Two members of our research team (Lei Wang, Machine Learning / Computer Vision Researcher and Moussa Reda Mansour, iCetana alumnus), have recently had a paper accepted at a major computer vision conference. Lei is attending the conference.
The 26th IEEE International Conference on Image Processing (ICIP) will be held in Taipei International Convention Center, Taipei, Taiwan, on September 22-25. ICIP is the world’s largest and most comprehensive technical conference focused on image and video processing and computer vision.
This paper (ICIP2019 poster: https://sigport.org/documents/loss-switching-fusion-similarity-search-video-classification, ICIP2019 conference proceeding https://ieeexplore.ieee.org/document/8803051) proposes a new approach to extracting the most useful information from video. It classifies videos using a lightweight Loss Switching Fusion Network (LSFNet). This system achieves fast training and state of the art benchmarking results. This shows that the approach can classify different background motions and separately identify human motions from these background motions.
The proposed solution has a variety of potential applications such as content-based video clustering and video filtering. Congratulations to all contributors to this paper. This highlights the quality of iCetana’s research work and the ability of our team.