Recent studies have implicated the role of differential co-expression or correlation structure in gene expression data to help explain phenotypic differences. However, few attempts have been made to characterize the function of variants based on their role in regulating differential co-expression. Here, we describe a statistical methodology that identifies pairs of transcripts that display diff...

We benchmark two tracking methods developed in the INRIA Lagadic team with a TrakMark dataset. Since these methods are based on a 3D model based approach, we selected a dataset named “Conference Venue Package 01” that includes a 3D textured model of a scene. For the evaluation. we compute the error of 3D rotation and translation with the ground truth transformation matrix. Through these evaluat...

Institutional investors are building increasingly more sophisticated algorithmic trading engines that account for textual as well as numerical information. To train these engines they need large datasets of information with highly accurate timestamps that cover long periods with differing trading conditions. Thus, the demand for temporal news datasets beyond the point where full archives are av...

In this paper, we propose a novel action recognition framework. The method uses pictorial structures and shrinkage optimized directed information assessment (SODA) coupled with Markov Random Fields called SODA+MRF to model the directional temporal dependency and bidirectional spatial dependency. As a variant of mutual information, directional information captures the directional information flo...

In this notebook paper, we describe our approach in the submission to the temporal action proposal (task 3) and temporal action localization (task 4) of ActivityNet Challenge hosted at CVPR 2017. Since the accuracy in action classification task is already very high (nearly 90% in ActivityNet dataset), we believe that the main bottleneck for temporal action localization is the quality of action ...

We present a new dataset, Functional Map of the World (fMoW), which aims to inspire the development of machine learning models capable of predicting the functional purpose of buildings and land use from temporal sequences of satellite images and a rich set of metadata features. The metadata provided with each image enables reasoning about location, time, sun angles, physical sizes, and other fe...

Many interesting processes can be represented as time-dependent datasets. We define a time-dependent dataset as a sequence of datasets captured at particular time steps. In such a sequence, each dataset is composed of observations (high-dimensional real vectors), and each observation has a corresponding observation across time steps. Dimensionality reduction provides a scalable alternative to c...

Instance level video object segmentation is an important technique for video editing and compression. To capture the temporal coherence, in this paper, we develop MaskRNN, a recurrent neural net approach which fuses in each frame the output of two deep nets for each object instance — a binary segmentation net providing a mask and a localization net providing a bounding box. Due to the recurrent...

Object Movement Identification from videos is very challenging, and has got numerous applications in sports evaluation, video surveillance, elder/child care, etc. In thisresearch, a model using sparse representation is presented for the human activity detection from the video data. This is done using a linear combination of atoms from a dictionary and a sparse coefficient matrix. The dictionary...

This paper proposes a simple yet effective face sketch synthesis method. Similar to existing exemplar-based methods, a training dataset containing photo-sketch pairs is required, and a K-NN photo patch search is performed between a test photo and every training exemplar for sketch patch selection. Instead of using the Markov Random Field to optimize global sketch patch selection, this paper for...