講演抄録/キーワード |
講演名 |
2008-06-20 17:00
A Stochastic Model of Selective Visual Attention with a Dynamic Bayesian Network Derek Pang(NTT/Simon Fraser Univ.)・○Akisato Kimura・Tatsuto Takeuchi・Junji Yamato・Kunio Kashino(NTT) DE2008-25 PRMU2008-43 |
抄録 |
(和) |
Recent studies in signal detection theory suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. To predict the likelihood of where humans typically focus on a video scene, we propose a new stochastic model of visual attention by introducing a dynamic Bayesian network. When describing the network of visual attention, the principle of the signal detection theory is introduced, namely, the position where a saliency response takes the maximim is the eye focusing position. Experimental results have demonstrated that our model performs significantly better in predicting human visual attention compared to the previous deterministic model. |
(英) |
Recent studies in signal detection theory suggest that the human responses to the stimuli on a visual display are non-deterministic. People may attend to different locations on the same visual input at the same time. To predict the likelihood of where humans typically focus on a video scene, we propose a new stochastic model of visual attention by introducing a dynamic Bayesian network. When describing the network of visual attention, the principle of the signal detection theory is introduced, namely, the position where a saliency response takes the maximim is the eye focusing position. Experimental results have demonstrated that our model performs significantly better in predicting human visual attention compared to the previous deterministic model. |
キーワード |
(和) |
視覚的注意 / 映像顕著度 / 動的ベイジアンネットワーク / 状態空間モデル / 隠れマルコフモデル / / / |
(英) |
visual attention / saliency / dynamic Bayesian network / state space model / hidden Markov model / / / |
文献情報 |
信学技報, vol. 108, no. 94, PRMU2008-43, pp. 139-144, 2008年6月. |
資料番号 |
PRMU2008-43 |
発行日 |
2008-06-12 (DE, PRMU) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
DE2008-25 PRMU2008-43 |
|