Neural Architecture Search for Enhancing Action Video Recognition in Compressed Domains

Autor(es)

Lamkowski, Pedro ; Rodrigues, Douglas ; Passos, Leandro A. ; Papa, Joao P. ; Almeida, Jurandy

• Tipo de documento: Artigo Científico
• Fonte: 2024 31ST INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING, IWSSIP 2024; v. N/A, p. 7-pg., 2024-01-01.

Resumo

Video classification models have become one of the most widely used topics in the computer vision field, encompassing many tasks such as medical, security, industrial, and other applications. Although deep learning models have achieved great results in the video domain, such models are built to operate in the domain of RGB frame sequences. In such models, a prior step is required for decoding video data since the vast majority relies on compressed formats. Nevertheless, large amounts of computational resources are required for decoding, especially in real-time. Researchers have already tackled the task of building networks that work in the compressed domain with promising results but with architectures still very close to those used for the RGB domain. We propose an approach that employs Neural Architecture Search to explore and find the most effective architectures for the compressed domain. Our approach was tested on UCF101 and HMDB51 datasets, obtaining a computationally less complex architecture than similar methods. (AU)

• Processo FAPESP: 23/03726-4 - Estudo e Desenvolvimento de Algoritmos Multimétodo Multiobjetivos
• Beneficiário: Douglas Rodrigues
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 19/07665-4 - Centro de Inteligência Artificial
• Beneficiário: Fabio Gagliardi Cozman
• Modalidade de apoio: Auxílio à Pesquisa - Programa eScience e Data Science - Centros de Pesquisa em Engenharia
• Processo FAPESP: 13/07375-0 - CeMEAI - Centro de Ciências Matemáticas Aplicadas à Indústria
• Beneficiário: Francisco Louzada Neto
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs
• Processo FAPESP: 23/14427-8 - Ciência de Dados para a Indústria Inteligente (CDII)
• Beneficiário: José Alberto Cuminato
• Modalidade de apoio: Auxílio à Pesquisa - Programa Centros de Pesquisa em Engenharia