Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
¼øÂ÷ µ¥ÀÌÅÍ°£ÀÇ À¯»çµµ Ç¥Çö¿¡ ÀÇÇÑ µ¿¿µ»ó ºÐ·ù |
¿µ¹®Á¦¸ñ(English Title) |
Video Classification System Based on Similarity Representation Among Sequential Data |
ÀúÀÚ(Author) |
ÀÌÈ£¼®
¾çÁöÈÆ
Hosuk Lee
Jihoon Yang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 07 NO. 01 PP. 0001 ~ 0008 (2018. 01) |
Çѱ۳»¿ë (Korean Abstract) |
µ¿¿µ»ó µ¥ÀÌÅÍ´Â ½Ã°£¿¡ µû¸¥ Á¤º¸´Â ¹°·ÐÀÌ°í, ¸¹Àº Á¤º¸·®°ú ÇÔ²² ÀâÀ½µµ Æ÷ÇÔÇÏ°í Àֱ⠶§¹®¿¡ ÀÌ¿¡ ´ëÇÑ °£´ÜÇÑ Ç¥ÇöÀ» ÇнÀÇÏ´Â °ÍÀº ½±Áö ¾Ê´Ù. º» ¿¬±¸¿¡¼´Â ÀÌ¿Í °°Àº µ¿¿µ»ó µ¥ÀÌÅ͸¦ Ãß»óÀûÀÌ¸é¼ º¸´Ù °£´ÜÇÏ°Ô Ç¥ÇöÇÒ ¼ö ÀÖ´Â ¼øÂ÷ µ¥ÀÌÅÍ°£ÀÇ À¯»çµµ Ç¥Çö ¹æ¹ý°ú µö·¯´× ÇнÀ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ÀÌ´Â µ¿¿µ»óÀ» ±¸¼ºÇÏ´Â À̹ÌÁö µ¥ÀÌÅÍ º¤ÅÍµé »çÀÌÀÇ À¯»çµµ¸¦ ³»ÀûÀ¸·Î Ç¥ÇöÇÒ ¶§ ±×°ÍµéÀÌ ¼·Î ÃÖ´ëÇÑÀÇ Á¤º¸¸¦ °¡Áú ¼ö ÀÖµµ·Ï ÇÏ´Â ÇÔ¼ö¸¦ ±¸ÇÏ°í ÇнÀÇÏ´Â °ÍÀÌ´Ù. ½ÇÁ¦ µ¥ÀÌÅ͸¦ ÅëÇÏ¿© Á¦¾ÈµÈ ¹æ¹ýÀÌ ±âÁ¸ÀÇ µ¿¿µ»ó ºÐ·ù ¹æ¹ýµéº¸´Ùµµ ¶Ù¾î³ ºÐ·ù ¼º´ÉÀ» º¸ÀÓÀ» È®ÀÎÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
It is not easy to learn simple expressions of moving picture data since it contains noise and a lot of information in addition to time-based information. In this study, we propose a similarity representation method and a deep learning method between sequential data which can express such video data abstractly and simpler. This is to learn and obtain a function that allow them to have maximum information when interpreting the degree of similarity between image data vectors constituting a moving picture. Through the actual data, it is confirmed that the proposed method shows better classification performance than the existing moving image classification methods.
|
Å°¿öµå(Keyword) |
µö ·¯´×
ºñµð¿À ºÐ·ù
À¯»çµµ ÃøÁ¤
Ç¥Çö ÇнÀ
Deep Learning
Video Classification
Similarity Measure
Representation Learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|