Diverse and Universal Camera

This work is a video installation that searches and collages the footage from the Encyclopedia Cinematographica (EC) using approximately 50 different behavior style related keywords (tags) such as dancing, laughing, and spinning and then plays the results in a loop. Since the combination of videos changes every time, it allows us to observe the differences and connections between various videos from different eras and regions. This is a work that reinterprets the characteristics of EC as an encyclopedia and visualizes them. It is intended to be a medium that enables both chance encounters, like traditional paper encyclopedias, and the expansion of knowledge based on relevance, as seen in modern internet searches. In the 2019 exhibition, all video tagging was done manually, but this time, we are attempting to apply deep learning technology by artificial intelligence (AI) to the work, creating a hybrid system that combines AI-based automatic tagging with manual tagging. In this exhibition, we are also simultaneously releasing a database containing information on all EC titles. In today's world, characterized by events like the Russia-Ukraine conflict, the Palestine issue, nationalistic tendencies in various countries, and anti-immigration sentiment, there is a prevailing atmosphere of intolerance worldwide. It is precisely in such times that we believe it is important to reconsider the social significance of EC, which has documented the diversity and universality of behaviors in the natural world.

Authors

Institutions

Publication Details

Published
2024-12-03
DOI
https://doi.org/10.1145/3680529.3688962
Primary Topic
Video Analysis and Summarization
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Diverse and Universal Camera

Yuta Ogai, Y. Noguchi
Video Analysis and Summarization
article

Diverse and Universal Camera

Yuta Ogai, Y. Noguchi
article en

Abstract

This work is a video installation that searches and collages the footage from the Encyclopedia Cinematographica (EC) using approximately 50 different behavior style related keywords (tags) such as dancing, laughing, and spinning and then plays the results in a loop. Since the combination of videos changes every time, it allows us to observe the differences and connections between various videos from different eras and regions. This is a work that reinterprets the characteristics of EC as an encyclopedia and visualizes them. It is intended to be a medium that enables both chance encounters, like traditional paper encyclopedias, and the expansion of knowledge based on relevance, as seen in modern internet searches. In the 2019 exhibition, all video tagging was done manually, but this time, we are attempting to apply deep learning technology by artificial intelligence (AI) to the work, creating a hybrid system that combines AI-based automatic tagging with manual tagging. In this exhibition, we are also simultaneously releasing a database containing information on all EC titles. In today's world, characterized by events like the Russia-Ukraine conflict, the Palestine issue, nationalistic tendencies in various countries, and anti-immigration sentiment, there is a prevailing atmosphere of intolerance worldwide. It is precisely in such times that we believe it is important to reconsider the social significance of EC, which has documented the diversity and universality of behaviors in the natural world.

Tokyo Polytechnic University (JP)
Tokyo Polytechnic University
Reduced inequalities
Openalex Percentile: Top 78%
Video Analysis and Summarization
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.