skip to main content

Search for: All records

Creators/Authors contains: "Ma, Jian"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, for scalability and quality. In total, we publicly release 272K manual semantic masks of 257 object classes, 9.9M interpolated dense masks, 67K hand-object relations, covering 36 hours of 179 untrimmed videos. Along with the annotations, we introduce three challenges in video object segmentation, interaction understanding and long-term reasoning. For data, code and leaderboards: 
    more » « less
  2. Abstract

    Higher-order genome organization and its variation in different cellular conditions remain poorly understood. Recent high-coverage genome-wide chromatin interaction mapping using Hi-C has revealed spatial segregation of chromosomes in the human genome into distinct subcompartments. However, subcompartment annotation, which requires Hi-C data with high sequencing coverage, is currently only available in the GM12878 cell line, making it impractical to compare subcompartment patterns across cell types. Here we develop a computational approach, SNIPERĀ (Subcompartment iNference using Imputed Probabilistic ExpRessions), based on denoising autoencoder and multilayer perceptron classifier to infer subcompartments using typical Hi-C datasets with moderate coverage. SNIPER accurately reveals subcompartments using moderate coverage Hi-C datasets and outperforms an existing method that uses epigenomic features in GM12878. We apply SNIPER to eight additional cell lines and find that chromosomal regions with conserved and cell-type specific subcompartment annotations have different patterns of functional genomic features. SNIPER enables the identification of subcompartments without high-coverage Hi-C data and provides insights into the function and mechanisms of spatial genome organization variation across cell types.

    more » « less
  3. Abstract Motivation

    Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet).


    We evaluated the efficacy of CFNet and G-CNN as compared to a standard CNN for several different image classification tasks, including simulated and real microscopy images of subcellular protein localization, and demonstrated improved performance. We believe CFNet has the potential to improve many high-throughput microscopy image analysis applications.

    Availability and implementation

    Source code of CFNet is available at:

    Supplementary information

    Supplementary data are available at Bioinformatics online.

    more » « less
  4. null (Ed.)