Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204679535> ?p ?o ?g. }
- W3204679535 abstract "Exploring to what humans pay attention in dynamic panoramic scenes is useful for many fundamental applications, including augmented reality (AR) in retail, AR-powered recruitment, and visual language navigation. With this goal in mind, we propose PV-SOD, a new task that aims to segment salient objects from panoramic videos. In contrast to existing fixation-/object-level saliency detection tasks, we focus on audio-induced salient object detection (SOD), where the salient objects are labeled with the guidance of audio-induced eye movements. To support this task, we collect the first large-scale dataset, named ASOD60K, which contains 4K-resolution video frames annotated with a six-level hierarchy, thus distinguishing itself with richness, diversity and quality. Specifically, each sequence is marked with both its super-/sub-class, with objects of each sub-class being further annotated with human eye fixations, bounding boxes, object-/instance-level masks, and associated attributes (e.g., geometrical distortion). These coarse-to-fine annotations enable detailed analysis for PV-SOD modelling, e.g., determining the major challenges for existing SOD models, and predicting scanpaths to study the long-term eye fixation behaviors of humans. We systematically benchmark 11 representative approaches on ASOD60K and derive several interesting findings. We hope this study could serve as a good starting point for advancing SOD research towards panoramic videos. The dataset and benchmark will be made publicly available at https://github.com/PanoAsh/ASOD60K." @default.
- W3204679535 created "2021-10-11" @default.
- W3204679535 creator A5001285878 @default.
- W3204679535 creator A5025883253 @default.
- W3204679535 creator A5044544424 @default.
- W3204679535 creator A5044757881 @default.
- W3204679535 creator A5056294284 @default.
- W3204679535 creator A5082634513 @default.
- W3204679535 date "2021-07-24" @default.
- W3204679535 modified "2023-09-27" @default.
- W3204679535 title "ASOD60K: An Audio-Induced Salient Object Detection Dataset for Panoramic Videos" @default.
- W3204679535 cites W1894057436 @default.
- W3204679535 cites W1980120082 @default.
- W3204679535 cites W1982075130 @default.
- W3204679535 cites W1988712925 @default.
- W3204679535 cites W2002781701 @default.
- W3204679535 cites W2039313011 @default.
- W3204679535 cites W2076756823 @default.
- W3204679535 cites W2086791339 @default.
- W3204679535 cites W2108598243 @default.
- W3204679535 cites W2110019070 @default.
- W3204679535 cites W2138682569 @default.
- W3204679535 cites W2194775991 @default.
- W3204679535 cites W2470139095 @default.
- W3204679535 cites W2501148868 @default.
- W3204679535 cites W2547489168 @default.
- W3204679535 cites W2565955132 @default.
- W3204679535 cites W2605929543 @default.
- W3204679535 cites W2620871200 @default.
- W3204679535 cites W2622036627 @default.
- W3204679535 cites W2740667773 @default.
- W3204679535 cites W2796422723 @default.
- W3204679535 cites W2798665861 @default.
- W3204679535 cites W2798807298 @default.
- W3204679535 cites W2799064164 @default.
- W3204679535 cites W2799108379 @default.
- W3204679535 cites W2810323393 @default.
- W3204679535 cites W2884414611 @default.
- W3204679535 cites W2895640967 @default.
- W3204679535 cites W2895696451 @default.
- W3204679535 cites W2938260698 @default.
- W3204679535 cites W2939217524 @default.
- W3204679535 cites W2945809413 @default.
- W3204679535 cites W2946520073 @default.
- W3204679535 cites W2948510860 @default.
- W3204679535 cites W2961348656 @default.
- W3204679535 cites W2962748579 @default.
- W3204679535 cites W2962835968 @default.
- W3204679535 cites W2962965915 @default.
- W3204679535 cites W2963112696 @default.
- W3204679535 cites W2963339238 @default.
- W3204679535 cites W2963529609 @default.
- W3204679535 cites W2963609011 @default.
- W3204679535 cites W2964306713 @default.
- W3204679535 cites W2965638232 @default.
- W3204679535 cites W2969261403 @default.
- W3204679535 cites W2984128514 @default.
- W3204679535 cites W2985335644 @default.
- W3204679535 cites W2986056979 @default.
- W3204679535 cites W2987701848 @default.
- W3204679535 cites W2989161706 @default.
- W3204679535 cites W2990984982 @default.
- W3204679535 cites W2996939355 @default.
- W3204679535 cites W2997217064 @default.
- W3204679535 cites W2997316506 @default.
- W3204679535 cites W2997462482 @default.
- W3204679535 cites W2998213057 @default.
- W3204679535 cites W3009259128 @default.
- W3204679535 cites W3034185160 @default.
- W3204679535 cites W3034287518 @default.
- W3204679535 cites W3034304805 @default.
- W3204679535 cites W3034515714 @default.
- W3204679535 cites W3035290198 @default.
- W3204679535 cites W3035422681 @default.
- W3204679535 cites W3039991645 @default.
- W3204679535 cites W3049847664 @default.
- W3204679535 cites W3087221416 @default.
- W3204679535 cites W3090053821 @default.
- W3204679535 cites W3090469840 @default.
- W3204679535 cites W3092604408 @default.
- W3204679535 cites W3092630514 @default.
- W3204679535 cites W3098389804 @default.
- W3204679535 cites W3104979525 @default.
- W3204679535 cites W3107944836 @default.
- W3204679535 cites W3108948422 @default.
- W3204679535 cites W3109623941 @default.
- W3204679535 cites W3111024204 @default.
- W3204679535 cites W3114738484 @default.
- W3204679535 cites W3118710621 @default.
- W3204679535 cites W3122006940 @default.
- W3204679535 cites W3131182250 @default.
- W3204679535 cites W3152765238 @default.
- W3204679535 cites W3174178235 @default.
- W3204679535 cites W3176679855 @default.
- W3204679535 cites W3177004386 @default.
- W3204679535 cites W3199914841 @default.
- W3204679535 cites W3201982745 @default.
- W3204679535 doi "https://doi.org/10.48550/arxiv.2107.11629" @default.
- W3204679535 hasPublicationYear "2021" @default.
- W3204679535 type Work @default.