View-Invariant Representation and Recognition of Actions
International Journal of Computer Vision
Invariance in motion analysis of videos
MULTIMEDIA '03 Proceedings of the eleventh ACM international conference on Multimedia
Reconstructing force-dynamic models from video sequences
Artificial Intelligence
Grounding the lexical semantics of verbs in visual perception using force dynamics and event logic
Journal of Artificial Intelligence Research
Learning to classify observed motor behavior
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
A survey of vision-based methods for action representation, segmentation and recognition
Computer Vision and Image Understanding
Human action recognition based on skeleton splitting
Expert Systems with Applications: An International Journal
| Hi-index | 0.00 |
A representation of visual motion convenient for recognition should make prominent the qualitative differences among simple motions. We argue that the first stage in such a motion representation is to make explicit boundaries that we define as starts, stops, and force discontinuities. When one of these boundaries occurs in motion, human observers have the subjective impression that some fleeting, significant event has occurred. We go farther and hypothesize that one of the subjective motion boundaries is seen if and only if one of our defined boundaries occurs. We enumerate all possible motion boundaries and provide evidence that they are psychologically real.