5 papers · 1 filter
MotionHint: Self-Supervised Monocular Visual Odometry with Motion Constraints
Cong Wang, Yu-Ping Wang, Dinesh Manocha
We present a novel self-supervised algorithm named MotionHint for monocular visual odometry (VO) that takes motion constraints into account. A key aspect of our approach is to use…
Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention
Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli +2
We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched. Our m…
HighlightMe: Detecting Highlights from Human-Centric Videos
Uttaran Bhattacharya, Gang Wu, Stefano Petrangeli +2
We present a domain- and user-preference-agnostic approach to detect highlightable excerpts from human-centric videos. Our method works on the graph-based representation of multipl…
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…