Back

CATER

A diagnostic dataset for Compositional Actions and TEmporal Reasoning

CATER

Computer vision has undergone a dramatic revolution in performance, driven in large part through deep features trained on large-scale supervised datasets. However, much of these improvements have focused on static image analysis; video understanding has seen rather modest improvements. Even though new datasets and spatiotemporal models have been proposed, simple frame-by-frame classification methods often still remain competitive. We posit that current video datasets are plagued with implicit biases over scene and object structure that can dwarf variations in temporal structure. In this work, we build a video dataset with fully observable and controllable object and scene bias, and which truly requires spatiotemporal understanding in order to be solved. Our dataset, named CATER, is rendered synthetically using a library of standard 3D objects, and tests the ability to recognize compositions of object movements that require long-term reasoning. As an illustrative example, consider the "cups and ball" shell game, where a target object (ball) is adversarially passed between container objects (cups) so as to deceive an observer as to its final position. Solving this task requires reasoning about recursive container relations and long-term occlusions. In addition to being a challenging dataset, CATER also provides a plethora of diagnostic tools to analyze modern spatiotemporal video architectures by being completely observable and controllable. Using CATER, we provide insights into some of the most recent state of the art deep video architectures.

Try V7 now
->
View author website
Task
Video Classification
Annotation Types
Classification Tags
Items
Classes
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
MIT
Blog
Learn about machine learning and latests advancements in AI.
Read More
Playbooks
Discover how to optimize AI for your business.
Learn more
Case Studies
Discover how V7 empowers AI industry greats.
Explore now
Webinars
Explore AI topics, gain insights, and learn from experts.
Watch now