Víctor Campos

Position	e-mail
PhD Candidate	victor.campos@bsc.es

Office	Phone
C6-E201	+34 934054282

Biography

Víctor Campos holds a BsC and a MsC degrees in Electrical Engineering from Universitat Politècnica de Catalunya. He is currently pursuing his PhD on the intersection between Deep Learning and High Performance Computing at the Barcelona Supercomputing Center, supported by Obra Social "la Caixa" through La Caixa-Severo Ochoa International Doctoral Fellowship program. During the Summer of 2016 he interned at the Deep Learning Competence Center at DFKI (NVIDIA AI Lab), under the supervision of Dr. Damian Borth. In 2017 he was a visiting researcher at Columbia University, where he worked under the supervision of Prof. Shih-Fu Chang. He interned at Salesforce Research and Deepmind in 2019 and 2020, respectively. His research interests focus on developing deep learning and reinforcement learning methods that benefit from increased compute and data.

Journal Articles top

2017
V. Campos, Jou, B., and Giró-i-Nieto, X., “From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction”, Image and Vision Computing, 2017. DOI Google Scholar BibTex (1.92 MB)

Book Chapters and Books top

2018
V. Campos, Giró-i-Nieto, X., Jou, B., Torres, J., and Chang, S. - F., “Sentiment concept embedding for visual affect recognition”, in Multimodal Behavior Analysis in theWild, 1st ed., Elsevier, 2018. Google Scholar BibTex

Conference Papers top

2020
V. Campos, Trott, A., Xiong, C., Socher, R., Giró-i-Nieto, X., and Torres, J., “Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills”, in International Conference on Machine Learning (ICML) 2020, 2020. Google Scholar BibTex (6.89 MB)

2018
A. Salvador, Bellver, M., Baradad, M., Campos, V., Marqués, F., Torres, J., and Giró-i-Nieto, X., “Recurrent Neural Networks for Semantic Instance Segmentation”, in ECCV 2018 Women in Computer Vision (WiCV) Workshop, 2018. Google Scholar BibTex (2.55 MB)
V. Campos, Jou, B., Giró-i-Nieto, X., Torres, J., and Chang, S. - F., “Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks”, in International Conference on Learning Representations (ICLR), 2018. Google Scholar BibTex
D. Fojo, Campos, V., and Giró-i-Nieto, X., “Comparing Fixed and Adaptive Computation Time for Recurrent Neural Network”, in International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018. Google Scholar BibTex (515.54 KB)
A. Salvador, Bellver, M., Baradad, M., Campos, V., Marqués, F., Torres, J., and Giró-i-Nieto, X., “Recurrent Neural Networks for Semantic Instance Segmentation”, in CVPR 2018 DeepVision Workshop, 2018. Google Scholar BibTex (199.14 KB)

see all

Theses top

2020
V. Campos, “Deep Learning that Scales: Leveraging Compute and Data”, Universitat Politècnica de Catalunya, Barcelona, Catalonia, 2020. Google Scholar BibTex (8.55 MB)

Other top

2021
J. José Nieto, “Discovery and Learning of Navigation Goals from Pixels in Minecraft”. 2021. Google Scholar BibTex (16.15 MB)	Ms Thesis

2018
C. Arenas, “Video Understanding through the Disentanglement of Appearance and Motion”. 2018. Google Scholar BibTex (1.06 MB)	Ms Thesis
D. Fojo, “Reproducing and Analyzing Adaptive Computation Time in PyTorch and TensorFlow”. 2018. Google Scholar BibTex (1.41 MB)	Ms Thesis

2017
V. Campos, “Learning to Skip State Updates in Recurrent Neural Networks”. 2017. Google Scholar BibTex (961.49 KB)	Ms Thesis

2016
D. Fernàndez, Campos, V., Jou, B., Giró-i-Nieto, X., and Chang, S. - F., “Is a “happy dog” more “happy” than “dog”? - Adjective and Noun Contributions for Adjective-Noun Pair prediction”, NIPS Women in Machine Learning Workshop. Barcelona, 2016. Google Scholar BibTex (3.11 MB)	Unpublished