Automatic event detection in cell videos is essential for monitoring cell populations in biomedicine. Deep learning methods have advantages over traditional approaches for cell event detection due to their ability to capture more discriminative features of cellular processes. Supervised deep learning methods however are inherently limited due to the scarcity of annotated data. Unsupervised deep learning methods have shown promise in general (non-cell) videos because they can learn the visual appearance and motion of regularly occurring events. Cell videos, however, can have rapid, irregular changes in cell appearance and motion, such as during cell division and death, which are often the events of most interest. We propose a novel unsupervised two-path input neural network architecture to capture these irregular events with three key elements: (i) a visual encoding path to capture regular spatio-temporal patterns of observed objects with convolutional long short-term memory units, (ii) an event detection path to extract information related to irregular events with max-pooling layers; and (iii) integration of the hidden states of the two paths to provide a comprehensive representation of the video that is used to simultaneously locate and classify cell events. We evaluated our network in detecting cell division in densely packed stem cells in phase-contrast microscopy videos. Our unsupervised method achieved higher or comparable accuracy to standard and state-of-the-art supervised methods. Index Terms-molecular and cellular imaging, machine learning, cell, unsupervised neural network, pattern recognition and classification 1 I. INTRODUCTION Research in stem cell biology and pharmacology includes the detection of cellular behavior after exposure to various stimuli in cell cultures. Parameters used to monitor cell health and growth include the measurement of cell division (mitosis and meiosis) and cell death [1, 2]. A wide range of procedures with luminescent, colorimetric or fluorescent assays are used to highlight critical events in images or videos. These assays are usually static and destructive and hence do not allow for longterm cell monitoring [3]. Phase-contrast, time-lapse microscopy