報告內容：View Angles may Reveal Your Mood: A psychological explanation and an example in the real world（照片視角可能揭示你的心情：認知心理學的解釋和現實生活的例子）
報告人：梁雪峰 教授
報告時間：10月23日 9:00
報告地點：現代交通工程中心7950會議室
報告人簡介:
Bio.Xuefeng Liang, who was selected for Shannxi Province thousand talents program in 2018, is a Huashang distinguished professor with the School of Artificial Intelligence, Xidian University. His research focuses on visual perception & cognition, computer vision and intelligent algorithms. He has published more than 70 research papers. He received his Ph.D. from Japan Advanced Institute of Science and Technology in 2006. During the three-year program, he explored computational geometry algorithms on a variety of vision problems. Afterward, he moved to National Institute of Advanced Industrial Science and Technology at Tsukuba, and worked on robotics vision. From 2008, he simultaneously worked at University College London & Queen Mary University of London for the research of visual perception on motion. From 2010, he was assigned as Associate Professor at Graduate School of Informatics, Kyoto University. In 2018, he joined Xidian University. He serves as the leading guest editor of Signal Processing Image Communication (Elsevier) and Sensors (MDPI), and on the Editorial Board of two international journals. He has chaired and co-chaired seven international conferences, including ICIT (2017, 2018, 2019), DSIT (2019),IReDLiA (2018), ICVIP (2017), and UCC (2017).
報告內容簡介:
Psychologists proposed an influential broaden-and-build theory which asserts that positive emotions broaden the scope of (visual) attention. However, this theory is only based on the laboratorial experiments, rarely confirmed or disproved with big datasets, e.g. more than thousands samples. Our study revealed a strong correlation between the preference of wide-view photos and the high rating of tourist sites. This preference was ascribed to the positive emotions broadening visual attention and triggering wide-view photo compositions. In terms of machine learning algorithms, a two-stage HVS model and a CNN only model and an end-to-end deep network have been proposed for data analysis. The experimental results showed that the deep learning algorithm outperforms the task and indicates an interesting hint. Meanwhile, we propose a machine learning method, which mimics the “Optimally interactive information” theory, to tackle the ambiguous problem, such as classifying the view type.
