Functional categorization of objects using real-time markerless motion capture

By Juergen Gall, Andrea Fossati, Luc Van Gool. 2011

68 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Learning human activities and object affordances from RGB-D videos (2012, methodology): “Similarly, we have an energy term, Ea, for labeling the sub-activity nodes which is defined as the sum of sub-activity node potentials as Ea = i∈Va ψa(i) = i∈Va k∈Ka yki wka · φa(i) , (4) where φa(i) denotes the feature map describing the subactivity node i through a vector of features, and…”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, methodology): “In this work, we combine in a single framework a generative model with discriminative salient points detected by aHough forest (Gall et al. 2011), i.”
First Person Action-Object Detection with EgoNet (2016, background): “Conversely, the activity can provide a functional cue to recognize objects [48, 14, 24].”
Modeling 4D Human-Object Interactions for Event and Object Recognition (2013, background): “In recent years, many work applied the human-object mutual context to event and object recognition [2, 5, 7, 9, 11, 14, 15, 23, 24].”
Audio-visual classification and detection of human manipulation actions (2014, background): “This has been confirmed in recent works [22]–[27] and it is supported by Gibson’s affordance theory [28], which states that humans and animals recognize objects in terms of function, in a task oriented manner.”
Articulated and Generalized Gaussian Kernel Correlation for Human Pose Estimation (2016, methodology): “Most generative methods involve explicit correspondence estimation in an ICP-like framework, where the pose and correspondence are iteratively and alternately updated, e.g. [7], [33].”
Human Activity Learning using Object Affordances from RGB-D Videos (2012, methodology): “[24] also use depth data to perform sub-activity (referred to as action) classiﬁcation and functional categorization of objects.”