EgoSampling: Fast-Forward and Stereo for Egocentric Videos
arXiv:1412.3596 · doi:10.1109/CVPR.2015.7299109
Abstract
While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.
in IEEE CVPR 2015, Boston, MA, June 2015
Cited by in corpus (10)
- Compact CNN for Indexing Egocentric Videos
- Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions
- Making a long story short: A Multi-Importance fast-forwarding egocentric videos with the emphasis on relevant objects
- Towards Semantic Fast-Forward and Stabilized Egocentric Videos
- Fast-Forward Video Based on Semantic Extraction
- A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos
- Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal Attention
- Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method
- Collaborative Multi-Agent Video Fast-Forwarding
- Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization