Hueihan Jhuang

Learn More
With nearly one billion online videos viewed everyday, an emerging new frontier in computer vision research is recognition and search in video. While much effort has been devoted to the collection and annotation of large scalable static image datasets containing thousands of image categories, human action datasets lag far behind. Current action recognition(More)
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feedforward architectures [25, 16, 20] and extends a neurobiological model of motion processing in the visual cortex [10]. The system consists of a hierarchy of spatio-temporal feature(More)
Although action recognition in videos is widely studied, current methods often fail on real-world datasets. Many recent approaches improve accuracy and robustness to cope with challenging video sequences, but it is often unclear what affects the results most. This paper attempts to provide insights based on a systematic performance evaluation using(More)
Several authors have noticed that the common representation of images as vectors is sub-optimal. The process of vectorization eliminates spatial relations between some of the nearby image measurements and produces a vector of a dimension which is the product of the measurements' dimensions. It seems that images may be better represented when taking into(More)
BACKGROUND Ankyrin 3 (ANK3) has been strongly implicated as a risk gene for bipolar disorder (BD) by recent genome-wide association studies of patient populations. However, the genetic variants of ANK3 contributing to BD risk and their pathological function are unknown. METHODS To gain insight into the potential disease relevance of ANK3, we examined the(More)
Neurobehavioural analysis of mouse phenotypes requires the monitoring of mouse behaviour over long periods of time. In this study, we describe a trainable computer vision system enabling the automated analysis of complex mouse behaviours. We provide software and an extensive manually annotated video database used for training and testing the system. Our(More)
A U T O M AT E D H O M E-C A G E B E H AV I O R A L PH E N O T YPIN G O F M I C E Hueihan Jhuang, Estibaliz Garrote, Xinlin Yu, Vinita Khilnani, Tomaso Poggio, Andrew D. Steele* and Thomas Serre * Department of Brain and Cognitive Sciences, McGovern Institute, Massachusetts Institute of Technology Current address: Department of Cognitive, Linguistic &(More)
The dorsal stream in the primate visual cortex is involved in the perception of motion and the recognition of actions. The two topics, motion processing in the brain, and action recognition in videos, have been developed independently in the field of neuroscience and computer vision. We present a dorsal stream model that can be used for the recognition of(More)
We describe a fully trainable computer vision system enabling the automated analysis of complex mouse behaviors. Our system computes a sequence of feature descriptors for each video sequence and a classifier is used to learn a mapping from these features to behaviors of interest. We collected a very large manually annotated video database of mouse behaviors(More)
Shot-boundary detection is the first step towards scene extraction in videos, which is useful for video content analysis and indexing. In this work, we apply gist and color features to represent the individual frames. Gist [15, 21] has been shown to characterize the structure of images well while being resistant to luminance change and also small(More)