Condensed movies: story based retrieval with contextual embeddings
Our objective in this work is long range understanding of the narrative structure of movies. Instead of considering the entire movie, we propose to learn from the ‘key scenes’ of the movie, providing a condensed look at the full storyline. To this end, we make the following three contributions: (i)...
Main Authors: | Bain, M, Nagrani, A, Brown, A, Zisserman, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Springer
2021
|
Similar Items
-
AutoAD: movie description in context
by: Han, T, et al.
Published: (2023) -
AutoAD II: The Sequel - who, when, and what in movie audio description
by: Han, T, et al.
Published: (2024) -
Frozen in time: A joint video and image encoder for end-to-end retrieval
by: Bain, M, et al.
Published: (2022) -
Learnable PINs: Cross-modal embeddings for person identity
by: Nagrani, A, et al.
Published: (2018) -
Playing a part: speaker verification at the movies
by: Brown, A, et al.
Published: (2021)