M
Mrigank Rochan
Researcher at University of Manitoba
Publications - 46
Citations - 1644
Mrigank Rochan is an academic researcher from University of Manitoba. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 13, co-authored 42 publications receiving 975 citations. Previous affiliations of Mrigank Rochan include Amrita Vishwa Vidyapeetham.
Papers
More filters
Proceedings ArticleDOI
Cross-Modal Self-Attention Network for Referring Image Segmentation
TL;DR: A cross-modal self-attention (CMSA) module that effectively captures the long-range dependencies between linguistic and visual features and a gated multi-level fusion module to selectively integrateSelf-attentive cross- modal features corresponding to different levels in the image.
Proceedings ArticleDOI
Malware Classification with Deep Convolutional Neural Networks
TL;DR: A CNN-based architecture to classify malware samples is proposed that achieves better than the state-of-the-art performance on two challenging malware classification datasets, Malimg and Microsoft malware.
Proceedings ArticleDOI
Gated Feedback Refinement Network for Dense Image Labeling
TL;DR: This paper proposes Gated Feedback Refinement Network (G-FRNet), an end-to-end deep learning framework for dense labeling tasks that addresses this limitation of existing methods and introduces gate units that control the information passed forward in order to filter out ambiguity.
Book ChapterDOI
Video Summarization Using Fully Convolutional Sequence Networks
TL;DR: This paper firstly establishes a novel connection between semantic segmentation and video summarization, and then adapt popular semantic segmentsation networks for video summarizations, and proposes fully convolutional sequence models to solveVideo summarization.
Proceedings ArticleDOI
Video Summarization by Learning From Unpaired Data
Mrigank Rochan,Yang Wang +1 more
TL;DR: In this article, the authors propose an approach that learns to generate optimal video summaries using a set of raw videos (V) and summary videos (S), where there exists no correspondence between V and S. The model aims to learn a mapping function F : V -> S such that the distribution of resultant summary videos from F(V) is similar to S with the help of an adversarial objective.