Michel M. Silva

Michel M. Silva

Assistant Professor
Researcher

  • Aug 2023 - Paper “AEvaluation of Optical Character Recognition System dealing with Misinformation in Portuguese” accepted to publication in SIBGRAPI 2023.

  • Aug 2023 - Paper “Presenter-Centric Image Collection and Annotation: Enhancing Accessibility for the Visually Impaired” accepted to publication in SIBGRAPI 2023.

  • Aug 2023 - Paper “ImageFactCk.BR: Um Repositório de Imagens para a Detecção de Desinformação Disseminada em Plataformas Digitais” accepted to publication in SBBD DSW 2023.

  • Sep 2022 - Paper “A multimodal hyperlapse method based on video and songs’ emotion alignment” accepted to publication in PRL 2022.

  • Sep 2022 - Paper “A soybean seedlings dataset for soil condition and genotype classification” accepted to publication in SIBGRAPI 2022.

  • Mar 2022 - Paper “Text-driven video acceleration: A weakly-supervised reinforcement learning method” accepted to publication in TPAMI 2022.

  • Fev 2022 - Paper “Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs” accepted to appear in VISAPP 2022 is now publicly available.

  • Nov 2021 - Paper “Describing image focused in cognitive and visual details for visually impaired people: An approach to generating inclusive paragraphs” accepted to appear in VISAPP 2022.

  • Aug 2021 - Paper “Evaluating Loss Functions for Illustration Super-Resolution Neural Networks” accepted to appear in WUW@SIBGRAPI 2021.

  • Oct 2020 - Honorable mention at the CAPES Thesis Award in the field of Computer Science.

  • Oct 2020 - Code of the paper “A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos” TPAMI 2020, is publicly available now.

  • May 2020 - Paper “A gaze driven fast-forward method for first-person videos” accepted to appear in EPIC@CVPR 2020.

  • Mar 2020 - Paper “A Sparse Sampling-based framework for Semantic Fast-Forward of First-Person Videos” accepted to publication in TPAMI 2020.

  • Feb 2020 - Paper “Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data” accepted to appear in CVPR 2020.

  • Nov 2019 - Paper “Personalizing Fast-Forward Videos Based on Visual and Textual Features from Social Network” accepted to WACV 2020.

  • Nov 2019 - Best Ph.Dd Thesis Award in the Workshop of Thesis and Dissertation (WTD) Sibgrapi 2019.

  • Oct 2019 - WTD “A Hands-on Tutorial on Fast Forwarding First-Person Videos” presented at Sibgrapi 2019 - Rio de Janeiro (Brazil).

  • Oct 2019 - Tutorial “A Hands-on Tutorial on Fast Forwarding First-Person Videos” presented at Sibgrapi 2019.

  • Oct 2019 - Started new job as Lecturer at the Department of Computer Science of Universidade Federal de Lavras (UFLA).

  • Oct 2019 - My Ph.D. Thesis is now available!

  • July 2019 - Ph.D. Thesis Defense.

  • Jan 2019 - The paper A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos is official available.

  • Set 2018 - Award on Integration Day of Post-Graduate Program in Computer Science of UFMG event DIP 2018 - category: Highlighted Doctoral Dissertation.

  • Jun 2018 - Poster presented at CVPR 2018 in Salt Lake City - Utah (USA).

  • Apr 2018 - Code of the paper A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos, CVPR 2018 is publicly available now.

  • Mar 2018 - The DoMSEV is publicly available now. This dataset was proposed in the paper A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos, CVPR 2018.

  • Mar 2018 - Code of the paper Making a long story short: A Multi-Importance fast-forwarding egocentric videos with the emphasis on relevant objects, JVCI 2018 is publicly available now.

  • Fev 2018 - Paper accepted to JVCI 2018 - Making a long story short: A Multi-Importance fast-forwarding egocentric videos with the emphasis on relevant objects.

  • Fev 2018 - Paper accepted to CVPR 2018 - A Weighted Sparse Sampling and Smoothing Frame Transition Approach for Semantic Fast-Forward First-Person Videos.

  • Oct 2017 - ArXiv Paper - Making a long story short: A Multi-Importance Semantic for Fast-Forwarding Egocentric Videos.

  • May 2016 - Paper accepted to EPIC@ECCV 2016 - Towards Semantic Fast-Forward and Stabilized Egocentric Videos.

  • April 2016 - Paper accepted to ICIP 2016 - Fast-Forward Video Based on Semantic Extraction.

News in the Press

  • Sep 2020 - List of the CAPES Thesis Award 2020 winners [Pt-br].

  • Mar 2019 - UFMG researchers create software to improve first-person videos [Pt-br].

  • Sep 2018 - DCC researchers presented papers at CVPR 2018, the premier Computer Vision conference in the world [Pt-br].