This Hand Is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video

53 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, background): “[30] studied the problem of hand disambiguation of multiple people in egocentric videos by modeling the spatial, temporal, and appearance coherency constraints of moving hands.”
Pooled motion features for first-person videos (2014, background): “Even though there has been previous works on extraction of first-person-specific semantic features like hand locations [11] and human gaze [13], features and representations designed to capture motion dynamics of first-person videos have been lacking.”
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions (2015, background): “In the context of detecting hands in egocentric views, there are strong spatial biases to hand location and size [5, 18], because of the way people coordinate head and hand movements: people are likely to center their active hand in or near their visual field as they perform a task, for example.”
Analysis of Hand Segmentation in the Wild (2018, methodology): “or each environment using scene-level feature probes. However, they assumed that there are no social interactions in videos, so that all hands in the video belong to the egocentric viewer. Lee et al. [22] proposed an approach to detect hands in social interactions in egocentric videos. They also pro”