Tassawar Iqbal
Papers
1
Total Citations
10
H-Index
1
About
Tassawar Iqbal is a researcher whose work centers on human action recognition through advanced deep learning and feature selection methodologies. His most-cited paper, "A Fused Heterogeneous Deep Neural Network and Robust Feature Selection Framework for Human Actions Recognition" (2021), has garnered 10 citations, reflecting its contribution to improving the accuracy and robustness of automated human activity analysis. This framework integrates heterogeneous neural network architectures with sophisticated feature selection techniques, addressing key challenges in computer vision and pattern recognition. While the paper has been retracted, it nonetheless highlights Iqbal's engagement with cutting-edge approaches in artificial intelligence. His research interests lie at the intersection of deep learning, feature engineering, and human-computer interaction, aiming to enhance the reliability of systems that interpret complex human movements. Though his citation impact is modest, his work represents a targeted effort to refine machine learning models for real-world applications, such as surveillance, healthcare monitoring, and interactive systems. For students and researchers exploring human action recognition, Iqbal's contributions offer insights into the challenges of fusing heterogeneous neural networks and the critical role of robust feature selection in achieving high-performance recognition systems.
Research Focus
Key Achievements
Top Papers
- 1