Institute of Information Science, Academia Sinica

Events

Print

Press Ctrl+P to print from browser

TIGP (SNHCC) -- Visual‐Semantic Embedding for Multi‐label Image Classification: From Fully Supervised to Zero Shot Settings 

:::

TIGP (SNHCC) -- Visual‐Semantic Embedding for Multi‐label Image Classification: From Fully Supervised to Zero Shot Settings 

  • LecturerProf. Mei‐Chen Yeh (Department of Computer Science and Information Engineering)
    Host: TIGP (SNHCC)
  • Time2022-04-25 (Mon.) 14:00 – 16:00
  • LocationVirtual only
Live Stream

Join the talk via 【webex】 or open Webex and enter Meeting number: 2517 220 6716 Password: 2022seminar

Abstract

Multi-label image classification is a crucial problem in computer vision, where the goal is to assign multiple labels to one image based on its content. Compared with single-label image classification, multi-label image classification is more general, but it is also more challenging because of the rich semantic information and complex dependency of an image and its labels. In this talk, I will introduce our TPAMI work addressing this problem, and share a ongoing work on extending this method for conventional and generalized zero-shot learning.