FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913508739> ?p ?o ?g. }

• W2913508739 endingPage "4290" @default.
• W2913508739 startingPage "4272" @default.
• W2913508739 abstract "What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step improve image interpretability for manual analysis or automatic visual recognition to classify scene content? While there have been important advances in the area of computational photography to restore or enhance the visual quality of an image, the capabilities of such techniques have not always translated in a useful way to visual recognition tasks. Consequently, there is a pressing need for the development of algorithms that are designed for the joint problem of improving visual appearance and recognition, which will be an enabling factor for the deployment of visual recognition tools in many real-world scenarios. To address this, we introduce the UG 2 dataset as a large-scale benchmark composed of video imagery captured under challenging conditions, and two enhancement tasks designed to test algorithmic impact on visual quality and automatic object recognition. Furthermore, we propose a set of metrics to evaluate the joint improvement of such tasks as well as individual algorithmic advances, including a novel psychophysics-based evaluation regime for human assessment and a realistic set of quantitative measures for object recognition performance. We introduce six new algorithms for image restoration or enhancement, which were created as part of the IARPA sponsored UG 2 Challenge workshop held at CVPR 2018. Under the proposed evaluation regime, we present an in-depth analysis of these algorithms and a host of deep learning-based and classic baseline approaches. From the observed results, it is evident that we are in the early days of building a bridge between computational photography and visual recognition, leaving many opportunities for innovation in this area." @default.
• W2913508739 created "2019-02-21" @default.
• W2913508739 creator A5001027385 @default.
• W2913508739 creator A5001608357 @default.
• W2913508739 creator A5002310440 @default.
• W2913508739 creator A5003527952 @default.
• W2913508739 creator A5009942900 @default.
• W2913508739 creator A5020446610 @default.
• W2913508739 creator A5025253635 @default.
• W2913508739 creator A5029597925 @default.
• W2913508739 creator A5030330008 @default.
• W2913508739 creator A5030528659 @default.
• W2913508739 creator A5031665162 @default.
• W2913508739 creator A5035577534 @default.
• W2913508739 creator A5035994035 @default.
• W2913508739 creator A5037179146 @default.
• W2913508739 creator A5042260417 @default.
• W2913508739 creator A5048522863 @default.
• W2913508739 creator A5049429852 @default.
• W2913508739 creator A5070884682 @default.
• W2913508739 creator A5082583182 @default.
• W2913508739 creator A5083414352 @default.
• W2913508739 creator A5087570320 @default.
• W2913508739 creator A5088727418 @default.
• W2913508739 creator A5091336946 @default.
• W2913508739 creator A5091513740 @default.
• W2913508739 date "2021-12-01" @default.
• W2913508739 modified "2023-10-11" @default.
• W2913508739 title "Bridging the Gap Between Computational Photography and Visual Recognition" @default.
• W2913508739 cites W128019999 @default.
• W2913508739 cites W1506491340 @default.
• W2913508739 cites W1547418092 @default.
• W2913508739 cites W1677182931 @default.
• W2913508739 cites W1930824406 @default.
• W2913508739 cites W1976416062 @default.
• W2913508739 cites W1976730913 @default.
• W2913508739 cites W1984043993 @default.
• W2913508739 cites W1988974846 @default.
• W2913508739 cites W2001412060 @default.
• W2913508739 cites W2021347102 @default.
• W2913508739 cites W2027231794 @default.
• W2913508739 cites W2028990532 @default.
• W2913508739 cites W2036682493 @default.
• W2913508739 cites W2037133587 @default.
• W2913508739 cites W2042015300 @default.
• W2913508739 cites W2044972040 @default.
• W2913508739 cites W2047920195 @default.
• W2913508739 cites W2055492845 @default.
• W2913508739 cites W2056370875 @default.
• W2913508739 cites W2080211902 @default.
• W2913508739 cites W2083609718 @default.
• W2913508739 cites W2097074225 @default.
• W2913508739 cites W2105191529 @default.
• W2913508739 cites W2108729907 @default.
• W2913508739 cites W2110644821 @default.
• W2913508739 cites W2113569611 @default.
• W2913508739 cites W2114380981 @default.
• W2913508739 cites W2114867966 @default.
• W2913508739 cites W2117539524 @default.
• W2913508739 cites W2121058967 @default.
• W2913508739 cites W2122086266 @default.
• W2913508739 cites W2128254161 @default.
• W2913508739 cites W2129680231 @default.
• W2913508739 cites W2134542730 @default.
• W2913508739 cites W2134574492 @default.
• W2913508739 cites W2135065661 @default.
• W2913508739 cites W2138204001 @default.
• W2913508739 cites W2141020570 @default.
• W2913508739 cites W2141200610 @default.
• W2913508739 cites W2142180098 @default.
• W2913508739 cites W2142683286 @default.
• W2913508739 cites W2142996775 @default.
• W2913508739 cites W2145287260 @default.
• W2913508739 cites W2150081556 @default.
• W2913508739 cites W2157494358 @default.
• W2913508739 cites W2158407119 @default.
• W2913508739 cites W2161907179 @default.
• W2913508739 cites W2167053624 @default.
• W2913508739 cites W2169574628 @default.
• W2913508739 cites W2183341477 @default.
• W2913508739 cites W2194775991 @default.
• W2913508739 cites W2242218935 @default.
• W2913508739 cites W2293078015 @default.
• W2913508739 cites W2319561215 @default.
• W2913508739 cites W2326925005 @default.
• W2913508739 cites W2440438634 @default.
• W2913508739 cites W2474628748 @default.
• W2913508739 cites W2503458650 @default.
• W2913508739 cites W2518876086 @default.
• W2913508739 cites W2519586580 @default.
• W2913508739 cites W2519597608 @default.
• W2913508739 cites W2536722097 @default.
• W2913508739 cites W2552164092 @default.
• W2913508739 cites W2553668389 @default.
• W2913508739 cites W2560533888 @default.
• W2913508739 cites W2593414223 @default.
• W2913508739 cites W2604885021 @default.
• W2913508739 cites W2608583225 @default.

• next