Effectiveness of Grasp Attributes and Motion-Constraints for Fine-Grained Recognition of Object Manipulation Actions

In this work, we consider the problem of recognition of object manipulation actions. This is a challenging task for real everyday actions, as the same object can be grasped and moved in different ways depending on its functions and geometric constraints of the task. We propose to leverage grasp and motion-constraints information, using a suitable representation, to recognize and understand action intention with different objects. We also provide an extensive experimental evaluation on the recent Yale Human Grasping dataset consisting of large set of 455 manipulation actions. The evaluation involves a) Different contemporary multi-class classifiers, and binary classifiers with one-vsone multi-class voting scheme, and b) Differential comparisons results based on subsets of attributes involving information of grasp and motion-constraints. Our results clearly demonstrate the usefulness of grasp characteristics and motion-constraints, to understand actions intended with an object.