[Adapt] [Adapt Seminar] Localizaiton from Embodied Dialog

[GUO Shijia]

Hi Adapters,


A number of ‘Embodied AI’ tasks combining language, visual perception, and navigation in realistic 3D environments have recently gained prominence, including Interactive and Embodied Question Answering, Vision-and-Language Navigation or VLN, and challenges based on household tasks. Tomorrow I will present a paper I found interesting concerning the Localization from Embodied dialog.


Imagine the following scenario: you get lost in a new building while trying to visit a friend who lives or works there. Unsure of exactly where you are, you call your friend and start describing your surroundings ("‘I’m standing on a red carpet looking at a seating area.") and your friend asks you ("Is there a round table in the middle of the room?")... After a few rounds of dialog, your friend who is familiar with the building will hopefully know your location. The paper Where Are You? Localizaiton from Embodied Dialog (paper here) focuses on the scenario described above.


Hope you'll enjoy the talk.


Best regards,
Sylvie


























--


郭诗佳（Guo Shijia）

上海交大巴黎高科卓越工程师学院
Shanghai Jiao Tong University
SJTU - ParisTech Elite Institute of Technology
Ecole d'Ingénieur SJTU-ParisTech
上海市闵行区东川路800号， 200240
800 Dongchuan Rd., Shanghai，200240  ,  P.R.China
Mobile：+86 13122211736
Email：47844555 at 163.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20201223/176f222c/attachment.html>