Film Trailer Generation via Task Decomposition

• URL: http://arxiv.org/abs/2111.08774v1
• Date: Tue, 16 Nov 2021 20:50:52 GMT
• Title: Film Trailer Generation via Task Decomposition
• Authors: Pinelopi Papalampidi, Frank Keller, Mirella Lapata
• Abstract summary: We model movies as graphs, where nodes are shots and edges denote semantic relations between them. We learn these relations using joint contrastive training which leverages privileged textual information from screenplays. An unsupervised algorithm then traverses the graph and generates trailers that human judges prefer to ones generated by competitive supervised approaches.
• Score: 65.16768855902268
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Movie trailers perform multiple functions: they introduce viewers to the story, convey the mood and artistic style of the film, and encourage audiences to see the movie. These diverse functions make automatic trailer generation a challenging endeavor. We decompose it into two subtasks: narrative structure identification and sentiment prediction. We model movies as graphs, where nodes are shots and edges denote semantic relations between them. We learn these relations using joint contrastive training which leverages privileged textual information (e.g., characters, actions, situations) from screenplays. An unsupervised algorithm then traverses the graph and generates trailers that human judges prefer to ones generated by competitive supervised approaches.

Related papers

• Towards Automated Movie Trailer Generation [98.9854474456265]
  We introduce Trailer Generation Transformer (TGT), a deep-learning framework utilizing an encoder-decoder architecture. TGT movie encoder is tasked with contextualizing each movie shot representation via self-attention, while the autoregressive trailer decoder predicts the feature representation of the next trailer shot. Our TGT significantly outperforms previous methods on a comprehensive suite of metrics.
  arXiv  Detail & Related papers  (2024-04-04T14:28:34Z)
• MoviePuzzle: Visual Narrative Reasoning through Multimodal Order Learning [54.73173491543553]
  MoviePuzzle is a novel challenge that targets visual narrative reasoning and holistic movie understanding. To tackle this quandary, we put forth MoviePuzzle task that amplifies the temporal feature learning and structure learning of video models. Our approach outperforms existing state-of-the-art methods on the MoviePuzzle benchmark.
  arXiv  Detail & Related papers  (2023-06-04T03:51:54Z)
• AI based approach to Trailer Generation for Online Educational Courses [0.0]
  The framework we propose is a template based method for video trailer generation. The proposed trailer is in the form of a timeline consisting of various fragments created by selecting, para-phrasing or generating content. We perform user evaluation with 63 human evaluators for evaluating the trailers generated by our system.
  arXiv  Detail & Related papers  (2023-01-10T13:33:08Z)
• Multilevel profiling of situation and dialogue-based deep networks for movie genre classification using movie trailers [7.904790547594697]
  We propose a novel multi-modality: situation, dialogue, and metadata-based movie genre classification framework. We develop the English movie trailer dataset (EMTD), which contains 2000 Hollywood movie trailers belonging to five popular genres.
  arXiv  Detail & Related papers  (2021-09-14T07:33:56Z)
• Where to look at the movies : Analyzing visual attention to understand movie editing [75.16856363008128]
  We propose a new eye-tracking database, containing gaze pattern information on movie sequences. We show how state-of-the-art computational saliency techniques behave on this dataset.
  arXiv  Detail & Related papers  (2021-02-26T09:54:58Z)
• Movie Summarization via Sparse Graph Construction [65.16768855902268]
  We propose a model that identifies TP scenes by building a sparse movie graph that represents relations between scenes and is constructed using multimodal information. According to human judges, the summaries created by our approach are more informative and complete, and receive higher ratings, than the outputs of sequence-based models and general-purpose summarization algorithms.
  arXiv  Detail & Related papers  (2020-12-14T13:54:34Z)
• Learning Trailer Moments in Full-Length Movies [49.74693903050302]
  We leverage the officially-released trailers as the weak supervision to learn a model that can detect the key moments from full-length movies. We introduce a novel ranking network that utilizes the Co-Attention between movies and trailers as guidance to generate the training pairs. We construct the first movie-trailer dataset, and the proposed Co-Attention assisted ranking network shows superior performance even over the supervised approach.
  arXiv  Detail & Related papers  (2020-08-19T15:23:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.