Shena Hoffmann
Chris Kam
Reference Information
Title - A multimodal labeling interface for wearable computing
Authors Shanqing Li, Yunde Jia
IUI 2010
Summary
This system is based around multi-model labeling. The paper talks about the system in which objects could be labeling using some sort of wearable device through a multi-model interface, which actually replaces the keyboard and mice. Speech recognition as well as visual tracking are both real-time. The visual system lets the user circle objects and then speaks to give the system it's name. The user wears a computer, Bluetooth microphone as well as a display that is mounted on the head.
Discussion
I really like the idea of this concept. I could see that this would be very applicable in the near future. Right now the hardware seems to be a big large but I'm sure they could be fixed with advancements of technology. It seems almost like a sci fi device in my eyes that would be seen in video games. I could see this being used by the military for eye level views of battle fields.
From what I got from reading your summary, I believe I saw a video some time ago about new language translator technology. The purpose was to point at an object and the translator would display the item's "label" and it would also display it in your language of preference. I am not sure if this is what you are talking about, but the idea of the paper sounds very interesting.
ReplyDeleteI also think that this could have some interesting applications, especially if the hardware were smaller. Right now, though, the application of just labeling objects seemed to be a little unhelpful to me.
ReplyDeleteThe applications of this work are intriguing.
ReplyDeleteSeems too bulky to be useful right now, but definitely will be something useful in the future!
ReplyDeleteI agree with Zach, but altogether I think it sounds promising. I have always considered speech recognition to be a large part of the future of HCI.
ReplyDelete