Chris Russell

Chris Russell

Auto-generated profile, based on publicly available information

Chris Russell

University of Oxford, Oxford, United Kingdom

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2019
Verified
Conference Paper
Open access
BMBrent Mittelstadt
Brent Mittelstadt
CRChris Russell
Chris Russell
SWSandra Wachter
Sandra Wachter

1 July 2017
Verified
Conference Paper
Closed access
DTDenis Tome
Denis Tome
CRChris Russell
Chris Russell
LALourdes Agapito
Lourdes Agapito
We propose a unified formulation for the problem of 3D human pose estimation from a single raw RGB image that reasons jointly about 2D joint estimation and 3D pose reconstruction to improve both tasks. We take an integrated approach that fuses probabilistic knowledge of 3D human pose with a multi-stage CNN architecture and uses the knowledge of plausible 3D landmark locations to refine the search for better 2D locations. The entire process is trained end-to-end, is extremely efficient and obtains state-of-the-art results on Human3.6M outperforming previous approaches both on 2D and 3D errors.

1 September 2009
Verified
Conference Paper
Closed access
LLL'UBor Ladicky
L'UBor Ladicky
CRChris Russell
Chris Russell
PKPushmeet Kohli
Pushmeet Kohli
PTPhilip H.S. Torr
Philip H.S. Torr
Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It is well known that each quantisation has its fair share of pros and cons; and the existence of a common optimal quantisation level suitable for all object categories is highly unlikely. Motivated by this observation, we propose a hierarchical random field model, that allows integration of features computed at different levels of the quantisation hierarchy. MAP inference in this model can be performed efficiently using powerful graph cut based move making algorithms. Our framework generalises much of the previous work based on pixels or segments. We evaluate its efficiency on some of the most challenging data-sets for object class segmentation, and show it obtains state-of-the-art results.

26 August 2021 in Nature Communications
Verified
Journal Article
Open access
PDF file
TATom R. Andersson
Tom R. Andersson
JHJ. Scott Hosking
J. Scott Hosking
MPMaría Pérez-Ortiz
María Pérez-Ortiz
BPBrooks Paige
Brooks Paige
AEAndrew Elliott
Andrew Elliott
ESEmily Shuckburgh
Emily Shuckburgh
Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that IceNet advances the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model in seasonal forecasts of summer sea ice, particularly for extreme sea ice events. This step-change in sea ice forecasting ability brings us closer to conservation tools that mitigate risks associated with rapid sea ice loss.

29 January 2019
Verified
Conference Paper
Open access
CRChris Russell
Chris Russell

9 September 2019 in ACM Transactions on Intelligent Systems and Technology
Verified
Journal Article
Open access
PDF file
Stephen LawStephen Law
Stephen Law
BPBrooks Paige
Brooks Paige
CRChris Russell
Chris Russell
When an individual purchases a home, they simultaneously purchase its structural features, its accessibility to work, and the neighborhood amenities. Some amenities, such as air quality, are measurable while others, such as the prestige or the visual impression of a neighborhood, are difficult to quantify. Despite the well-known impacts intangible housing features have on house prices, limited attention has been given to systematically quantifying these difficult to measure amenities. Two issues have led to this neglect. Not only do few quantitative methods exist that can measure the urban environment, but that the collection of such data is both costly and subjective. We show that street image and satellite image data can capture these urban qualities and improve the estimation of house prices. We propose a pipeline that uses a deep neural network model to automatically extract visual features from images to estimate house prices in London, UK. We make use of traditional housing features such as age, size, and accessibility as well as visual features from Google Street View images and Bing aerial images in estimating the house price model. We find encouraging results where learning to characterize the urban quality of a neighborhood improves house price prediction, even when generalizing to previously unseen London boroughs. We explore the use of non-linear vs. linear methods to fuse these cues with conventional models of house pricing, and show how the interpretability of linear models allows us to directly extract proxy variables for visual desirability of neighborhoods that are both of interest in their own right, and could be used as inputs to other econometric methods. This is particularly valuable as once the network has been trained with the training data, it can be applied elsewhere, allowing us to generate vivid dense maps of the visual appeal of London streets.