Sorry, you need to enable JavaScript to visit this website.

In this paper, we investigate the problem of action recognition in RGB-D egocentric videos. These self-generated and embodied videos provide richer semantic cues than the conventional videos captured from the third-person view for action recognition. Moreover, they contain both appearance information and 3D structure of the scenes from the RGB modality and depth modality respectively. Motivated by these advantages,

Categories:
7 Views

Dear SigPort Users, do you want to use audio and video to demonstrate your research results? SigPort has a solution.  Sigport now supports PDF documents with audio/video attachments. Please see our sample files:  Sample 1: http://sigport.org/1791     Sample 2: http://sigport.org/1792     How to add audio and video to your presentation slides and posters?

Categories:
13 Views

Dear SigPort Users, do you want to use audio and video to demonstrate your research results? SigPort has a solution.  Sigport now supports PDF documents with audio/video attachments. Please see our sample files: Sample 1: http://sigport.org/1791    Sample 2: http://sigport.org/1792     How to add audio and video to your presentation slides and posters?

Categories:
738 Views

Pages