to address real-world challenges. As a Research Scholar and Teaching Assistant in the past, I’ve developed a strong foundation in both the theoretical and practical aspects of Artificial Intelligence and Computer Vision.

Beyond my research, I am passionate about teaching and mentoring students. I believe in creating a learning environment that encourages curiosity, exploration, and innovation. Guiding students in their research and seeing them grow into independent thinkers is one of the most rewarding parts of my academic journey.

Employment

• Thapar Institute of Engineering and Technology Assistant professor -I
  2024 - Present
• Thapar Institute of Engineering and Technology Assistant Professor-I
  2024 - Present
• Thapar Institute of Engineering and Technology Assistant Professor
  2024 - Present
• Delhi Technological University

Education

• Delhi Technological University PhD
  2021 - 2024

Projects & Funding

Projects & funding information is unavailable.

Publications (11)

• Progress, achievements, and challenges in multimodal sentiment analysis using deep learning: A survey
  Applied Soft Computing 2024 DOI: 10.1016/j.asoc.2023.111206
  +Save
• Contrastive Learning-based Multi-Modal Architecture for Emoticon Prediction by Employing Image-Text Pairs
  arXiv 2024 DOI: 10.48550/arXiv.2408.02571
  +Save
• Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection
  arXiv 2024 DOI: 10.48550/arXiv.2408.02595
  +Save
• Multimodal Architecture for Sentiment Recognition via employing Multiple Modalities
  Proceedings - 2nd International Conference on Advancement in Computation and Computer Technologies, InCACCT 2024 2024 DOI: 10.1109/InCACCT61598.2024.10551131
  +Save
• Target-Dependent Multimodal Sentiment Analysis Via Employing Visual-to-Emotional-Caption Translation Network using Visual-Caption Pairs
  arXiv 2024 DOI: 10.48550/arXiv.2408.10248
  +Save
• VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features
  arXiv 2024 DOI: 10.48550/arXiv.2408.10246
  +Save
• Multimodal Sarcasm Recognition by Fusing Textual, Visual and Acoustic content via Multi-Headed Attention for Video Dataset
  2023 World Conference on Communication & Computing (WCONF) 2023 DOI: 10.1109/wconf58270.2023.10235179
  +Save
• Attention-free based dual-encoder mechanism for Aspect-based Multimodal Sentiment Recognition
  2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT) 2023 DOI: 10.1109/apsit58554.2023.10201711
  +Save
• Multimodal Sarcasm Detection (MSD) in Videos using Deep Learning Models
  2023 International Conference in Advances in Power, Signal, and Information Technology (APSIT) 2023 DOI: 10.1109/apsit58554.2023.10201731
  +Save
• VABDC-Net: A framework for Visual-Caption Sentiment Recognition via spatio-depth visual attention and bi-directional caption processing
  Knowledge-Based Systems 2023 DOI: 10.1016/j.knosys.2023.110515
  +Save