What Am I Gonna Wear Today?
media laboratory, mit
It happens before dinners, meetings, movies, visits, or even
only a walk. We all ask ourselves the same questions almost
everyday, and for all the activities we participate - "What
am I gonna wear?" . It tends to be tricky or even bothersome
for many of us to make the decisions, because what we wear
reflects many clues that are important to our social interactions,
such as manners, tastes, and how people we meet mean to us.
Viewing this process computationally, we claim that deciding
what to put on is in fact striding across the gap and searching
for the match between two concepts: a) how the clothes express
our characters, and b) how the events or people we are to
meet mean to us. In this project, we attempt to apply commonsense
computing techniques to achieve this concept-matching goal,
and provide users helpful suggestions.
The scenario of using this system goes
as follows. After providing a set of descriptions about the
owned clothes and accessories, the user only needs to type
in any sentences he/she wishes (e.g., "I am going to
a dinner with my girlfriend's parents." or "I feel
relaxing today."), and the system will find the most
suitable choices accordingly. The fuller the wearables as
well as the input sentences are described by the user, the
more accurate the system can catches his/her needs, and the
more helpful the suggestions will be.
::You Gotta Have Commonsense...
We use a Commonsense reasoning
system to map between the goals stated by the user, and possible
characteristics of the product that might be relevant. For
example, the boss's birthday party suggests a higher value
for the "formal vs. casual" attribute, than say,
a child's birthday party. The five dimensions built particularly
for describing the styles or functions of clothes/accessories
are: luxurious<->simple, formal<->casual, sexy<->conservative,
modern<->classic, and elegant<->vulgar. We weighed
several common brands (e.g., sisley, nike) and wearables (e.g.,
jacket, glasses) in these dimensions, and also a word list
that contains tens of words about events, places, and social
relationships.Using the spreading activation technique, the
concepts carried by the words in the word list are spread
to all the other terms in ConceptNet, a semantic network that
is developed based on an 800,000-sentence Common Sense knowledge
base (OMCS), such that the system is capable of providing
suggestions under general cases.
::A Different Recommender
Putting this idea in a broader perspective, online shoppers
in all kinds of product areas are potentially benefited.
Although Electronic Commerce
on the Web is thriving, they still have trouble finding products
that will meet their needs and desires. AI has offered many
kinds of Recommender Systems, but they are all oriented toward
searching based on concrete attributes of the product (e.g.
price, color) or the user (as in Collaborative Filtering).
Our fashion recommendation system serves as a different recommender
technique, namely, Scenario-Oriented Recommendation,
which works even when users don’t necessarily know exactly
what product characteristics they are looking for. It breaks
down boundaries between products' categories, finds the "first
example" for existing techniques like Collaborative Filtering,
and helps promote independent brands.
What am I gonna wear today?
Edward Shen, Henry Lieberman, and Francis Lam (2007).
What am I gonna wear?: Scenatio-Oriented Recommendation. In
the proceedings of the International Conference on Intelligent
User Interface, IUI 2007, Jan 28-31, 2007, Honolulu, Hawaii,
"Program Assists the Fashion-Challenged." In
Discovery News Channel (.html)
edward or francis or lieber at media dot mit dot edu