Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361275746> ?p ?o ?g. }
- W4361275746 endingPage "1618" @default.
- W4361275746 startingPage "1618" @default.
- W4361275746 abstract "Video saliency object detection is one of the classic research problems in computer vision, yet existing works rarely focus on the impact of input quality on model performance. As optical flow is a key input for video saliency detection models, its quality significantly affects model performance. Traditional optical flow models only calculate the optical flow between two consecutive video frames, ignoring the motion state of objects over a period of time, leading to low-quality optical flow and reduced performance of video saliency object detection models. Therefore, this paper proposes a new optical flow model that improves the quality of optical flow by expanding the flow perception range and uses high-quality optical flow to enhance the performance of video saliency object detection models. Experimental results on the datasets show that the proposed optical flow model can significantly improve optical flow quality, with the S-M values on the DAVSOD dataset increasing by about 39%, 49%, and 44% compared to optical flow models such as PWCNet, SpyNet, and LFNet. In addition, experiments that fine-tuning the benchmark model LIMS demonstrate that improving input quality can further improve model performance." @default.
- W4361275746 created "2023-03-31" @default.
- W4361275746 creator A5016806784 @default.
- W4361275746 creator A5030724247 @default.
- W4361275746 creator A5052577152 @default.
- W4361275746 creator A5054958308 @default.
- W4361275746 date "2023-03-30" @default.
- W4361275746 modified "2023-09-25" @default.
- W4361275746 title "Video Saliency Object Detection with Motion Quality Compensation" @default.
- W4361275746 cites W1904063580 @default.
- W4361275746 cites W1951289974 @default.
- W4361275746 cites W1969226866 @default.
- W4361275746 cites W1982075130 @default.
- W4361275746 cites W1990881985 @default.
- W4361275746 cites W2042933440 @default.
- W4361275746 cites W2100470808 @default.
- W4361275746 cites W2110019070 @default.
- W4361275746 cites W2138682569 @default.
- W4361275746 cites W2176137647 @default.
- W4361275746 cites W2183706426 @default.
- W4361275746 cites W2221502561 @default.
- W4361275746 cites W2470139095 @default.
- W4361275746 cites W2547489168 @default.
- W4361275746 cites W2548527721 @default.
- W4361275746 cites W2588503511 @default.
- W4361275746 cites W2768270796 @default.
- W4361275746 cites W2793668851 @default.
- W4361275746 cites W2803472033 @default.
- W4361275746 cites W2885976210 @default.
- W4361275746 cites W2943978556 @default.
- W4361275746 cites W2963112696 @default.
- W4361275746 cites W2963782415 @default.
- W4361275746 cites W2963868681 @default.
- W4361275746 cites W2964156315 @default.
- W4361275746 cites W2965638232 @default.
- W4361275746 cites W2968393007 @default.
- W4361275746 cites W2969626490 @default.
- W4361275746 cites W2973058802 @default.
- W4361275746 cites W2996803365 @default.
- W4361275746 cites W2997217064 @default.
- W4361275746 cites W3025800305 @default.
- W4361275746 cites W3049318984 @default.
- W4361275746 cites W3097848036 @default.
- W4361275746 cites W3141316140 @default.
- W4361275746 cites W3177085432 @default.
- W4361275746 cites W3180447501 @default.
- W4361275746 cites W3203058509 @default.
- W4361275746 cites W3204643350 @default.
- W4361275746 cites W3215023725 @default.
- W4361275746 cites W3216044769 @default.
- W4361275746 cites W4206294875 @default.
- W4361275746 cites W4239147634 @default.
- W4361275746 cites W4283317841 @default.
- W4361275746 cites W4309460928 @default.
- W4361275746 cites W4312205422 @default.
- W4361275746 cites W4312636847 @default.
- W4361275746 cites W4313496334 @default.
- W4361275746 cites W4318482805 @default.
- W4361275746 cites W764651262 @default.
- W4361275746 doi "https://doi.org/10.3390/electronics12071618" @default.
- W4361275746 hasPublicationYear "2023" @default.
- W4361275746 type Work @default.
- W4361275746 citedByCount "0" @default.
- W4361275746 crossrefType "journal-article" @default.
- W4361275746 hasAuthorship W4361275746A5016806784 @default.
- W4361275746 hasAuthorship W4361275746A5030724247 @default.
- W4361275746 hasAuthorship W4361275746A5052577152 @default.
- W4361275746 hasAuthorship W4361275746A5054958308 @default.
- W4361275746 hasBestOaLocation W43612757461 @default.
- W4361275746 hasConcept C103910844 @default.
- W4361275746 hasConcept C11171543 @default.
- W4361275746 hasConcept C114227958 @default.
- W4361275746 hasConcept C115961682 @default.
- W4361275746 hasConcept C121332964 @default.
- W4361275746 hasConcept C127413603 @default.
- W4361275746 hasConcept C128840427 @default.
- W4361275746 hasConcept C13280743 @default.
- W4361275746 hasConcept C153180895 @default.
- W4361275746 hasConcept C154945302 @default.
- W4361275746 hasConcept C155542232 @default.
- W4361275746 hasConcept C15744967 @default.
- W4361275746 hasConcept C176217482 @default.
- W4361275746 hasConcept C185798385 @default.
- W4361275746 hasConcept C205649164 @default.
- W4361275746 hasConcept C21547014 @default.
- W4361275746 hasConcept C2524010 @default.
- W4361275746 hasConcept C26517878 @default.
- W4361275746 hasConcept C2776151529 @default.
- W4361275746 hasConcept C2779530757 @default.
- W4361275746 hasConcept C2780023022 @default.
- W4361275746 hasConcept C2781238097 @default.
- W4361275746 hasConcept C31972630 @default.
- W4361275746 hasConcept C33923547 @default.
- W4361275746 hasConcept C38349280 @default.
- W4361275746 hasConcept C38652104 @default.
- W4361275746 hasConcept C41008148 @default.
- W4361275746 hasConcept C55020928 @default.
- W4361275746 hasConcept C62520636 @default.