233 citations · 450 across the 31 of their papers we have counts for
8 papers · 1 filter
Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs
Rohan Chandra, Tianrui Guan, Srujan Panuganti +4
We present a novel approach for traffic forecasting in urban traffic scenarios using a combination of spectral graph analysis and deep learning. We predict both the low-level infor…
M3ER: Multiplicative Multimodal Emotion Recognition Using Facial, Textual, and Speech Cues
Trisha Mittal, Uttaran Bhattacharya, Rohan Chandra +2
We present M3ER, a learning-based method for emotion recognition from multiple input modalities. Our approach combines cues from multiple co-occurring modalities (such as face, tex…
Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping
Uttaran Bhattacharya, Christian Roncal, Trisha Mittal +5
We present an autoencoder-based semi-supervised approach to classify perceived human emotions from walking styles obtained from videos or motion-captured data and represented as se…
STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits
Uttaran Bhattacharya, Trisha Mittal, Rohan Chandra +3
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. Gi…
GraphRQI: Classifying Driver Behaviors Using Graph Spectrums
Rohan Chandra, Uttaran Bhattacharya, Trisha Mittal +3
We present a novel algorithm (GraphRQI) to identify driver behaviors from road-agent trajectories. Our approach assumes that the road-agents exhibit a range of driving traits, such…
DensePeds: Pedestrian Tracking in Dense Crowds Using Front-RVO and Sparse Features
Rohan Chandra, Uttaran Bhattacharya, Aniket Bera +1
We present a pedestrian tracking algorithm, DensePeds, that tracks individuals in highly dense crowds (greater than 2 pedestrians per square meter). Our approach is designed for vi…