Our researchers are actively involved in the broader industrial engineering and computer vision research communities. We share some of this technical work here.
We propose TemporalVLM, a video large language model for effective temporal reasoning and fine-grained understanding in long videos. TemporalVLM includes two novel components: (i) a time-aware clip encoder and (ii) a bidirectional long short-term memory module.
We propose a self-supervised procedure learning framework built upon a fused Gromov-Wasserstein optimal transport formulation with a structural prior to establish frame-to-frame correspondences between videos and a contrastive regularization to avoid the collapse to degenerate solutions, yielding superior results on large-scale egocentric and third-person benchmarks. Our peer-reviewed research has been accepted for publication at WACV 2026.
We propose a novel approach for joint unsupervised video alignment and action segmentation based on a unified optimal transport framework, yielding comparable video alignment yet superior action segmentation results while saving both time and memory consumption. Our peer-reviewed research has been accepted for publication at ICCV 2025.
We use 2D Skeleton Heatmaps and Multi-Modality Fusion to obtain state-of-the-art results on action segmentation. Our peer-reviewed research has been accepted for publication at ICRA 2024.
We use 2D Skeleton Heatmaps and Multi-Modality Fusion to obtain state-of-the-art results on several fine-grained human activity understanding tasks. Our peer-reviewed research has been accepted to ECCV 2024.
We present a novel transformer-based framework for unsupervised activity segmentation which leverages not only frame-level cues but also segment-level cues. Our peer-reviewed research has been accepted for publication at WACV 2024.
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 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.
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.
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.
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 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.
Brandin and his team help our customers with setting up the Pathfinder platform and getting up-to-speed on all the features and functionalities, in addition to assisting them with standardizing their processes where needed.
Brandin is a seasoned manufacturing leader, who has spent more than a decade designing and setting up assembly lines in both the US and China, optimizing them, and working with human operators to maximize productivity and quality.
Jesse works closely with our marquis customers to understand their needs, and figures out the best solution that immediately adds dollars to their bottom line.
Jesse has two decades of enterprise sales experience. He has held sales leadership roles at pioneering technology startups.
Andrey takes inventions and converts them into innovations. He leads our product engineering team to turn our scientific prototypes into robust customer-facing products.
Andrey co-founded and successfully exited a startup to immigrate to the US. He spent his next eight years building the core data science infrastructure for Amazon’s supply chain planning team, and the CV/ML infrastructure for Microsoft’s HoloLens organization.
Zeeshan focuses on delighting our customers by understanding their needs and defining product and strategy to meet and exceed these needs. He works closely with our sales leadership to grow our customer base.
Zeeshan was a scientific leader at Microsoft’s HoloLens division, where he invented AI technologies to assist frontline workers across industries. Earlier, he shipped IoT platforms and visual defect detection software for manufacturers at Siemens and MVTec GmbH.
Huy takes our product roadmap and figures out what’s achievable with today’s AI advances, and what we need to invent to solve our customers’ pain points.
Huy led teams of scientists and engineers at NEC and invented technologies for driver assistance systems that are part of 500,000+ Honda cars. He is an inventor on more than 20 US patents, and his research papers are cited by every lab from MIT, Stanford, and CMU to Apple, Google, and Baidu.
