Search

One major technique debt in video object segmentation is to label the object masks for training instances. As a result, we propose to prepare inexpensive, yet high quality pseudo ground truth corrected with motion cue for video object segmentation training. Our method conducts semantic segmentation using instance segmentation networks and, then, selects the segmented object of interest as the pseudo ground truth based on the motion information. Afterwards, the pseudo ground truth is exploited to finetune the pretrained objectness network to facilitate object segmentation in the remaining frames of the video. We show that the pseudo ground truth could effectively improve the segmentation performance. This straightforward unsupervised video object segmentation method is more efficient than existing methods. Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets. And the category-agnostic pseudo ground truth has great potential to extend to multiple arbitrary object tracking.

Reducing the negative effects of extended computer use is becoming increasingly important and it has been demonstrated that appropriate stretching yields benefits. We investigated the opportunities of motivating heavy computer users to stretch by incorporating mobile and sensing technologies into a 1-on-1 social competition game. We implemented the "Social Persuasion System for Stretching" SP-Stretch and conducted a 4-week study with 25 heavy computer users. Based on the quantitative and qualitative results, we identify a number of design considerations, and provide suggestions for future research.