FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386766769> ?p ?o ?g. }

• W4386766769 endingPage "101665" @default.
• W4386766769 startingPage "101644" @default.
• W4386766769 abstract "Anomaly detection for video surveillance gains more attention as the number of deployed cameras constantly increases while the state-of-the-art (SOTA) machine learning methods push the detection performance to its limit. Low complexity methods are relatively straightforward to train (low variance) but suffer from high bias (low performance) whereas, the complex ones can achieve high performance (low bias) with a large sample size to suppress the high variance of estimated parameters. Also, most of the SOTA methods can only detect indigenous anomalies that are spatially stationary, failing at detecting the locational anomalies that are due to nonstationary spatial statistics. To solve these issues, we propose an ensemble technique based on a context tree that generates a hierarchical ensemble of image plane partitions, which we call context tree based anomaly detection (CTBAD). With CTBAD, partitions yield anomaly detection models of varying complexities, i.e., from coarse to fine details in partitioning with each partition model (which can be any SOTA method) trained separately to allow the detection of locational anomalies, and then we combine them linearly in a weighted manner to achieve a gradual transition from simpler models to more complex ones as more data become available in a video stream. As a result, CTBAD benefits from low variance of low complexity methods when the data is sparse and exploits high complexity to achieve low bias when sufficient data is observed. Our experiments show that we significantly reduce the number of training samples to reach the same accuracy of a complex model while successfully detecting the locational anomalies." @default.
• W4386766769 created "2023-09-16" @default.
• W4386766769 creator A5010366535 @default.
• W4386766769 creator A5035853332 @default.
• W4386766769 creator A5092706501 @default.
• W4386766769 date "2023-01-01" @default.
• W4386766769 modified "2023-09-27" @default.
• W4386766769 title "A Hierarchical Approach for Improved Anomaly Detection in Video Surveillance" @default.
• W4386766769 cites W1530699444 @default.
• W4386766769 cites W1987034518 @default.
• W4386766769 cites W2025025927 @default.
• W4386766769 cites W2064675550 @default.
• W4386766769 cites W2089497633 @default.
• W4386766769 cites W2097363716 @default.
• W4386766769 cites W2122646361 @default.
• W4386766769 cites W2136655611 @default.
• W4386766769 cites W2155817051 @default.
• W4386766769 cites W2163294786 @default.
• W4386766769 cites W2163612318 @default.
• W4386766769 cites W2194775991 @default.
• W4386766769 cites W2295124130 @default.
• W4386766769 cites W2340896621 @default.
• W4386766769 cites W2341058432 @default.
• W4386766769 cites W2560474170 @default.
• W4386766769 cites W2579718262 @default.
• W4386766769 cites W2594447095 @default.
• W4386766769 cites W2599354622 @default.
• W4386766769 cites W2608862709 @default.
• W4386766769 cites W2618530766 @default.
• W4386766769 cites W2622370560 @default.
• W4386766769 cites W2748846029 @default.
• W4386766769 cites W2753526808 @default.
• W4386766769 cites W2777342313 @default.
• W4386766769 cites W2807955733 @default.
• W4386766769 cites W2808771744 @default.
• W4386766769 cites W2889431799 @default.
• W4386766769 cites W2914570111 @default.
• W4386766769 cites W2949500778 @default.
• W4386766769 cites W2960737790 @default.
• W4386766769 cites W2962791923 @default.
• W4386766769 cites W2962852342 @default.
• W4386766769 cites W2963037989 @default.
• W4386766769 cites W2963061824 @default.
• W4386766769 cites W2963167376 @default.
• W4386766769 cites W2963240734 @default.
• W4386766769 cites W2963541464 @default.
• W4386766769 cites W2963610939 @default.
• W4386766769 cites W2963899855 @default.
• W4386766769 cites W2964232409 @default.
• W4386766769 cites W2965383240 @default.
• W4386766769 cites W2966661 @default.
• W4386766769 cites W3011248632 @default.
• W4386766769 cites W3015608037 @default.
• W4386766769 cites W3034314048 @default.
• W4386766769 cites W3035699237 @default.
• W4386766769 cites W3035802502 @default.
• W4386766769 cites W3042642865 @default.
• W4386766769 cites W3045608583 @default.
• W4386766769 cites W3081188215 @default.
• W4386766769 cites W3127213927 @default.
• W4386766769 cites W3135550350 @default.
• W4386766769 cites W3137503405 @default.
• W4386766769 cites W3160958489 @default.
• W4386766769 cites W3168984673 @default.
• W4386766769 cites W3169077988 @default.
• W4386766769 cites W3190318906 @default.
• W4386766769 cites W3209793239 @default.
• W4386766769 cites W4210954769 @default.
• W4386766769 cites W4221140561 @default.
• W4386766769 cites W4239510810 @default.
• W4386766769 cites W4253461361 @default.
• W4386766769 cites W4281478450 @default.
• W4386766769 cites W4290854015 @default.
• W4386766769 cites W4292828584 @default.
• W4386766769 cites W4313442814 @default.
• W4386766769 cites W4385800770 @default.
• W4386766769 cites W4386076578 @default.
• W4386766769 cites W67460294 @default.
• W4386766769 doi "https://doi.org/10.1109/access.2023.3315739" @default.
• W4386766769 hasPublicationYear "2023" @default.
• W4386766769 type Work @default.
• W4386766769 citedByCount "0" @default.
• W4386766769 crossrefType "journal-article" @default.
• W4386766769 hasAuthorship W4386766769A5010366535 @default.
• W4386766769 hasAuthorship W4386766769A5035853332 @default.
• W4386766769 hasAuthorship W4386766769A5092706501 @default.
• W4386766769 hasBestOaLocation W43867667691 @default.
• W4386766769 hasConcept C113174947 @default.
• W4386766769 hasConcept C114614502 @default.
• W4386766769 hasConcept C119857082 @default.
• W4386766769 hasConcept C121955636 @default.
• W4386766769 hasConcept C124101348 @default.
• W4386766769 hasConcept C134306372 @default.
• W4386766769 hasConcept C144133560 @default.
• W4386766769 hasConcept C151730666 @default.
• W4386766769 hasConcept C153180895 @default.
• W4386766769 hasConcept C154945302 @default.
• W4386766769 hasConcept C165696696 @default.

• next