Human Activity Learning using Object Affordances from RGB-D Videos
By Hema Swetha Koppula, Rudhir Gupta, Ashutosh Saxena. 2012
19 citations recorded by the source corpus.
Human activities comprise several sub-activities performed in a sequence and involve interactions with various objects. This makes reasoning about the object affordances a central task for activity recognition. In this work, we consider the problem of jointly labeling the object affordances and human activities from RGB-D videos. We frame the problem as a Markov Random Field where the nodes represent objects and sub-activities, and the edges represent the relationships between object affordances, their relations with sub-activities, and their evolution over time. We formulate the learning problem using a structural SVM approach, where labeling over various alternate temporal segmentations are considered as latent variables. We tested our method on a dataset comprising 120 activity videos collected from four subjects, and obtained an end-to-end precision of 81.8% and recall of 80.0% for labeling the activities.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Ashutosh Saxena
- Hema Swetha Koppula
- Rudhir Gupta
- Juergen Gall
- Mao Ye
- Qing Zhang
- Jiejie Zhu
- Ruigang Yang
In Computer Vision and Pattern Recognition
- Ashutosh Saxena
- Luc Van Gool
- Hema Swetha Koppula
- Juergen Gall
- Jitendra Malik
- Li Fei-Fei
- Kristen Grauman
- Ruigang Yang
Citations in the corpus
- Learning human activities and object affordances from RGB-D videos (2012, methodology): “1A first version of this work was made available on arXiv (Koppula et al., 2012) for faster dissemination of scientific work.”
- A Survey on Human Motion Analysis from Depth Data (2013, background): “[30, 31] explicitly consider human-object interactions.”