Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Victor Campos

How to Initialize your Network? Robust Initialization for WeightNorm & ResNets

Jun 05, 2019
Devansh Arpit, Victor Campos, Yoshua Bengio

  Access Paper or Ask Questions

Recurrent Neural Networks for Semantic Instance Segmentation

Sep 03, 2018
Amaia Salvador, Miriam Bellver, Victor Campos, Manel Baradad, Ferran Marques, Jordi Torres, Xavier Giro-i-Nieto

* Extended abstract of this work was presented at CVPR 2018 DeepVision Workshop 

  Access Paper or Ask Questions

Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks

Feb 05, 2018
Victor Campos, Brendan Jou, Xavier Giro-i-Nieto, Jordi Torres, Shih-Fu Chang

* Accepted as conference paper at ICLR 2018 

  Access Paper or Ask Questions

More cat than cute? Interpretable Prediction of Adjective-Noun Pairs

Aug 21, 2017
Delia Fernandez, Alejandro Woodward, Victor Campos, Xavier Giro-i-Nieto, Brendan Jou, Shih-Fu Chang

* Oral paper at ACM Multimedia 2017 Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes (MUSA2) 

  Access Paper or Ask Questions

Disentangling Motion, Foreground and Background Features in Videos

Jul 17, 2017
Xunyu Lin, Victor Campos, Xavier Giro-i-Nieto, Jordi Torres, Cristian Canton Ferrer

* Poster presented at the CVPR 2017 Workshop Brave New Ideas for Motion Representations in Videos 

  Access Paper or Ask Questions

From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction

Jan 27, 2017
Victor Campos, Brendan Jou, Xavier Giro-i-Nieto

* Accepted for publication in Image and Vision Computing. Models and source code available at 

  Access Paper or Ask Questions

Diving Deep into Sentiment: Understanding Fine-tuned CNNs for Visual Sentiment Prediction

Aug 24, 2015
Victor Campos, Amaia Salvador, Brendan Jou, Xavier Giró-i-Nieto

* Preprint of the paper accepted at the 1st Workshop on Affect and Sentiment in Multimedia (ASM), in ACM MultiMedia 2015. Brisbane, Australia 

  Access Paper or Ask Questions