Excited to share that we have just released the code for our #CVPR2020 paper "Straight to the Point: Fast-Forwarding Videos via Reinforcement Learning Using Textual Data".
Code: https://t.co/P7d33MHnDS
#verlab#dccufmg#ufmg
What does a supervisor look for in a good PhD student? As @davmoltisanti says: "perseverance and passion" ;-) You can know more about Davide's work here: https://t.co/7vDKSC3DsT
Seis trabalhos da UFMG foram agraciados com menções honrosas no Prêmio Capes de Teses 2020: https://t.co/A3MQSKwu61
Trabalhos são das áreas de ciência animal, ciência política, história, ciência da computação, física e química.
Parabéns a todos!
If you're attending #CVPR2020, feel free to join us in a live discussion and Q&A session @ 9:00 AM - 11:00 AM PDT (13:00-15:00 BRT): https://t.co/3IaIFv2AWp
We create a visual-textual embedding space for our RL agent to adaptively navigate through videos.
#verlab#dccufmg
This year VeRLab will contribute with TWO papers to CVPR 2020!
#1 - Straight to the Point: Fast-forwarding Videos via ReinforcementLearning Using Textual Data
#2 - A gaze driven fast-forward method for first-person videos
#computervision#cvpr@dcc_ufmg@ufmg
Veja mais detalhes em https://t.co/ajTU0CeGau
Laís Mota de Alencar Rocha, orientada pela Mirella Mouro.
Manoel Horta Ribeiro, orientado por Wagner Meira.
Marcos Yukio Siraichi, orientado por Fernando Pereira.
Michel Silva, orientado Erickson Rangel do Nascimento.
Nesta publicação são apresentados os recentes resultados com novos métodos capazes de combinar informações textuais (extraídas de documentos) e visuais (extraídos de vídeos). Será publicado no IEEE CVPR 2020.
Saiba mais: https://t.co/S3Y4q2bEVw
#verlab#dcc#ufmg
Nova publicação dos pesquisadores do VERLAB na IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)! O periódico com o maior fator de impacto (17.730) dentre todos os periódicos da Computer Society.
Acesse: https://t.co/eMjjn3PgVV
This is one of the results of a novel approach that will be presented this year in #cvpr2020! It takes as input a video and a text to create an accelerated video based on the semantics in the text.
More details at: https://t.co/2QE1iO9Fc3
This video is a part of the paper "Straight to the Point: Fast-Forwarding Videos via Reinforcement Learning Using Textual Data" that will be presented at #cvpr2020.
We congratulate @washingtonsk8, @michelms, @edsonroteia, Leandro Marcolino and @ericksonrn_ on the accepted work.
Check out our new #CVPR2020 paper on fast-forwarding instructional videos! This joint work with @michelms, @edsonroteia, @leandrosmarc, and @ericksonrn_ is now available at:
����https://t.co/wQuaWKJuMA
🌎https://t.co/ZLNX3kIE3u
▶ https://t.co/j7ap47SWKy
#verlab #dccufmg