Categorizing object-action relations from semantic scene graphs
By Eren Erdal Aksoy, Alexey Abramov, Florentin Wörgötter, Babette K. Dellen. 2010
96 citations recorded by the source corpus.
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
- Juergen Gall
- Luc Van Gool
- Ashutosh Saxena
- Hema Swetha Koppula
- Michael J. Black
- Rudhir Gupta
- Mohamed Hassan
- Hedvig Kjellström
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jitendra Malik
- Michael J. Black
- Cordelia Schmid
- Abhinav Kumar Gupta
- Ashutosh Saxena
- Andrew Zisserman
- Kristen Grauman
Citations in the corpus
- Learning human activities and object affordances from RGB-D videos (2012, background): “Some recent works (Gupta et al., 2009; Yao and Fei-Fei, 2010; Aksoy et al., 2010; Jiang et al., 2011a; Pirsiavash and Ramanan, 2012) show that modeling the interaction between human poses and objects in 2D videos results in a better performance on the tasks of object detection and activity recogniti”
- Audio-visual classification and detection of human manipulation actions (2014, background): “proposed by [29] but, in their current implementation, this approach requires the manual definition of discrete labels, and it is furthermore sensitive to the observation point of view.”
- Resolving 3D Human Pose Ambiguities With 3D Scene Constraints (2019, background): “Joint Human & World Models: Several works focus on improving 2D object detection, 2D pose, and action recognition by observing RGB imagery of people interacting with objects [5, 23, 35, 52, 72].”
- Functional categorization of objects using real-time markerless motion capture (2011, background): “In [1], a rule-based approach is proposed to extract scene graphs that represent spatio-temporal correlations between objects.”
- Hallucinated Humans as the Hidden Context for Labeling 3D Scenes (2013, background): “Only recently, some works [9, 32, 1, 25, 20] have shown that modeling the interaction between human poses and objects in 2D images and videos result in a better performance on the tasks of object detection and activity recognition.”
- Learning the semantics of object–action relations by observation (2011, background): “Parts of this study have been published at a conference (Aksoy et al. 2010).”