--- title: "Sergio Guadarrama — author profile and papers" description: "Sergio Guadarrama: 2 papers on Elamur Research (2014), h-index 31 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/sergio-guadarrama/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sergio-guadarrama/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Sergio Guadarrama # Sergio Guadarrama Sergio Guadarrama's papers here deal with deep learning for computer vision, and in particular with the software and model designs that make convolutional networks practical to build, share and extend. Both works date from 2014. They address two linked questions: how to make state-of-the-art visual recognition models fast to run and easy to reproduce, and how to carry convolutional image representations over to tasks that unfold in time, such as video and the generation of descriptions. The more widely cited of the two is [Caffe: Convolutional Architecture for Fast Feature Embedding](https://md.research.elamur.ai/free/en/papers/jia-2014-caffe-convolutional-architecture-fast-feature/), an open-source framework from the Berkeley vision group. Written in C++, it uses CUDA to run on GPUs and offers Python and MATLAB interfaces. Models are specified in configuration files as graphs of layers, kept apart from the code that executes them, so one network can switch between CPU and GPU with a single call. The second paper, [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://md.research.elamur.ai/free/en/papers/donahue-2014-long-term-recurrent-convolutional-networks/), joins a convolutional visual encoder to stacked LSTM layers and trains the combination end to end. Because weights are shared across time steps, the model accepts inputs and produces outputs of varying length, learning structure over both space and time. The framework is tested in several settings involving video and image description. Bylines from 2011 to 2017 place Guadarrama at the [University of California, Berkeley](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/), with a shorter link to the [International Computer Science Institute](https://md.research.elamur.ai/free/en/labs/international-computer-science-institute/) there. Papers from 2016 to 2022 list [Google](https://md.research.elamur.ai/free/en/companies/google/) in Mountain View. Co-authors on the papers here include [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/) and [Trevor Darrell](https://md.research.elamur.ai/free/en/authors/trevor-darrell/), who appear on both, along with [Kate Saenko](https://md.research.elamur.ai/free/en/authors/kate-saenko/), [Lisa Anne Hendricks](https://md.research.elamur.ai/free/en/authors/lisa-anne-hendricks/), [Marcus Rohrbach](https://md.research.elamur.ai/free/en/authors/marcus-rohrbach/) and [Ross Girshick](https://md.research.elamur.ai/free/en/authors/ross-girshick/). For readers new to this work, the Caffe paper gives the clearest picture of the tooling, and the LRCN paper shows how those convolutional models were extended to sequences. Sergio Guadarrama has 2 papers in our library, in 2014; often with [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/), [Trevor Darrell](https://md.research.elamur.ai/free/en/authors/trevor-darrell/), [Kate Saenko](https://md.research.elamur.ai/free/en/authors/kate-saenko/). 2 papers in our library · 2014 [OpenAlex](https://openalex.org/A5004083108) · [**h-index 31**](https://openalex.org/authors/A5004083108) · [94 works](https://openalex.org/works?filter=author.id:A5004083108) · [29,091 citations](https://openalex.org/works?filter=author.id:A5004083108&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/sergio-guadarrama/#papers) · [🔗 442 citations in our library](https://md.research.elamur.ai/free/en/authors/sergio-guadarrama/cited-by/) · [⭐ Paper Star rank #615](https://md.research.elamur.ai/free/en/paper-stars/page/7/#star-615) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Sergio+Guadarrama) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Sergio+Guadarrama) · [dblp](https://dblp.org/search?q=Sergio+Guadarrama) · [ACL Anthology](https://aclanthology.org/search/?q=Sergio+Guadarrama) ## Affiliations [🎓**University of California, Berkeley** Berkeley · United States 2011–2017 · 19 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-berkeley/) · [🔬**European Centre for Soft Computing** Mieres · Spain 2008–2015 · 16 papers](https://ror.org/02b1fy379) · [🎓**Universidad Politécnica de Madrid** Madrid · Spain 2002–2007 · 16 papers](https://ror.org/03n6nwv02) · [🏢**Google** Mountain View · United States 2016–2022 · 11 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🔬**International Computer Science Institute** Berkeley · United States 2013–2015 · 2 papers](https://md.research.elamur.ai/free/en/labs/international-computer-science-institute/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Works by year ### 2010s [**2014** 2 papers](https://md.research.elamur.ai/free/en/authors/sergio-guadarrama/year/2014/) ## Papers The most cited first (OpenAlex and our library). 1. **[Caffe: Convolutional Architecture for Fast Feature Embedding](https://md.research.elamur.ai/free/en/papers/jia-2014-caffe-convolutional-architecture-fast-feature/)** *(2014 · 4,064 citations)* Deep convolutional networks had become the leading approach to visual recognition, but reproducing published results could take months. 2. **[Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://md.research.elamur.ai/free/en/papers/donahue-2014-long-term-recurrent-convolutional-networks/)** *(2014 · 142 citations)* Deep CNNs had come to dominate image interpretation, but most video and description systems still relied on a fixed visual representation or simple averaging over time. ## Co-authors here 6 co-authors with a page, the most papers together first. - [Jeff Donahue](https://md.research.elamur.ai/free/en/authors/jeff-donahue/) ×2 - [Trevor Darrell](https://md.research.elamur.ai/free/en/authors/trevor-darrell/) ×2 - [Kate Saenko](https://md.research.elamur.ai/free/en/authors/kate-saenko/) - [Lisa Anne Hendricks](https://md.research.elamur.ai/free/en/authors/lisa-anne-hendricks/) - [Marcus Rohrbach](https://md.research.elamur.ai/free/en/authors/marcus-rohrbach/) - [Ross Girshick](https://md.research.elamur.ai/free/en/authors/ross-girshick/) ## Cited by Papers of our library cite their works 442 times (of the 140,884 papers whose bibliographies we read); [34 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/sergio-guadarrama/cited-by/).