3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image

Chakraborty, Ishani; Cheng, Hui; Javed, Omar

doi:10.1109/cvpr.2013.437

Cited by 20 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ramanathan et al [18] recognize social roles played by people in various events. Chakraborty et al [4] classify photos into classes such as 'couple, family, group, or crowd'. Sun et al [22] predict social relationships for fine-grained relationships between humans in everyday images.…”

Section: Social Relationship Recognitionmentioning

confidence: 99%

An End-To-End Network for Generating Social Relationship Graphs

Goel

Teck

Tan

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Socially-intelligent agents are of growing interest in artificial intelligence. To this end, we need systems that can understand social relationships in diverse social contexts. Inferring the social context in a given visual scene not only involves recognizing objects, but also demands a more indepth understanding of the relationships and attributes of the people involved. To achieve this, one computational approach for representing human relationships and attributes is to use an explicit knowledge graph, which allows for high-level reasoning. We introduce a novel end-to-endtrainable neural network that is capable of generating a Social Relationship Graph -a structured, unified representation of social relationships and attributes -from a given input image. Our Social Relationship Graph Generation Network (SRG-GN) is the first to use memory cells like Gated Recurrent Units (GRUs) to iteratively update the social relationship states in a graph using scene and attribute context. The neural network exploits the recurrent connections among the GRUs to implement message passing between nodes and edges in the graph, and results in significant improvement over previous methods for social relationship recognition.

show abstract

Section: Social Relationship Recognitionmentioning

confidence: 99%

An End-To-End Network for Generating Social Relationship Graphs

Goel

Teck

Tan

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…These theories have already been exploited for detecting conversational groups on still images. For example, [4] estimated 3D proxemics parameters to identify social interactions in internet images [8,28,29]. Detected social interactions on RGB images using the concept of F-Formations by [16], where the centre of a circular space (O-Space) is induced by people's orientation [40].…”

Section: Detection Of Social Interactionsmentioning

confidence: 99%

“…In particular, we build two windowed moving histograms, with 9 time bins each, splitting the QTC C components in two sets: the first one considers the distance relations (q 1 , q 2 ), while the second captures the side relations (q 3 , q 4 ). This separation has also the advantage of reducing the total number of bins (2 • 3 2 rather than 3 4 ). An example of QTC C histogram is shown in Fig.…”

Section: Segmentation Featuresmentioning

confidence: 99%

Social Activity Recognition on Continuous RGB-D Video Sequences

Coppola

Coşar

Faria

et al. 2019

Int J of Soc Robotics

View full text Add to dashboard Cite

Modern service robots are provided with one or more sensors, often including RGB-D cameras, to perceive objects and humans in the environment. This paper proposes a new system for the recognition of human social activities from a continuous stream of RGB-D data. Many of the works until now have succeeded in recognising activities from clipped videos in datasets, but for robotic applications it is important to be able to move to more realistic scenarios in which such activities are not manually selected. For this reason, it is useful to detect the time intervals when humans are performing social activities, the recognition of which can contribute to trigger human-robot interactions or to detect situations of potential danger. The main contributions of this research work include a novel system for the recognition of social activities from continuous RGB-D data, combining temporal segmentation and classification, as well as a model for learning the proximity-based priors of the social activities. A new public dataset with RGB-D videos of social and individual activities is also provided and used for evaluating the proposed solutions. The results show the good performance of the system in recognising social activities from continuous RGB-D data.

show abstract

“…The space is divided into intimate, personal, social and public spaces. In robotics, this is a topic that was carried out by [15], [16], [17], yet in a simpler way, using only the concept of defined distances based on thresholds observed from social science. Differently from others, our approach extracts proximity-based features learned from social interaction as prior for the recognition module.…”

Section: Introductionmentioning

confidence: 99%

Social activity recognition based on probabilistic merging of skeleton features with proximity priors from RGB-D data

Coppola

Faria

Nunes

et al. 2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Social activity based on body motion is a key feature for non-verbal and physical behavior defined as function for communicative signal and social interaction between individuals. Social activity recognition is important to study human-human communication and also human-robot interaction. Based on that, this research has threefold goals: (1) recognition of social behavior (e.g. human-human interaction) using a probabilistic approach that merges spatio-temporal features from individual bodies and social features from the relationship between two individuals; (2) learn priors based on physical proximity between individuals during an interaction using proxemics theory to feed a probabilistic ensemble of activity classifiers; and (3) provide a public dataset with RGB-D data of social daily activities including risk situations useful to test approaches for assisted living, since this type of dataset is still missing. Results show that using the proposed approach designed to merge features with different semantics and proximity priors improves the classification performance in terms of precision, recall and accuracy when compared with other approaches that employ alternative strategies.

show abstract

3D Visual Proxemics: Recognizing Human Interactions in 3D from a Single Image

Cited by 20 publications

References 15 publications

An End-To-End Network for Generating Social Relationship Graphs

An End-To-End Network for Generating Social Relationship Graphs

Social Activity Recognition on Continuous RGB-D Video Sequences

Social activity recognition based on probabilistic merging of skeleton features with proximity priors from RGB-D data

Contact Info

Product

Resources

About