Abstract | ||
---|---|---|
We present a model for gaze prediction in egocentric video by leveraging the implicit cues that exist in camera wearer's behaviors. Specifically, we compute the camera wearer's head motion and hand location from the video and combine them to estimate where the eyes look. We further model the dynamic behavior of the gaze, in particular fixations, as latent variables to improve the gaze prediction. Our gaze prediction results outperform the state-of-the-art algorithms by a large margin on publicly available egocentric vision datasets. In addition, we demonstrate that we get a significant performance boost in recognizing daily actions and segmenting foreground objects by plugging in our gaze predictions into state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICCV.2013.399 | ICCV |
Keywords | Field | DocType |
hand location,camera wearer,predict gaze,egocentric video,dynamic behavior,prediction result,state-of-the-art algorithm,foreground object,available egocentric vision datasets,daily action,state-of-the-art method,image segmentation,gesture recognition | Computer vision,Fixation (psychology),Gaze,Computer science,Action recognition,Gesture recognition,Image segmentation,Latent variable,Artificial intelligence | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1550-5499 |
Citations | PageRank | References |
73 | 1.82 | 16 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yin Li | 1 | 797 | 35.85 |
Alireza Fathi | 2 | 930 | 40.79 |
James M. Rehg | 3 | 5259 | 474.66 |