Affordances and Action Recognition
Affordances are opportunities for action that are directly perceivable in an organism’s environment without higher-level cognitive functions. Action recognition is the result of mapping an observed action onto an internal motor or semantic representation.
Affordances are defined by Gibson  as opportunities for action that are directly perceivable without the need for higher-level cognitive functions such as object recognition. The concept of affordances for action has generated significant interest in the computer vision and robotics community. More recently, links between this concept and that of action recognition have been explored, suggesting that the two may share common mechanisms.
Affordances. In robotics, early use of the term affordances dealt with the extraction of features from the visual environment that signal...
- 1.Gibson JJ (1966) The senses considered as perceptual systems. Houghton Mifflin, BostonGoogle Scholar
- 3.Paletta L, Fritz G, Kintzler F, Irran J, Dorffner G (2007) Learning to perceive affordances in a framework of developmental embodied cognition. IEEE International Conference on Development and Learning, London, pp 110–115Google Scholar
- 9.Yamato J, Ohya J, Ishii K (1992) Recognizing human action in time-sequential images using hidden Markov model. In: Proceedings of computer vision and pattern recognition (CVPR), Champaign, IL, pp 379–385Google Scholar
- 10.Bobick AF, Ivanov YA (1998) Action recognition using probabilistic parsing. In: Proceedings of computer vision and pattern recognition (CVPR), Santa Barbara, pp 196–202Google Scholar
- 11.Gupta A, Davis LS (2007) Objects in action: an approach for combining action understanding and object perception. In: Proceedings of computer vision and pattern recognition (CVPR), Minneapolis, pp 1–8Google Scholar
- 13.Lopes M, Melo FS, Montesano L (2007) Affordance-based imitation learning in robots. In: IEEE/RSJ international conference on intelligent robots and systems, San Diego, CA, pp 1015–1021Google Scholar
- 14.Moore DJ, Essa IA, Hayes MH (1999) Exploiting human actions and object context for recognition tasks. Proc Int Conf Comput Vis (ICCV) 1:80–86Google Scholar