Abstract | ||
---|---|---|
The past decade has witnessed the use of high-level features in saliency prediction for both videos and images. Unfortunately, the existing saliency prediction methods only handle high-level static features, such as face. In fact, high-level dynamic features (also called actions), such as speaking or head turning, are also extremely attractive to visual attention in videos. Thus, in this paper, we... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/TIP.2018.2837106 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
Videos,Face,Visualization,Feature extraction,Databases,Turning | Computer vision,Fixation (psychology),Pattern recognition,Salience (neuroscience),Visualization,Head turning,Feature extraction,Coding (social sciences),Artificial intelligence,Videoconferencing,Hidden Markov model,Mathematics | Journal |
Volume | Issue | ISSN |
27 | 9 | 1057-7149 |
Citations | PageRank | References |
0 | 0.34 | 25 |
Authors | ||
4 |