Data VFD Dataset (Japanese) æ¦è¦ è¨èªå¦çã®ãããä¼è°EMNLPã«ã¦çºè¡¨ããè«æâA Visually-grounded First-person Dialogue Dataset with Verbal and Non-verbal Responsesâã®ãã¼ã¿ã»ããã§ãã è«æã§ã¯æ§ã ãªç¤¾ä¼çç¶æ³ã§ç»åå ã®äººç©ã話ããããè¨èã®è¿çãã¢ãã«åãã¦ãã¾ãã æ¬ãã¼ã¿ã»ããã¯GazeFollow Dataset ï¼Recasens et al.,2015ï¼ã«åºã¥ãã¦ãããGazeFollow Datasetã«åå¨ãããï¼1ï¼ã·ã¼ã³ç»åãï¼2ï¼è©±è ã®è¦ç·æ å ±ãå¼ãç¶ãã§ãã¾ãã è«æã§ä½¿ç¨ãããã¼ã¿ã»ãããä½æãããããæ°ãã«æ¥æ¬èªã§ï¼3ï¼è©±è ã®çºè©±ããã¹ããããã³ï¼4ï¼è¿çè ã®è¨èªçããã³éè¨èªçè¿çã®ï¼ã¤ã®ã¢ããã¼ã·ã§ã³ãå¼ç¤¾ã¯ã©ã¦ãã½ã¼ã·ã³ã°ãµã¼ãã¹ãå©ç¨ã
{{#tags}}- {{label}}
{{/tags}}