MemX captures human visual attention on the fly, analyzes the salient visual content, and records moments of personal interest in the form of compact video snippets . Attention tracking focuses computation-intensive video analysis on salient regions, while video analysis makes human attentiondetection and tracking more accurate . MemX significantly improves theattention tracking accuracy over the eye-tracking-alone method, while maintaining high system energy efficiency . We have conducted 11 in-fieldpilot studies across a range of daily usage scenarios, which demonstrate the feasibility and potential benefits of MemX . We propose a new temporal visualattention network that unifies visual attention tracking and salientvisual content analysis. We have also conducted 11 pilot studies across the field .

Author(s) : Yuhu Chang, Yingying Zhao, Mingzhi Dong, Yujiang Wang, Yutian Lu, Qin Lv, Robert P. Dick, Tun Lu, Ning Gu, Li Shang

Links : PDF - Abstract

Code :
Coursera

Keywords : tracking - attention - memx - video - analysis -

Leave a Reply

Your email address will not be published. Required fields are marked *