H
Helena de Almeida Maia
Researcher at State University of Campinas
Publications - 19
Citations - 78
Helena de Almeida Maia is an academic researcher from State University of Campinas. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 4, co-authored 14 publications receiving 43 citations. Previous affiliations of Helena de Almeida Maia include Universidade Federal de Juiz de Fora.
Papers
More filters
Proceedings ArticleDOI
Multi-stream Convolutional Neural Networks for Action Recognition in Video Sequences Based on Adaptive Visual Rhythms
Darwin Ttito Concha,Helena de Almeida Maia,Helio Pedrini,Hemerson Tacon,André de Souza Brito,Hugo de Lima Chaves,Marcelo Bernardes Vieira +6 more
TL;DR: A multi-stream network is the architecture of choice to incorporate temporal information, since it may benefit from pre-trained deep networks for images and from handcrafted features for initialization, and its training cost is usually lower than video-based networks.
Journal ArticleDOI
Survey on Digital Video Stabilization: Concepts, Methods, and Challenges
TL;DR: A thorough review of the literature for video stabilization, organized according to a proposed taxonomy, and a formal definition for the problem is introduced, along with a brief interpretation in physical terms.
Journal Article
A video tensor self-descriptor based on variable size block matching
Helena de Almeida Maia,Ana Mara de Oliveira Figueiredo,Fabio Luiz Marinho de Oliveira,Virgínia Fernandes Mota,Marcelo Bernardes Vieira +4 more
TL;DR: A different and simple approach for video description using only block matching vectors, considering that most works on the field are based on the gradient of image intensities, which is suitable when the time response is a major application issue.
Book ChapterDOI
Human action recognition using convolutional neural networks with symmetric time extension of visual rhythms
Hemerson Tacon,André de Souza Brito,Hugo de Lima Chaves,Marcelo Bernardes Vieira,Saulo Moraes Villela,Helena de Almeida Maia,Darwin Ttito Concha,Helio Pedrini +7 more
TL;DR: This work proposes the usage of multiple Visual Rhythm crops, symmetrically extended in time and separated by a fixed stride, which provide a 2D representation of the video volume matching the fixed input size of the 2D Convolutional Neural Network employed.
Book ChapterDOI
A Video Tensor Self-descriptor Based on Block Matching
Ana Mara de Oliveira Figueiredo,Helena de Almeida Maia,Fabio Luiz Marinho de Oliveira,Virgínia Fernandes Mota,Marcelo Bernardes Vieira +4 more
TL;DR: A new motion descriptor which uses only block matching vectors to obtain orientation tensors and to generate the final descriptor, considered a self-descriptor, since it depends only on the input video.