今天和winston討論~~
終於確定了我們的方向了!!
為了保密原則^^*等我們弄得好像可以work時再來公佈~
不過沒辦法做到emotion的部分...殘念>"< (其實我還滿想做這個的~~""")
最後和奇芽歸納出架構~~愈來愈有趣了~也比較有可行性!!
畢竟還有一個月就要把結果弄出來~
這星期待做:
1. web interface (flash or other?)
2. video from youtube (至少10)
3. tag populate 確定以下兩者哪個可行
1) photo取出文字(記得有看到過類似的paper@_@要找一下)
2) internet上取photo+文字 (which sites can be used?)
4. 玩一下face detection~為了簡單~也許只用opencv way
--
1. 給photo-->search target
2. target content~?
架構
Subscribe to:
Post Comments (Atom)
[ Articles ]
[ Tags ]
- ammai (15)
- demographic (3)
- geospatial (3)
- mmai (7)
- note (1)
- papers (18)
- working (3)
[ About ]
Welcome :P
I am Saphina Cheng (anon),
a master student of MiRA (Multimedia indexing, Retrieval, and Analysis) group of the Communication & Multimedia Laboratory at National Taiwan University
This blog are about my reading papers.
Any opinion is appreciated.
Contact:

0 Comment(s):
Post a Comment