In this paper, researchers model movies as graphs to generate trailers, identifying narrative structure and predicting sentiment, surpassing supervised methods.
Authors: Pinelopi Papalampidi, Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh; Frank Keller, Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh; Mirella Lapata, Institute for Language, Cognition and Computation, School of Informatics, University of Edinburgh. Table of Links Abstract and Intro Related Work Problem Formulation Experimental Setup Results and Analysis Conclusions and References A.
on the held-out set of 41 movies . As evaluation metric, we use accuracy, i.e., the percentage of correctly identified trailer shots and we consider a total budget of 10 shots for the trailers in order to achieve the desired length . We compare without TPs traverses the graph with TP and sentiment criteria removed . For the unsupervised systems which include stochasticity and produce proposals , we consider the best proposal trailer. The second block of Table 3 presents supervised approaches which use noisy trailer labels for training.
without TPs still performs better than without TPs and Supervised without TPs is most often selected as best , which suggests that the overall approach of modeling movies as graphs and performing random walks instead of individually selecting shots helps create coherent trailers. However, the same model is also most often selected as worst, which shows that this naive approach on its own cannot guarantee good-quality trailers. We include video examples of generated trailers based on our approach in the Supplementary Material.
on the held-out set of 41 movies . As evaluation metric, we use accuracy, i.e., the percentage of correctly identified trailer shots and we consider a total budget of 10 shots for the trailers in order to achieve the desired length . We compare without TPs traverses the graph with TP and sentiment criteria removed . For the unsupervised systems which include stochasticity and produce proposals , we consider the best proposal trailer. The second block of Table 3 presents supervised approaches which use noisy trailer labels for training.
without TPs still performs better than
United Kingdom Latest News, United Kingdom Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Film Trailer Generation via Task Decomposition: Abstract and IntroIn this paper, researchers model movies as graphs to generate trailers, identifying narrative structure and predicting sentiment, surpassing supervised methods.
Read more »
Film Trailer Generation via Task Decomposition: Related WorkIn this paper, researchers model movies as graphs to generate trailers, identifying narrative structure and predicting sentiment, surpassing supervised methods.
Read more »
Film Trailer Generation via Task Decomposition: Problem FormulationIn this paper, researchers model movies as graphs to generate trailers, identifying narrative structure and predicting sentiment, surpassing supervised methods.
Read more »
IMAX Unveils Next-Generation Film Cameras at the Cannes Film FestivalChristopher Nolan, Hoyte van Hoytema, and Cillian Murphy Oppenheimer on the set of Oppenheimer
Read more »
Efficient Guided Generation for Large Language Models: LLM Sampling and Guided GenerationResearchers propose a finite-state machine framework for text generation, offering precise control and improved performance.
Read more »
Bentley Continental GT V8 PHEV prototype reviewA new-generation Bentley Continental GT gets a new-generation engine with mighty plug-in assistance
Read more »