Research Contributions
Our researchers are actively involved in the broader industrial engineering and computer vision research communities. We share some of this technical work here.
We introduce our approach for temporal activity segmentation with timestamp supervision, through a graph convolutional network, which is learned in an end-to-end manner to exploit both frame features and connections between neighboring frames to generate dense framewise labels from sparse timestamp labels. Our peer-reviewed research has been accepted for publication at IROS 2022.


Timestamp-Supervised Action Segmentation with Graph Convolutional Networks
We introduce our approach for temporal activity segmentation with timestamp supervision, through a graph convolutional network, which is learned in an end-to-end manner to exploit both frame features and connections between neighboring frames to generate dense framewise labels from sparse timestamp labels. Our peer-reviewed research has been accepted for publication at IROS 2022.

Unsupervised Activity Segmentation by Joint Representation Learning and Online Clustering
We present a novel approach for unsupervised activity segmentation, which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. Our peer-reviewed research has been accepted for publication at CVPR 2022.

Learning by Aligning Videos in Time
We present a Self-Supervised Approach for Training Viewpoint-, Actor-, and Scene-Invariant Video Representations. Our peer-reviewed research was accepted for publication at CVPR 2021.

ICCV Workshop on Computer Vision for the Factory Floor
With this workshop, we bring together computer vision researchers and leaders from academia and industry for exchange of ideas that lie at the intersection of computer vision and the smart factory.

Towards Anomaly Detection in Dashcam Videos
We present a novel framework for unsupervised anomaly detection in video streams, evaluated on dashcam video datasets. Our peer-reviewed research was published at IV 2020.

Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
We present a novel approach for activity recognition in few-shot settings. Our peer-reviewed research was published at the IEEE Transactions on Pattern Analysis and Machine Intelligence 2021.
We present a novel approach for unsupervised activity segmentation, which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. Our peer-reviewed research has been accepted for publication at CVPR 2022.

We present a Self-Supervised Approach for Training Viewpoint-, Actor-, and Scene-Invariant Video Representations. Our peer-reviewed research was accepted for publication at CVPR 2021.

With this workshop, we bring together computer vision researchers and leaders from academia and industry for exchange of ideas that lie at the intersection of computer vision and the smart factory.

We present a novel framework for unsupervised anomaly detection in video streams, evaluated on dashcam video datasets. Our peer-reviewed research was published at IV 2020.

We present a novel approach for activity recognition in few-shot settings. Our peer-reviewed research was published at the IEEE Transactions on Pattern Analysis and Machine Intelligence 2021.
