Título: Deep Image Features for Instance-level Recognition and Matching
Por: André Araujo
Quando: 03 de junho, 11h.
Onde: Sala 2077 do ICEx
Resumo: In this talk, I will discuss recent work from our team at Google Research, covering novel methods and datasets. Instance-level recognition, retrieval and matching are key computer vision problems which generally depend on effective image representations, both global and local. Our team has proposed a suite of state-of-the-art models to address these tasks: DELF (ICCV’17), one of the first deep learning methods for joint detection & description of local image features; Detect-to-Retrieve (CVPR’19), where deep local features can be efficiently aggregated guided by a trained object detector; DELG (ECCV’20), the first end-to-end trained deep model for joint local and global feature extraction. I will also present our team’s efforts on pushing for larger scale and more realistic benchmarks in this area, with the Google Landmarks Dataset (CVPR’20), and recent workshops at computer vision conferences (CVPR/ECCV/ICCV since 2018).
Bio: André Araujo é atualmente Staff Software Engineer / Tech Lead Manager na Google Research, baseado no escritório de Belo Horizonte. André obteve doutorado em engenharia elétrica na Universidade de Stanford em 2016. Seus interesses de pesquisa atuais são principalmente em visão computacional, mais especificamente em “instance-level recognition”, como recentes trabalhos em representações locais e globais de imagens. André tem servido como organizador principal de workshops na área de instance-level recognition desde 2018 nas principais conferências da área, além de também servir regularmente como revisor, e mais recentemente como “area chair”.
