Gunnar Atli Sigurdsson

2nd year PhD Student, advised by Abhinav Gupta
Robotics Institute, School of Computer Science
Carnegie Mellon University

{myfirstname}@cmu.edu   LinkedIn Profile GitHub Page Google Scholar Profile   Semantic Scholar Profile

My research focuses on large-scale semi-supervised and unsupervised methods for understanding time information in computer vision. This includes human activities, events, and causal reasoning. I am interested in deep learning, particularly in recurrent neural networks, and augmenting those with higher-level reasoning.

Gunnar Atli

News

Hollywood in Homes / Charades

allenai.org/plato/charades/

Computer vision has a great potential to help our daily lives by searching for lost keys, watering flowers or reminding us to take a pill. To succeed with such tasks, computer vision methods need to be trained from real and diverse examples of our daily dynamic scenes. While most of such scenes are not particularly exciting, they typically do not appear on YouTube, in movies or TV broadcasts. So how do we collect sufficiently many diverse but boring samples representing our lives? We propose a novel Hollywood in Homes approach to collect such data. Instead of shooting videos in the lab, we ensure diversity by distributing and crowdsourcing the whole process of video creation from script writing to video recording and annotation. Following this procedure we collect a new dataset, Charades, with hundreds of people recording videos in their own homes, acting out casual everyday activities.

, , , , , , "Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding", In European Conference on Computer Vision, 2016. [pdf] [bibtex] [poster] [web]
, , , , , "Much Ado About Time: Exhaustive Annotation of Temporal Data", In HCOMP, 2016. [pdf] [bibtex] [web]
, , , , "Asynchronous Temporal Fields for Action Recognition", In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [pdf] [bibtex] [code]
missing

missing

Learning Visual Storylines

What does a typical visit to Paris look like? In this work, we show how to automatically learn the temporal aspects, or storylines of visual concepts from web data. Our novel Skipping Recurrent Neural Network (S-RNN) uses a framework that skips through the images in the photo stream to explore the space of all ordered subsets of the albums.

, , , "Learning Visual Storylines with Skipping Recurrent Neural Networks", In European Conference on Computer Vision, 2016. [pdf] [bibtex] [poster] [code]

Shape Analysis

Image segmentation algorithms commonly return segmentation masks that represent the shape of objects. Particularly, in the medical imaging domain, this shape incorporates information about, for example, the state of the segmented organ. By looking at the shape of an object, in two or three dimensions, it is possible to look for signs of disease.

, , , , "Interpretable exemplar-based shape classification using constrained sparse linear models", In Proc. SPIE, vol. 9413, no. , pp. 94130R-94130R-7, 2015. (Oral Presentation) [pdf] [bibtex] [doi] [slides] [code]
missing

missing missing

Diffusion MRI processing

Using modern diffusion weighted magnetic resonance imaging protocols, the orientations of multiple neuronal fiber tracts within each voxel can be estimated. Further analysis of these populations, including application of fiber tracking and tract segmentation methods, is often hindered by lack of spatial smoothness of the estimated orientations. For example, a single noisy voxel can cause a fiber tracking method to switch tracts in a simple crossing tract geometry. In this work, a generalized spatial smoothing framework that handles multiple orientations as well as their fractional contributions within each voxel is proposed.

, , "Smoothing fields of weighted collections with applications to diffusion MRI processing", In Proc. SPIE, vol. 9034, no. , pp. 90342D-90342D-7, 2014. [pdf] [bibtex] [doi] [poster] [code]

Show More

Polysomnography Analysis

The Icelandic biomedical company, Nox Medical, provides solutions for sleep monitoring and diagnostics. With portable sleep monitors, there is opportunity to measure large population of people in their own beds. From this data, we are interested in exploring relationships between underlying disease and measurements. We performed statistical analysis on various time-series from the device and looked at the discriminative power of various features for classifying events. Using regression and classification algorithms, such as neural networks, we were able to predict vibration in patients from sounds, and warrant further study of relationships with disease. Our work was incorporated in to the company's software suite, Noxturnal.

, , , , , , , , , , "How to measure snoring? A comparison of the microphone, cannula and piezoelectric sensor", In Journal of Sleep Research, 2015. [bibtex] [doi]
, , , , , , "Snoring - Validation of different objective measurements", In European Respiratory Journal, European Respiratory Society, vol. 42, no. Suppl 57, 2014. [bibtex]
missing

missing

Active Radiator

The immense popularity of wireless communications has left the common frequency bands crowded, prompting researchers to utilize available spectrum at ever higher frequencies. At mm-wave frequencies there is pronounced need for novel antenna designs that are tightly integrated with their driving circuitry in order to reduce power losses. A radiator concept for 94 GHz CMOS-technology was reviewed, scaled up, and redesigned to work at 2.4 GHz on a FR-4 printed circuit board, in the interest of testing the concept. The radiator works in similar manner to an array of dipoles, and can connect directly to the last amplifier stage without impedance matching, due to load-pull matched input impedances, accomplishing all of its power combining in the air. 3D full-wave electromagnetic field simulations were performed on all transmission line structures and furthermore, various ways to achieve symmetric power splitting and shorted transmission line stubs with coupled lines were designed and experimented with, in order to achieve acceptable efficiency and radiation pattern of the radiating array. Work with Steven Bowers and Ali Hajimiri at Caltech.

CV available on request.

, , , , "Asynchronous Temporal Fields for Action Recognition", In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [pdf] [bibtex] [code]
, , , , , "Much Ado About Time: Exhaustive Annotation of Temporal Data", In HCOMP, 2016. [pdf] [bibtex] [web]
, , , "Learning Visual Storylines with Skipping Recurrent Neural Networks", In European Conference on Computer Vision, 2016. [pdf] [bibtex] [poster] [code]
, , , , , , "Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding", In European Conference on Computer Vision, 2016. [pdf] [bibtex] [poster] [web]
, , , , "Interpretable exemplar-based shape classification using constrained sparse linear models", In Proc. SPIE, vol. 9413, no. , pp. 94130R-94130R-7, 2015. (Oral Presentation) [pdf] [bibtex] [doi] [slides] [code]
, , , , , , , , , , "How to measure snoring? A comparison of the microphone, cannula and piezoelectric sensor", In Journal of Sleep Research, 2015. [bibtex] [doi]
, , "Smoothing fields of weighted collections with applications to diffusion MRI processing", In Proc. SPIE, vol. 9034, no. , pp. 90342D-90342D-7, 2014. [pdf] [bibtex] [doi] [poster] [code]
, , , , , , "Feasibility of a non-invasive sensor for measuring ICU patient mobility", In Critical Care Medicine, vol. 42, pp. A1389, 2014. (Research Citation Award) [bibtex] [doi]
, , , , , , "Snoring - Validation of different objective measurements", In European Respiratory Journal, European Respiratory Society, vol. 42, no. Suppl 57, 2014. [bibtex]

Please see my GitHub page for released code.