• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) GuessWhat?! ¹®Á¦¿¡ ´ëÇÑ ºÐ¼®°ú ÆÄÈÑ
¿µ¹®Á¦¸ñ(English Title) Analyzing and Solving GuessWhat?!
ÀúÀÚ(Author) ÀÌ»ó¿ì   ÇÑöȣ   ÇãÀ¯Á¤   °­¿ì¿µ   ÀüÀçÇö   À庴Ź   Sang-Woo Lee   Cheolho Han   Yujung Heo   Wooyoung Kang   Jaehyun Jun   Byoung-Tak Zhang  
¿ø¹®¼ö·Ïó(Citation) VOL 45 NO. 01 PP. 0030 ~ 0035 (2018. 01)
Çѱ۳»¿ë
(Korean Abstract)
GuessWhat?!Àº Áú¹®ÀÚ¿Í ´äº¯ÀÚ·Î ±¸¼ºµÈ µÎ Ç÷¹À̾ À̹ÌÁö¸¦ º¸°í Áú¹®ÀÚ¿¡°Ô ºñ¹Ð·Î °¨Ãß¾îÁø Á¤´ä ¹°Ã¼¿¡ ´ëÇØ ¿¹/¾Æ´Ï¿À/Àß ¸ð¸£°ÚÀ½ ¼Â Áß Çϳª·Î ¹¯°í ´äÇϸç, Á¤´ä ¹°Ã¼¸¦ Ãß·Á ³ª°¡´Â ¹®Á¦ÀÌ´Ù. GuessWhat?!Àº ÃÖ±Ù ÄÄÇ»ÅÍ ºñÀü°ú ÀΰøÁö´É ´ëÈ­ ½Ã½ºÅÛÀÇ Å×½ºÆ®º£µå·Î¼­ ÄÄÇ»ÅÍ ºñÀü°ú ÀΰøÁö´É ÇаèÀÇ ¸¹Àº °ü½ÉÀ» ¹Þ¾Ò´Ù. º» ³í¹®¿¡¼­, ¿ì¸®´Â GuessWhat?! °ÔÀÓ ÇÁ·¹ÀÓ¿öÅ©°¡ °¡Áö´Â Ư¼º¿¡ ´ëÇØ ³íÀÇÇÑ´Ù. ´õ ³ª¾Æ°¡, ¿ì¸®´Â Á¦¾ÈµÈ ƲÀ» ±â¹ÝÀ¸·Î GuessWhat?!ÀÇ °£´ÜÇÑ solutionÀ» Á¦¾ÈÇÑ´Ù. »ç¶÷ÀÌ Æò±Õ 4¢¦5°³ Á¤µµÀÇ Áú¹®À» ÅëÇÏ¿© ¸ÂÃß´Â ÀÌ ¹®Á¦¿¡ ´ëÇÏ¿©, ¿ì¸®°¡ Á¦¾ÈÇÑ ¹æ¹ýÀº 2°³ÀÇ Áú¹®¸¸À¸·Î ±âÁ¸ µö·¯´× ±â¹Ý ±â¼úÀÇ ¼º´ÉÀ» »óȸÇÏ´Â ¼º´ÉÀ» º¸À̸ç, 5°³ÀÇ Áú¹®ÀÌ Çã¿ëµÇ¸é Àΰ£ ¼öÁØÀÇ ¼º´ÉÀ» ´É°¡ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
GuessWhat?! is a game in which two machine players, composed of questioner and answerer, ask and answer yes-no-N/A questions about the object hidden for the answerer in the image, and the questioner chooses the correct object. GuessWhat?! has received much attention in the field of deep learning and artificial intelligence as a testbed for cutting-edge research on the interplay of computer vision and dialogue systems. In this study, we discuss the objective function and characteristics of the GuessWhat?! game. In addition, we propose a simple solver for GuessWhat?! using a simple rule-based algorithm. Although a human needs four or five questions on average to solve this problem, the proposed method outperforms state-of-the-art deep learning methods using only two questions, and exceeds human performance using five questions.
Å°¿öµå(Keyword) ´ëÈ­ ½Ã½ºÅÛ   À̹ÌÁö ÁúÀÇ ÀÀ´ä   GuessWhat?!   ÀΰøÁö´É °ÔÀÓ   dialogue system   visual question answering   GuessWhat?!   artificial intelligence game  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå