Alakh Aggarwal
Scholar

Alakh Aggarwal

Google Scholar ID: X9XBBCcAAAAJ
University of Texas at Dallas
Deep LearningMachine LearningComputer Vision3D Vision
Citations & Impact
All-time
Citations
138
 
H-index
3
 
i10-index
3
 
Publications
6
 
Co-authors
4
list available
Resume (English only)
Academic Achievements
  • Successfully defended thesis titled 'Learning Complex Occlusion-Aware 3D Representations from Human-Object Interactions' in 2025; Submitted research paper 'GS-HOI' to 3DV 2026 in 2025; Received 'Best Paper Award' for 'TexHOI' in CVM 2025; Passed the Ph.D. proposal in 2025; Received Betty and Gifford Johnson Travel Awards in 2025; 'TexHOI' recommended to IEEE TVCG in 2025; Conditionally accepted research paper on inverse rendering of dynamic hand-object interaction in CVM 2025; 'Layered-Garment Net' accepted in ACCV 2022; Published research paper on Face De-identification in 2020; Published research paper on Broad Learning System in 2019.
Research Experience
  • Collaborated with multiple professors during undergraduate studies, including Dr. Pratik Chattopadhyay, Dr. Shankar M. Venkatesan, and Dr. Ravi S. Hegde. Research areas included Broad Learning Systems, De-identification, Neural Networks, Computer Vision, Lip-Reading System, and Object Detection Feature Transfer.
Education
  • Graduated from Indian Institute of Technology (BHU) Varanasi with a B.Tech. in Computer Science and Engineering in 2019; Pursuing a Ph.D. in Computer Science at The University of Texas at Dallas since 2019, under the guidance of Dr. Xiaohu Guo.
Background
  • Research Interests: 3D Vision and its applications; Field: Computer Science; Summary: Currently pursuing a Ph.D. in Computer Science at The University of Texas at Dallas, focusing on Implicit 3D Graphics and Scene Reconstruction.
Miscellany
  • Vision is to leverage expertise to advance vision technologies and contribute meaningfully to the world. Name Alakh, derived from Sanskrit, means that which cannot be perceived by the naked eye, symbolizing the aspiration to uncover visual information beyond what meets the eye.