selected publications

• blog posting

  • Lightweight Multi-Branch Network for Person Re-Identification.  arXiv (Cornell University). 2021
  • You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization.  arXiv (Cornell University). 2019
  • Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks 2019

• conference paper

  • How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild.  2021 IEEE/CVF International Conference on Computer Vision (ICCV). 2021
  • How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild..  International Conference on Computer Vision. 1193-1203. 2021