More Like this

1. In the blink of an eye: leveraging blink-induced suppression for imperceptible position and orientation redirection in virtual reality

   https://doi.org/10.1145/3197517.3201335  

   Langbehn, Eike; Steinicke, Frank; Lappe, Markus; Welch, Gregory F.; Bruder, Gerd (July 2018, ACM Transactions on Graphics)
2. Blink: Fast and Generic Collectives for Distributed ML

   Wang, G; Venkataraman, S; Phanishayee, A; Thelin, J; Devanur, N; Stoica, I (March 2020, Conference on Machine Learning and Systems (MLSys))

   Model parameter synchronization across GPUs introduces high overheads for data-parallel training at scale. Existing parameter synchronization protocols cannot effectively leverage available network resources in the face of ever increasing hardware heterogeneity. To address this issue, we propose Blink, a collective communication library that dynamically generates optimal communication primitives by packing spanning trees. We propose techniques to minimize the number of trees generated and extend Blink to leverage heterogeneous communication channels for hybrid, and faster, data transfers. Evaluations show that compared to the state-of-the-art (NCCL), Blink can achieve up to 8× faster model synchronization (AllReduce), and reduce end-to-end DNN training time for image classification tasks by up to 40%. 

   more » « less
3. Blinking characteristics of organic fluorophores for blink-based multiplexing

   https://doi.org/10.1038/s42004-024-01106-5  

   Seabury, Amelia G.; Khodabocus, Alisha J.; Kogan, Isabelle M.; Hoy, Grayson R.; DeSalvo, Grace A.; Wustholz, Kristin L. (January 2024, Communications Chemistry)

   Abstract Single-molecule fluorescence experiments have transformed our understanding of complex materials and biological systems. Whether single molecules are used to report on their nano-environment or provide for localization, understanding their blinking dynamics (i.e., stochastic fluctuations in emission intensity under continuous illumination) is paramount. We recently demonstrated another use for blinking dynamics called blink-based multiplexing (BBM), where individual emitters are classified using a single excitation laser based on blinking dynamics, rather than color. This study elucidates the structure-activity relationships governing BBM performance in a series of model rhodamine, BODIPY, and anthraquinone fluorophores that undergo different photo-physical and-chemical processes during blinking. Change point detection and multinomial logistic regression analyses show that BBM can leverage spectral fluctuations, electron and proton transfer kinetics, as well as photostability for molecular classification—even within the context of a shared blinking mechanism. In doing so, we demonstrate two- and three-color BBM with ≥ 93% accuracy using spectrally-overlapped fluorophores. 

   more » « less
4. In the Blink of an Eye: Event-based Emotion Recognition

   https://doi.org/10.1145/3588432.3591511  

   Zhang, Haiwei; Zhang, Jiqing; Dong, Bo; Peers, Pieter; Wu, Wenwei; Wei, Xiaopeng; Heide, Felix; Yang, Xin (July 2023, ACM)
5. Blink detection for off-angle iris images using deep learning

   https://doi.org/10.1117/12.2662248  

   Palta, Hasan; Omoteso, Timi; Karakaya, Mahmut (June 2023, Pattern Recognition and Tracking XXXIV)

   Alam, Mohammad S.; Asari, Vijayan K. (Ed.)

   Iris recognition is one of the well-known areas of biometric research. However, in real-world scenarios, subjects may not always provide fully open eyes, which can negatively impact the performance of existing systems. Therefore, the detection of blinking eyes in iris images is crucial to ensure reliable biometric data. In this paper, we propose a deep learning-based method using a convolutional neural network to classify blinking eyes in off-angle iris images into four different categories: fully-blinked, half-blinked, half-opened, and fully-opened. The dataset used in our experiments includes 6500 images of 113 subjects and contains images of a mixture of both frontal and off-angle views of the eyes from -50 to 50 in gaze angle. We train and test our approach using both frontal and off-angle images and achieve high classification performance for both types of images. Compared to training the network with only frontal images, our approach shows significantly better performance when tested on off-angle images. These findings suggest that training the model with a more diverse set of off-angle images can improve its performance for off-angle blink detection, which is crucial for real-world applications where the iris images are often captured at different angles. Overall, the deep learning-based blink detection method can be used as a standalone algorithm or integrated into existing standoff biometrics frameworks to improve their accuracy and reliability, particularly in scenarios where subjects may blink. 

   more » « less