Domain and View-Point Agnostic Hand Action Recognition

View-Invariance in Action Recognition

Automatically understanding human actions using motion trajectories derived from video sequences is a very challenging problem. Since an action takes place in 3-D, and is projected on 2-D image, depending on the viewpoint of the camera, the projected 2-D trajectory may vary. Therefore, the same action may have very different trajectories, and trajectories of different actions may look the same....

View-Independent Recognition of Hand Postures

In Proc. of IEEE Conf. on CVPR’2000, Vol.II, pp.88-94, Hilton Head Island, SC, 2000 Since human hand is highly articulated and deformable, hand posture recognition is a challenging example in the research of view-independent object recognition. Due to the difficulties of the modelbased approach, the appearance-based learning approach is promising to handle large variation in visual inputs. Howe...

Agnostic Domain Adaptation

The supervised learning paradigm assumes in general that both training and test data are sampled from the same distribution. When this assumption is violated, we are in the setting of transfer learning or domain adaptation: Here, training data from a source domain, aim to learn a classifier which performs well on a target domain governed by a different distribution. We pursue an agnostic approa...

Data Compression Approach to Monolingual GIRT Task: an Agnostic Point of View

Point of View: Custom Information Delivery via Hand-Held Devices

Socially, hand-held devices are becoming ubiquitous; technologically, they are already in a position to mediate access to on-line news. We argue that current frameworks for news delivery to hand-helds, typically involving transcoding methods by remote proxies layered over generic summarisation techniques are not well suited to the task. This work addresses two questions in this context: the spe...