Movie Description Rohrbach, Anna; Torabi, Atousa; Rohrbach, Marcus ...
International journal of computer vision,
05/2017, Letnik:
123, Številka:
1
Journal Article
Recenzirano
Odprti dostop
Audio description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus ...naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. We introduce the
Large Scale Movie Description Challenge
(LSMDC) which contains a parallel corpus of 128,118 sentences aligned to video clips from 200 movies (around 150 h of video in total). The goal of the challenge is to automatically generate descriptions for the movie clips. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are more visual and describe precisely what
is shown
rather than what
should happen
according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in the challenges organized in the context of two workshops at ICCV 2015 and ECCV 2016.
While movie studios have leveraged data traditionally through demographics, there may be missed opportunities in securing further granular insights through personality and lifestyle scales. Due to ...the amount of hyper-competition among movies but also across platforms, marketers and advertisers may revisit consideration of how consumer personality and consumer lifestyle may aid them in predicting movie frequency consumption across genres and platforms. This study deployed a survey and collected a national randomized sample (N=301). Implications include cultivating consumer profiles and anticipating how certain personalities and lifestyles may help measure certain movie genre and movie platform consumption.
The creative industries have frequently expressed concern that they can't compete with freely available copies of their content. Competing with free is particularly concerning for movie studios, ...whose content may be more prone to single-use consumption than other industries such as music. This issue has gained renewed importance recently with the advent of new digital video recording and distribution technologies, and the widespread availability of Internet piracy. We examine competition between "free" and paid video content in two important contexts: the impact of legitimate free distribution in one channel on sales through paid channels, and the impact of illegitimate free distribution in pirated channels on sales through paid channels. We do this by studying the impact of movie broadcasts on DVD demand and the impact of piracy availability at the time of broadcast on DVD demand. Our data include all movies shown on over-the-air and cable television during an eight-month period in 2005-2006. With respect to the impact of movie broadcasts on piracy and sales, we find that movie broadcasts on over-the-air networks result in a significant increase in both DVD sales at Amazon. com and illegal downloads for those movies that are available on BitTorrent at the time of broadcast. With respect to the impact of piracy on sales, we use the television broadcast as an exogenous demand shock and find that the availability of pirated content at the time of broadcast has no effect on post-broadcast DVD sales gains. Together our results suggest that creative artists can use product differentiation and market segmentation strategies to compete with freely available copies of their content. Specifically, the post-broadcast increase in DVD sales suggests that giving away content in one channel can stimulate sales in a paid channel if the free content is sufficiently differentiated from its paid counterpart. Likewise, our finding that the presence of pirated content does not cannibalize sales for the movies in our sample suggests that if free and paid products appeal to separate customer segments, the presence of free products need not harm paid sales.
Purpose/significance Exploring the hidden themes that affect the interactive effect of movie microblogging can explore the hot issues of users' attention and provide effective marketing strategies ...for enterprises. Method/process This paper crawled the popular microblog of 123 movies released in 2017 from Sina Weibo, used the topic modeling method to mine the hidden themes in the movie microblog text, and used the regression method to analyze the impact of hidden themes on the interactive effect of movie microblogging.Results/conclusions It turns out that there are 6 interpretable themes: movie characters, movie promotion, interactive marketing, movie content, movie evaluation and offline activities, of which 4 themes of movie promotion, interactive marketing, movie content and movie evaluation have a positive impact on the interactive effect of movie Weibo; at the same time, it is found that the number of user fans and the popularity of topic discussion positively affect the interactive effect of movie
This research investigates how movie ratings from professional critics, amateur communities, and viewers themselves influence key movie performance measures (i.e., movie revenues and new movie ...ratings). Using movie-level data, the authors find that high early movie revenues enhance subsequent movie ratings. They also find that high advertising spending on movies supported by high ratings maximizes the movie's revenues. Furthermore, they empirically show that sequel movies tend to reap more revenues but receive lower ratings than originals. Using individual viewer—level data, this research highlights how viewers' own viewing and rating histories and movie communities' collective opinions explain viewer satisfaction. The authors find that various aspects of these ratings explain viewers' new movie ratings as a measure of viewer satisfaction, after controlling for movie characteristics. Furthermore, they find that viewers' movie experiences can cause them to become more critical in ratings over time. Finally, they find a U-shaped relationship between viewers' genre preferences and genre-specific movie ratings for heavy viewers.