Human Action Recognition in Videos

• Grant number: 17/09160-1
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: August 01, 2017
• End date: February 29, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Agreement: Coordination of Improvement of Higher Education Personnel (CAPES)
• Principal Investigator: Hélio Pedrini
• Grantee: Helena de Almeida Maia
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 14/12236-1 - AnImaLS: Annotation of Images in Large Scale: what can machines and specialists learn from interaction?, AP.TEM

Abstract

The purpose of this document is to present our doctoral thesis proposal for detecting and identifying human actions in video sequences based on the combination of computer vision, image processing and machine learning techniques. The problem of human action recognition can be applied to a large variety of tasks, such as surveillance systems, intelligent homes, health monitoring, and human-computer interaction. Several conditions may hamper the recognition process, making it a challenging problem. In this research plan, we present some insights into the topic under investigation, a brief review of relevant approaches available in the literature, justifications for the need to further study, as well as strategies for a novel methodology to address the problem. (AU)

Scientific publications

(7)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

CONCHA, DARWIN TTITO; MAIA, HELENA DE ALMEIDA; PEDRINI, HELIO; TACON, HEMERSON; BRITO, ANDRE DE SOUZA; CHAVES, HUGO DE LIMA; VIEIRA, MARCELO BERNARDES; WANI, MA; KANTARDZIC, M; SAYEDMOUCHAWEH, M; et al. Multi-Stream Convolutional Neural Networks for Action Recognition in Video Sequences Based on Adaptive Visual Rhythms. 2018 17TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), v. N/A, p. 8-pg., 2018-01-01. (17/09160-1, 17/12646-3)

TACON, HEMERSON; BRITO, ANDRE S.; CHAVES, HUGO L.; VIEIRA, MARCELO BERNARDES; VILLELA, SAULO MORAES; MAIA, HELENA DE ALMEIDA; CONCHA, DARWIN TTITO; PEDRINI, HELIO; MISRA, S; GERVASI, O; et al. Human Action Recognition Using Convolutional Neural Networks with Symmetric Time Extension of Visual Rhythms. COMPUTATIONAL SCIENCE AND ITS APPLICATIONS - ICCSA 2019, PT I, v. 11619, p. 16-pg., 2019-01-01. (17/09160-1, 17/12646-3)

CHAVES, HUGO DE LIMA; RIBEIRO, KEVYN SWHANTS; BRITO, ANDRE DE SOUZA; TACON, HEMERSON; VIEIRA, MARCELO BERNARDES; CERQUEIRA, AUGUSTO SANTIAGO; VILLELA, SAULO MORAES; MAIA, HELENA DE ALMEIDA; CONCHA, DARWIN TTITO; PEDRINI, HELIO; et al. Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos. VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, v. N/A, p. 10-pg., 2020-01-01. (17/09160-1, 17/12646-3)

BRITO, ANDRE DE SOUZA; VIEIRA, MARCELO BERNARDES; VILLELA, SAULO MORAES; TACON, HEMERSON; CHAVES, HUGO DE LIMA; MAIA, HELENA DE ALMEIDA; CONCHA, DARWIN TTITO; PEDRINI, HELIO. Weighted voting of multi-stream convolutional neural networks for video-based action recognition using optical flow rhythms. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, v. 77, MAY 2021. (17/09160-1, 17/12646-3)

ROBERTO E SOUZA, MARCOS; MAIA, HELENA DE ALMEIDA; VIEIRA, MARCELO BERNARDES; PEDRINI, HELIO. Survey on visual rhythms: A spatio-temporal representation for video sequences. Neurocomputing, v. 402, p. 409-422, AUG 18 2020. (17/12646-3, 17/09160-1)

SOUSA E SANTOS, ANDERSON CARLOS; MAIA, HELENA DE ALMEIDA; ROBERTO E SOUZA, MARCOS; VIEIRA, MARCELO BERNARDES; PEDRINI, HELIO; FARINELLA, GM; RADEVA, P; BRAZ, J. Fuzzy Fusion for Two-stream Action Recognition. VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, v. N/A, p. 7-pg., 2020-01-01. (17/12646-3, 17/09160-1)

TACON, HEMERSON; BRITO, ANDRE DE SOUZA; CHAVES, HUGO DE LIMA; VIEIRA, MARCELO BERNARDES; VILLELA, SAULO MORAES; MAIA, HELENA DE ALMEIDA; CONCHA, DARWIN TTITO; PEDRINI, HELIO; FARINELLA, GM; RADEVA, P; et al. Multi-stream Architecture with Symmetric Extended Visual Rhythms for Deep Learning Human Action Recognition. VISAPP: PROCEEDINGS OF THE 15TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS, VOL 4: VISAPP, v. N/A, p. 8-pg., 2020-01-01. (17/12646-3, 17/09160-1)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

MAIA, Helena de Almeida. Redes neurais convolucionais baseadas em ritmos visuais e fusão adaptativa para uma arquitetura de múltiplos canais aplicada ao reconhecimento de ações humanas. 2020. Doctoral Thesis - Universidade Estadual de Campinas (UNICAMP). Instituto de Computação Campinas, SP.