Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document : 26 / 27
ÇѱÛÁ¦¸ñ(Korean Title) |
ÆмǻçÁøÀÇ "ÁÁ¾Æ¿ä"¸¦ ÀÌ¿ëÇÑ ÀνºÅ¸±×·¥ »ç¿ëÀÚ ÀÓº£µù°ú ÆмǻçÁø Ãßõ |
¿µ¹®Á¦¸ñ(English Title) |
Instagram User Embedding and Fashion Photo Recommendation Using "likes" of Fashion Photos |
ÀúÀÚ(Author) |
Àå´ë½Ä
°í¿µÁß
Daesik Jang
Youngjoong Ko
ÀÌÀ翵
±è¿µÈÆ
Jaeyoung Lee
Younghoon Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 48 NO. 11 PP. 1235 ~ 1240 (2021. 11) |
Çѱ۳»¿ë (Korean Abstract) |
°³°³ÀÎÀÌ ¼±È£ÇÏ´Â ÆÐ¼Ç ½ºÅ¸ÀÏÀÌ ´Ù¾çÇØÁö¸ç, °³ÀÎÈµÈ ÆмÇÃßõ ¿¬±¸¿¡ ´ëÇÑ ¼ö¿ä°¡ Áõ°¡ÇÏ°í ÀÖ´Ù. ÃÖ±Ù¿¡´Â µö·¯´× ±â¼úÀÇ ¹ßÀüÀ¸·Î µö·¯´×À» È°¿ëÇÏ¿© ÆмǻçÁøÀ¸·ÎºÎÅÍ Æ¯Â¡À» ÃßÃâÇÏ°í Ãßõ¿¡ È°¿ëÇÏ´Â ¿¬±¸°¡ ¸¹ÀÌ ÁøÇàµÇ°í ÀÖ´Ù. º» ¿¬±¸¿¡¼´Â, ÆмǻçÁøÀÇ Ãßõ¿¡ ÀÖ¾î¼ ÆÐ¼Ç ½ºÅ¸ÀÏ »Ó ¾Æ´Ï¶ó, ¼ÒºñÀÚµµ °í·ÁÇϱâ À§ÇØ ¼Ò¼È ³×Æ®¿öÅ© µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ°íÀÚ Çß´Ù. ÀνºÅ¸±×·¥°ú °°Àº ¼Ò¼È ³×Æ®¿öÅ©ÀÇ °¢ »ç¿ëÀÚ´Â ÀÚ½ÅÀÌ ¼±È£ÇÏ´Â ½ºÅ¸ÀÏÀÇ ÆмǻçÁøÀ» Æ÷½ºÆÃÇÏ°í ¡°ÁÁ¾Æ¿ä¡±·Î űëÇÏ´Â °æÇâÀÌ ÀÖ¾î, ¼Ò¼È ³×Æ®¿öÅ© µ¥ÀÌÅÍ´Â »ç¿ëÀÚ¿Í ÆмǻçÁø »çÀÌÀÇ °ü°è¸¦ ÆľÇÇϴµ¥ ÀÖ¾î¼ ¸Å¿ì Áß¿äÇÏ´Ù. º» ¿¬±¸ÆÀÀº »ç¿ëÀÚ¿Í ÆмǻçÁøÀ¸·Î ÀÌ·ç¾îÁø ¼Ò¼È ³×Æ®¿öÅ© µ¥ÀÌÅÍ ±¸Á¶·ÎºÎÅÍ »ç¿ëÀÚ¿Í ÆмǻçÁøÀ» °°Àº º¤ÅÍ°ø°£¿¡ ¸ÅÇÎÇÏ´Â ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ƯÈ÷, ÇнÀ¿¡ ÀÌ¿ëµÇÁö ¾ÊÀº »ç¿ëÀÚ¿Í ÆмÇÀ̹ÌÁöµµ Ãß°¡ÇнÀ ¾øÀÌ º¤ÅÍ°ø°£¿¡ ¸ÅÇÎÇÔÀ¸·Î½á, ÀÓÀÇÀÇ »ç¿ëÀÚ°¡ ¼±È£ÇÒ ¸¸ÇÑ ÆмǻçÁøÀ» ÃßõÇØÁÖ±â À§ÇØ Á¦¾È ¹æ¹ýÀ» ÀÌ¿ëÇÒ ¼ö ÀÖ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
As individual preference of fashion styles diversifies, demands for research recommending personalized fashion are increasing. Recently, with the development of deep learning technology, many studies have been conducted using deep learning to extract features from fashion photos and use them for recommendations. In this work, we exploit social network data to consider users and fashion styles in recommending fashion photos. Since social network users tend to post fashion photos in their preferred style and tag them with ¡°Like¡°, social network data are very important for understanding relationship between users and fashion photos. We propose a technique to map users and fashion photos into the same vector space using social network data structure which consists of users and fashion photos. Especially, it is possible to use our method to recommend fashion photos that a user might prefer by mapping users and fashion photos not used for learning into a vector space without additional learning. |
Å°¿öµå(Keyword) |
Áö½Ä ±×·¡ÇÁ ¿Ï¼º
¸µÅ© ¿¹Ãø
»çÀü ÇнÀµÈ ¾ð¾î ¸ðµ¨
multi-task learning
»óÀ§ Ŭ·¡½º
knowledge graph completion
link prediction
pre-trained language model
multi-task learning
hyper-class
¼Ò¼È ³×Æ®¿öÅ©
»ç¿ëÀÚ-ÆмǻçÁø µ¥ÀÌÅͱ¸Á¶
ÆмǻçÁø Ãßõ½Ã½ºÅÛ
ÀνºÅ¸±×·¥ "ÁÁ¾Æ¿ä" űë
social networks
users-fashion photos data structure
fashion photos recommender systems
Instagram "Like" tagging
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|