Papers
1
Total Citations
1
H-Index
1
About
Naman Goyal is a researcher at the forefront of explainable artificial intelligence (XAI) and multimodal deep learning. His work centers on developing interpretable AI frameworks that integrate convolutional neural networks and transformer architectures for complex visual tasks, particularly intent detection from images and videos. Goyal’s most-cited paper, "Multi-modal ensemble framework of convolutional neural networks and transformers for visual intent detection using explainable artificial intelligence" (2025), introduces a novel hybrid approach that combines the spatial feature extraction strengths of CNNs with the contextual understanding of transformers, all while ensuring model decisions are transparent and interpretable. This work has already garnered early citations, signaling its potential to influence both XAI and computer vision communities. By prioritizing explainability in high-stakes applications, Goyal addresses a critical gap in deploying AI systems where trust and accountability are paramount. His contributions are particularly relevant for autonomous systems, human-computer interaction, and surveillance analytics. As an emerging voice in responsible AI, Goyal’s research promises to shape how next-generation models balance performance with interpretability, making him a researcher to watch in the evolving landscape of trustworthy machine learning.
Research Focus
Key Achievements
Top Papers
- 1