中央研究院 資訊科學研究所

活動訊息

友善列印

列印可使用瀏覽器提供的(Ctrl+P)功能

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 

  • 講者葉梅珍 教授 (國立臺灣師範大學 資訊工程學系)
    邀請人:TIGP (SNHCC)
  • 時間2022-04-25 (Mon.) 14:00 – 16:00
  • 地點僅提供視訊
線上串流

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

摘要

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.