Blog(1)
Temporal sequences (e.g., videos) are an appealing data source as they provide a rich source of information and additional constraints to leverage in learning. By far the main focus on temporal sequence analysis in computer vision has been on learning representations (i.e., compact abstractions of the input data) targeting high-level distinctions between signals (e.g., action classification, “What action is present in the video?”).
Research Areas(0)
Publications(18)
SonicFinger: Pre-touch and Contact Detection Tactile Sensor for Reactive Pregrasping
AuthorSiddharth Rupavatharam; Caleb Escobedo; Daewon Lee; Colin Prepscius; Larry Jackel; Richard Howard; Volkan Isler
PublishedInternational Conference on Robotics and Automation (ICRA)
Date2023-05-29
Identifying Multimodal Context Awareness Requirements for Supporting User Interaction with Procedural Videos
AuthorGeorgianna Lin, Jinyi Li, Afsaneh Fazly, Vladimir Pavlović, Khai Truong
PublishedInternational Conference on Human Factors in Computing Systems (CHI)
Date2023-04-23
Efficient Flow-Guided Multi-frame De-fencing
AuthorStavros Tsogkas, Fengjia Zhang, Allan Jepson, Alex Levinshtein
PublishedIEEE Winter Conference on Applications of Computer Vision (WACV)
Date2023-01-03
News(2)
The problem of sequence-to-sequence alignment is central to many computational applications. Aligning two sequences (e.g., temporal signals) entails computing the optimal pairwise correspondence between the sequence elements while preserving their match orderings.
SRC-N ‘s published paper “Automatic Detection and Classification System of Domestic Waste via Multi-Model Cascaded Convolutional Neural Network” and “Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction” was accepted.
Others(0)