HySTER: A Hybrid Spatio-Temporal Event Reasoner
arXiv:2101.06644
Abstract
The task of Video Question Answering (VideoQA) consists in answering natural language questions about a video and serves as a proxy to evaluate the performance of a model in scene sequence understanding. Most methods designed for VideoQA up-to-date are end-to-end deep learning architectures which struggle at complex temporal and causal reasoning and provide limited transparency in reasoning steps. We present the HySTER: a Hybrid Spatio-Temporal Event Reasoner to reason over physical events in videos. Our model leverages the strength of deep learning methods to extract information from video frames with the reasoning capabilities and explainability of symbolic artificial intelligence in an answer set programming framework. We define a method based on general temporal, causal and physics rules which can be transferred across tasks. We apply our model to the CLEVRER dataset and demonstrate state-of-the-art results in question answering accuracy. This work sets the foundations for the incorporation of inductive logic programming in the field of VideoQA.
arXiv commentPreprint accepted by the 35th AAAI Conference on Artificial Intelligence (AAAI-21) Workshop on Hybrid Artificial Intelligence (HAI)
References in corpus (11)
- Deep Residual Learning for Image Recognition
- Feature Pyramid Networks for Object Detection
- Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
- Learning to Reason: End-to-End Module Networks for Visual Question Answering
- CLEVRER: CoLlision Events for Video REpresentation and Reasoning
- Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"
- Inductive Learning of Answer Set Programs from Noisy Examples
- ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
- VQA-LOL: Visual Question Answering under the Lens of Logic
- MarioQA: Answering Questions by Watching Gameplay Videos
- Exploring Neural Models for Parsing Natural Language into First-Order Logic