Hierarchical structure is a common characteristic for some kinds of videos (e.g., sports videos, game videos): The videos are composed of several actions hierarchically and there exist temporal dependencies among segments with different scales, where action labels can be enumerated. Our ideas are based on two observations: First, the actions are the fundamental units for people to understand these videos. Second, the humans summarize a video by iteratively observing and refining, i.e., observing segments in video and hierarchically refining the boundaries of important actions. Based on the above insights, we generate action proposals to construct the structure of the video and formulate the summarization process as a hierarchical refining process. We also train a hierarchical summarization network with deep Q-learning (HQSN) to achieve the refining process and explore temporal dependency. Besides, we collect a new dataset that consists of structured game videos with fine-grain actions and importance annotations. The experimental results demonstrate the effectiveness of the proposed method.
The application of plant landscape color has a great effect on the landscape of the scenic spot. By colorful foliage and ornamental plants with high color recognition, visitors can deepen their impressions, and thus increase the landscape aesthetic expectations and psychological recognition of the landscape sense. The plants in Norbulingka were taken as research object in this paper. Via field investigation and consulting a lot of data, color characters of ornamental plants from each genus and family were identified from the angle of plant characteristics of arbor, shrub and herb. CMYK color card value was used to collect color data of leaves, flowers and fruits from different plants, and quantitative analysis on color difference of leaves, flowers and fruits from ornamental plants was conducted, to obtain evaluation method and reasoning basis of plant color design in Norbulingka. The results showed that: 1) in color values of leaves, percentage of purple herb = red shrub; cyan herb > light green herb, dark green arbor > grass green arbor, yellow shrub > jade green shrub, bitter orange arbor < bottle green arbor; 2) in color values of flowers, percentage of bitter orange herb < blue shrub, cyan herb > light green herb, dark green arbor > grass green arbor, yellow shrub > jade green shrub, bitter orange arbor < bottle green arbor; 3) in color values of fruits, percentage of purple shrub > yellow shrub, yellow arbor > red arbor, blue herb = green arbor, red shrub < green shrub.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.