Sergio Guadarrama


[CV] [Resume] [BibTex] [Google Scholar]

Since January 2015, I am working at Nest/Google.

From January 2013 until January 2015, I was a Research Scientist at the EECS Department at the University of California at Berkeley working with Prof. Lotfi Zadeh and Prof. Trevor Darrell. Currently I'm working on the Mind's Eye project which focuses on Activity Recognition in Videos in collaboration with Prof. Kate Saenko, Prof. Raymond Mooney and Prof. Trevor Darrell. I have also worked on the BOLT-E Project which focused on Grounded Language Acquisition in collaboration with Prof. Dan Klein, Prof. Pieter Abbell and Prof. Trevor Darrell.

My research interests lies at the intersection of Computer Vision, Natural Language Processing and Machine Learning and it is focused on Object and Activity Recognition in Videos and on Grounded Language Acquisition. Currently, I am working on the YouTube2Text project to automatically describe short YouTube videos using different levels of generalization and web knowledge.

Selected Publications


Long-term recurrent convolutional networks for visual recognition and description
J. Donahue, L. Hendricks, S. Guadarrama, M. Rohrbach, S. Venugopalan, K. Saenko and T. Darrell
arXiv preprint arXiv:1411.4389
[PDF] [BibTex] [More Info]


Caffe: Convolutional architecture for fast feature embedding
J. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama and T. Darrell
Proceedings of the ACM International Conference on Multimedia
[PDF] [BibTex] [More Info]


Open-vocabulary Object Retrieval
S. Guadarrama, E. Rodner, K. Saenko, N. Zhang, R. Farrell, J. Donahue and T. Darrell
Robotics: Science and Systems, 2014 (RSS-2014)
[PDF] [BibTex] [More Info]


YouTube2Text: Recognizing and Describing Arbitrary Activities Using Semantic Hierarchies and Zero-Shot Recognition
S. Guadarrama, N. Krishnamoorthy, G. Malkarnenkar, R. Mooney, T. Darrell and K. Saenko
International Conference on Computer Vision 2013, (ICCV-2013)
[PDF] [BibTex] [More Info]


Grounding Spatial Relations for Human-Robot Interaction
S. Guadarrama, L. Riano, D. Golland, D. Gohring, Y. Jia, D. Klein, P. Abbeel and T. Darrell
IEEE/RSJ International Conference on Intelligent Robots and Systems, (IROS-2013)
[PDF] [BibTex] [More Info]


Generating Natural-Language Video Descriptions Using Text-Mined Knowledge
N. Krishnamoorthy, G. Malkarnenkar, R. J. Mooney, K. Saenko and S. Guadarrama
Proceedings of the 27th AAAI Conference on Artificial Intelligence, (AAAI-2013)
[PDF] [BibTex] [More Info]