Improving Social Awareness Through DANTE: Deep Affinity Network for Clustering Conversational Interactants

@article{Swofford2020ImprovingSA,
  title={Improving Social Awareness Through DANTE: Deep Affinity Network for Clustering Conversational Interactants},
  author={Mason Swofford and John Peruzzi and Marynel V{\'a}zquez and Roberto Mart{\'i}n-Mart{\'i}n and Silvio Savarese},
  journal={Proceedings of the ACM on Human-Computer Interaction},
  year={2020},
  volume={4},
  pages={1 - 23}
}
We propose a data-driven approach to detect conversational groups by identifying spatial arrangements typical of these focused social encounters. Our approach uses a novel Deep Affinity Network (DANTE) to predict the likelihood that two individuals in a scene are part of the same conversational group, considering their social context. The predicted pair-wise affinities are then used in a graph clustering framework to identify both small (e.g., dyads) and large groups. The results from our… 
Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos
TLDR
This paper proposes an end-to-end trainable framework for the social task, and sets the state-of-the-art results on two widely adopted benchmarks for the traditional group activity recognition task.
REFORM: Recognizing F-formations for Social Robots
TLDR
This work introduces REFORM (REcognize F-FORmations with Machine learning), a data-driven approach for detecting F-formations given human and agent positions and orientations, and introduces symmetry and tightness as quantitative measures to characterize F- formations.
Social Processes: Self-Supervised Forecasting of Nonverbal Cues in Social Conversations
TLDR
This work forms the task of Social Cue Forecasting to leverage the larger amount of unlabeled low-level behavior cues, and proposes the Social Process (SP) models—socially aware sequence-to-sequence (Seq2Seq) models within the Neural Process (NP) family.
Deep Neural Network with Extracted Features for Social Group Detection
TLDR
In the latest years, the use of deep neural networks (DNNs) for learning and detecting has been increased, and in this work, DNNs are used for detecting social groups with extracted features.
Perceptions of Conversational Group Membership based on Robots' Spatial Positioning: Effects of Embodiment
TLDR
The results suggest that robot embodiment can influence perceptions of conversational group membership and whether robot embodiment leads to a discernible orientation for the agent.
Group-Aware Robot Navigation in Crowded Environments
TLDR
Simulation experiments show that group-aware policies, compared to baseline policies that neglect human groups, achieve greater robot navigation performance, minimize violation of social norms and discomfort, and reduce the robot’s movement impact on pedestrians.
Prevention and Resolution of Conflicts in Social Navigation - a Survey
TLDR
This survey starts by defining a conflict in social navigation, and offers a detailed taxonomy of its components, then maps existing work while discussing papers using the framing of the proposed taxonomy.
Temporal Anticipation and Adaptation Methods for Fluent Human-Robot Teaming
  • T. Iqbal, L. Riek
  • Computer Science
    2021 IEEE International Conference on Robotics and Automation (ICRA)
  • 2021
TLDR
This paper introduces TANDEM: Temporal Anticipation and Adaptation for Machines, a series of neurobiologically-inspired algorithms that enable robots to fluently coordinate with people that leverages a humanlike understanding of external and internal temporal changes to facilitate coordination.
The Visual Social Distancing Problem
TLDR
The Visual Social Distancing problem is introduced, defined as the automatic estimation of the inter-personal distance from an image, and the characterization of related people aggregations, and indicates a path to research new Computer Vision methods that can possibly provide a solution to such problem.
Conversational Group Detection with Graph Neural Networks
TLDR
The results suggest that using GNNs to leverage both individual and relationship features when computing groups is beneficial, especially when more features are available for each individual.
...
1
2
...

References

SHOWING 1-10 OF 90 REFERENCES
Conversational Group Detection With Deep Convolutional Networks
TLDR
This paper is the first paper to incorporate features extracted from the room layout image, and the first to incorporate a deep network to generate an image representation of the proposed o-spaces, which builds on the PointNet architecture which allows unordered inputs of variable sizes.
SALSA: A Novel Dataset for Multimodal Group Behavior Analysis
TLDR
This work proposes SALSA, a novel dataset facilitating multimodal and Synergetic sociAL Scene Analysis, and shows how the recorded multiple cues synergetically aid automatic analysis of social interactions.
Detecting conversational groups in images and sequences: A robust game-theoretic approach
TLDR
A game-theoretic framework is proposed, aimed at modeling the spatial structure characterizing F-formations, a common type of people aggregation occurring when two or more persons sustain a social interaction, such as a chat at a cocktail party.
F-Formation Detection: Individuating Free-Standing Conversational Groups in Images
TLDR
A rigorous definition of group is furnished considering the background of the social sciences, which allows to specify many kinds of group, so far neglected in the Computer Vision literature, and a detailed state of the art on the group detection algorithms are presented.
Recognizing F-Formations in the Open World
TLDR
A data-driven approach to detect F-formations from sets of tracked human positions and orientations is explored, trained and evaluated on two openly available human-only datasets and a small human-robot dataset that was collected.
Automatic detection of interaction groups
TLDR
This paper proposes an approach for detecting interaction group configurations based on the assumption that conversational turn taking is synchronized inside groups based on one HMM constructed upon conversational hypotheses, which shows good results and thus confirms the conversational hypothesis.
Social interaction discovery by statistical analysis of F-formations
TLDR
A novel approach for detecting social interactions in a crowded scene by employing solely visual cues and employing the sociological notion of F-formation, which is a set of possible configurations in space that people may assume while participating in a social interaction.
Temporal encoded F-formation system for social interaction detection
TLDR
This paper proposes an extended F-formation system for robust detection of interactions and interactants, which employs a heat-map based feature representation for each individual, namely Interaction Space (IS), to model their location, orientation, and temporal information.
Discovering social interactions in real work environments
The goal of this work is to detect pairwise primitive interactions in groups for social interaction analysis in real environments. We propose a system that extracts locations and head poses of people
Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic Interaction
We present a new research task and a dataset to understand human social interactions via computational methods, to ultimately endow machines with the ability to encode and decode a broad channel of
...
1
2
3
4
5
...