Activity Recognition

Activity Recognition

Activity recognition has become a very active area in the past few years. It is a challenging problem that has attracted the attention of the research community due to its practical and real-world applications, such as human computer interfaces, content based video indexing, video surveillance, and robotics, among others. A definition for such task can be described as labeling video segments containing human motion with activity classes. For instance, we can define an activity as a composition of one or more actions organized temporally.

Basically, the literature divides the activity recognition task on three main steps: (i) data representation (feature extraction), allowing the image/video content to be represented in a more discriminative space being rich enough to allow a proper recognition; (ii) activity segmentation, producing atomic movements by identifying suitable break points resulting into segments that could be used to describe the  action as a whole or even the task to find the spatial and temporal location of the action; and (iii)  activity classification, which the purpose is to learn a function that can assign (discrete) labels to the images/videos.




1.Carlos Caetano, Jefersson A. dos Santos, William Robson Schwartz (2018): Statistical Measures from Co-occurrence of Codewords for Action Recognition. In: VISAPP 2018 - International Conference on Computer Vision Theory and Applications, pp. 1-8, 2018. (Type: Inproceeding | Links | BibTeX)
2.Victor Hugo Cunha de Melo, Jesimon B. Santos, Carlos Caetano, Jessica Sena, Otavio A. B. Penatti, William Robson Schwartz (2018): Object-based Temporal Segment Relational Network for Activity Recognition. In: Conference on Graphic, Patterns and Images (SIBGRAPI), pp. 1-8, 2018. (Type: Inproceeding | BibTeX)
3.Igor L. O Bastos, Larissa Rocha Soares, William Robson Schwartz (2017): Pyramidal Zernike Over Time: A spatiotemporal feature descriptor based on Zernike Moments. In: Iberoamerican Congress on Pattern Recognition (CIARP 2017), pp. 77-85, 2017. (Type: Inproceeding | Links | BibTeX)
4.Carlos Caetano, Victor Hugo Cunha de Melo, Jefersson Alex dos Santos, William Robson Schwartz (2017): Activity Recognition based on a Magnitude-Orientation Stream Network. In: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2017. (Type: Inproceeding | Links | BibTeX)
5.Carlos Caetano, Jefersson A. dos Santos, William Robson Schwartz (2016): Optical Flow Co-occurrence Matrices: A Novel Spatiotemporal Feature Descriptor. In: IAPR International Conference on Pattern Recognition (ICPR), pp. 1-6, 2016. (Type: Inproceeding | Links | BibTeX)