Training-free generic object detection in 2-D and 3-D using locally adaptive regression kernels

A method of learning-free detection and localization of actions, comprising:

• a. providing a query video action of interest and providing a target video by using an appropriately programmed computer;
• b. obtaining at least one query space-time localized steering kernel (3-D LSK) from said query video action of interest and obtaining at least one target 3-D LSK from said target video by using said appropriately programmed computer, wherein said kernel 3-D LSK and said target 3-D LSK implicitly contain information about local motion of voxels across time, wherein no explicit motion estimation is required;
• c. determining at least one query feature from said query 3-D LSK and determining at least one target patch feature from said target 3-D LSK by using said appropriately programmed computer;
• and
• d. outputting a resemblance map, wherein said resemblance map provides a likelihood of a similarity between each said query feature and each said target patch feature by using said appropriately programmed computer to output learning-free detection and localization of actions.