Corpus ID: 221090058

A Unified Framework for Shot Type Classification Based on Subject Centric Lens

@inproceedings{Rao2020AUF,
  title={A Unified Framework for Shot Type Classification Based on Subject Centric Lens},
  author={Anyi Rao and Jiaze Wang and Linning Xu and Xuekun Jiang and Q. Huang and B. Zhou and D. Lin},
  year={2020}
}
  • Anyi Rao, Jiaze Wang, +4 authors D. Lin
  • Published 2020
  • Computer Science, Engineering
  • Shots are key narrative elements of various videos, e.g. movies, TV series, and user-generated videos that are thriving over the Internet. The types of shots greatly influence how the underlying ideas, emotions, and messages are expressed. The technique to analyze shot types is important to the understanding of videos, which has seen increasing demand in real-world applications in this era. Classifying shot type is challenging due to the additional information required beyond the video content… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    MovieNet: A Holistic Dataset for Movie Understanding
    • 6
    • PDF
    Online Multi-modal Person Search in Videos
    • 3
    • PDF
    Placepedia: Comprehensive Place Understanding with Multi-Faceted Annotations
    • 2
    • PDF
    Knowledge Distillation Meets Self-Supervision
    • 4
    • PDF
    Learn to Propagate Reliably on Noisy Affinity Graphs
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 60 REFERENCES
    Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
    • 1,821
    • Highly Influential
    • PDF
    Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
    • 1,479
    • PDF
    A unified framework for semantic shot classification in sports video
    • 98
    • PDF
    Deep Residual Learning for Image Recognition
    • 50,533
    • Highly Influential
    • PDF
    Temporal Action Detection with Structured Segment Networks
    • 206
    • PDF
    ImageNet Large Scale Visual Recognition Challenge
    • 16,498
    • PDF
    ActivityNet: A large-scale video benchmark for human activity understanding
    • 779
    • PDF
    R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
    • 292
    • PDF
    Shot classification in sports video
    • 16
    Using context saliency for movie shot classification
    • 17
    • PDF