DAZSL: Dynamic Attributes for Zero-Shot Learning

8 Dec 2019Jonathan D. JonesTae Soo KimMichael PevenZihao XiaoJin BaiYi ZhangWeichao QiuAlan YuilleGregory D. Hager

Inspired by earlier applications to still images, zero-shot activity recognition has largely focused on image-derived representations without regard to the video's temporal aspect. Since these methods cannot capture the time evolution of an activity, reversible actions such as entering and exiting a car are often indistinguishable... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.