STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits

@inproceedings{Bhattacharya2020STEPST,
  title={STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits},
  author={Uttaran Bhattacharya and Trisha Mittal and Rohan Chandra and Tanmay Randhavane and Aniket Bera and D. Manocha},
  booktitle={AAAI},
  year={2020}
}
  • Uttaran Bhattacharya, Trisha Mittal, +3 authors D. Manocha
  • Published in AAAI 2020
  • Computer Science
  • We present a novel classifier network called STEP, to classify perceived human emotion from gaits, based on a Spatial Temporal Graph Convolutional Network (ST-GCN) architecture. Given an RGB video of an individual walking, our formulation implicitly exploits the gait features to classify the emotional state of the human into one of four emotions: happy, sad, angry, or neutral. We use hundreds of annotated real-world gait videos and augment them with thousands of annotated synthetic gaits… CONTINUE READING
    16 Citations

    Figures, Tables, and Topics from this paper

    Explore Further: Topics Discussed in This Paper

    ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation
    • 9
    • PDF
    Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression
    • 4
    • PDF
    Learnable Graph Inception Network for Emotion Recognition
    • PDF
    EmotiCon: Context-Aware Multimodal Emotion Recognition Using Frege’s Principle
    • 14
    • PDF
    Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders
    • 4
    • Highly Influenced
    • PDF
    Emotions Don't Lie: An Audio-Visual Deepfake Detection Method using Affective Cues
    • 9
    • PDF
    How are you feeling? Multimodal Emotion Learning for Socially-Assistive Robot Navigation
    • 4
    The Liar's Walk: Detecting Deception with Gait and Gesture
    • 8
    • PDF

    References

    SHOWING 1-10 OF 105 REFERENCES
    Identifying Emotions from Walking using Affective and Deep Features
    • 22
    • PDF
    Adaptive Real-Time Emotion Recognition from Body Movements
    • 20
    Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
    • 689
    • Highly Influential
    • PDF
    Emotion Recognition through Gait on Mobile Devices
    • Mangtik Chiu, Jiayu Shu, P. Hui
    • Computer Science
    • 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops)
    • 2018
    • 7
    • PDF
    Spatiotemporal Residual Networks for Video Action Recognition
    • 466
    • PDF
    Temporal Convolutional Networks for Action Segmentation and Detection
    • 355
    • PDF
    Emotion Recognition by Body Movement Representation on the Manifold of Symmetric Positive Definite Matrices
    • 13
    • PDF
    3D Convolutional Neural Networks for Human Action Recognition
    • 3,463
    • PDF
    Video-based emotion recognition using CNN-RNN and C3D hybrid networks
    • 238