The "something something" video database for learning and evaluating visual common sense
This addresses the problem of enabling AI systems to reason about complex scenes and integrate visual knowledge with natural language, though it is incremental as it focuses on dataset creation rather than a new method.
The authors tackled the lack of common sense knowledge in neural networks by creating the 'something-something' video database with over 100,000 videos across 174 classes, designed for tasks requiring physical world understanding.
Neural networks trained on datasets such as ImageNet have led to major advances in visual object classification. One obstacle that prevents networks from reasoning more deeply about complex scenes and situations, and from integrating visual knowledge with natural language, like humans do, is their lack of common sense knowledge about the physical world. Videos, unlike still images, contain a wealth of detailed information about the physical world. However, most labelled video datasets represent high-level concepts rather than detailed physical aspects about actions and scenes. In this work, we describe our ongoing collection of the "something-something" database of video prediction tasks whose solutions require a common sense understanding of the depicted situation. The database currently contains more than 100,000 videos across 174 classes, which are defined as caption-templates. We also describe the challenges in crowd-sourcing this data at scale.