FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3160469062> ?p ?o ?g. }

• W3160469062 abstract "Detecting tiny objects in a high-resolution video is challenging because the visual information is little and unreliable. Specifically, the challenge includes very low resolution of the objects, MPEG artifacts due to compression and a large searching area with many hard negatives. Tracking is equally difficult because of the unreliable appearance, and the unreliable motion estimation. Luckily, we found that by combining this two challenging tasks together, there will be mutual benefits. Following the idea, in this paper, we present a neural network model called the Recurrent Correlational Network, where detection and tracking are jointly performed over a multi-frame representation learned through a single, trainable, and end-to-end network. The framework exploits a convolutional long short-term memory network for learning informative appearance changes for detection, while the learned representation is shared in tracking for enhancing its performance. In experiments with datasets containing images of scenes with small flying objects, such as birds and unmanned aerial vehicles, the proposed method yielded consistent improvements in detection performance over deep single-frame detectors and existing motion-based detectors. Furthermore, our network performs as well as state-of-the-art generic object trackers when it was evaluated as a tracker on a bird image dataset." @default.
• W3160469062 created "2021-05-24" @default.
• W3160469062 creator A5003277535 @default.
• W3160469062 creator A5006134569 @default.
• W3160469062 creator A5026866776 @default.
• W3160469062 creator A5062487802 @default.
• W3160469062 creator A5067212480 @default.
• W3160469062 creator A5069342829 @default.
• W3160469062 date "2021-05-17" @default.
• W3160469062 modified "2023-10-18" @default.
• W3160469062 title "Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approach" @default.
• W3160469062 cites W1475617732 @default.
• W3160469062 cites W1485009520 @default.
• W3160469062 cites W1514535095 @default.
• W3160469062 cites W1536680647 @default.
• W3160469062 cites W1797109199 @default.
• W3160469062 cites W182571476 @default.
• W3160469062 cites W1847088711 @default.
• W3160469062 cites W1857884451 @default.
• W3160469062 cites W1947481528 @default.
• W3160469062 cites W1964846093 @default.
• W3160469062 cites W1971129545 @default.
• W3160469062 cites W1976818984 @default.
• W3160469062 cites W1994081853 @default.
• W3160469062 cites W1997121481 @default.
• W3160469062 cites W2016053056 @default.
• W3160469062 cites W2016589492 @default.
• W3160469062 cites W2031454541 @default.
• W3160469062 cites W2031489346 @default.
• W3160469062 cites W2064675550 @default.
• W3160469062 cites W2081222853 @default.
• W3160469062 cites W2096343094 @default.
• W3160469062 cites W2102605133 @default.
• W3160469062 cites W2103876808 @default.
• W3160469062 cites W2117539524 @default.
• W3160469062 cites W2117687030 @default.
• W3160469062 cites W2118877769 @default.
• W3160469062 cites W2122469558 @default.
• W3160469062 cites W2125556102 @default.
• W3160469062 cites W2130293653 @default.
• W3160469062 cites W2155893237 @default.
• W3160469062 cites W2161969291 @default.
• W3160469062 cites W2163605009 @default.
• W3160469062 cites W2194775991 @default.
• W3160469062 cites W2204302769 @default.
• W3160469062 cites W2336589871 @default.
• W3160469062 cites W2346349911 @default.
• W3160469062 cites W2407521645 @default.
• W3160469062 cites W24089286 @default.
• W3160469062 cites W2419501904 @default.
• W3160469062 cites W2470394683 @default.
• W3160469062 cites W2511671220 @default.
• W3160469062 cites W2520477759 @default.
• W3160469062 cites W2552900565 @default.
• W3160469062 cites W2560474170 @default.
• W3160469062 cites W2570343428 @default.
• W3160469062 cites W2576085163 @default.
• W3160469062 cites W2579152745 @default.
• W3160469062 cites W2594258618 @default.
• W3160469062 cites W2613599172 @default.
• W3160469062 cites W2614241281 @default.
• W3160469062 cites W2617855130 @default.
• W3160469062 cites W2625219738 @default.
• W3160469062 cites W2740668812 @default.
• W3160469062 cites W2743905801 @default.
• W3160469062 cites W2751023760 @default.
• W3160469062 cites W2765393545 @default.
• W3160469062 cites W2766881959 @default.
• W3160469062 cites W2895451584 @default.
• W3160469062 cites W2951527505 @default.
• W3160469062 cites W2962778460 @default.
• W3160469062 cites W2962824803 @default.
• W3160469062 cites W2962835968 @default.
• W3160469062 cites W2962855257 @default.
• W3160469062 cites W2962858109 @default.
• W3160469062 cites W2962889061 @default.
• W3160469062 cites W2963063317 @default.
• W3160469062 cites W2963121817 @default.
• W3160469062 cites W2963246338 @default.
• W3160469062 cites W2963954913 @default.
• W3160469062 cites W2963998989 @default.
• W3160469062 cites W2964052344 @default.
• W3160469062 cites W2964253307 @default.
• W3160469062 cites W2964308564 @default.
• W3160469062 cites W3100935401 @default.
• W3160469062 cites W3106250896 @default.
• W3160469062 cites W639708223 @default.
• W3160469062 cites W764651262 @default.
• W3160469062 doi "https://doi.org/10.48550/arxiv.2105.08253" @default.
• W3160469062 hasPublicationYear "2021" @default.
• W3160469062 type Work @default.
• W3160469062 sameAs 3160469062 @default.
• W3160469062 citedByCount "0" @default.
• W3160469062 crossrefType "posted-content" @default.
• W3160469062 hasAuthorship W3160469062A5003277535 @default.
• W3160469062 hasAuthorship W3160469062A5006134569 @default.
• W3160469062 hasAuthorship W3160469062A5026866776 @default.
• W3160469062 hasAuthorship W3160469062A5062487802 @default.
• W3160469062 hasAuthorship W3160469062A5067212480 @default.
• W3160469062 hasAuthorship W3160469062A5069342829 @default.

• next