Hierarchical Object-oriented Spatio-Temporal Reasoning for Video Question Answering

TL;DR

This paper introduces HOSTR, a hierarchical object-oriented neural network that models dynamic objects and their interactions over space and time, significantly improving Video QA performance and interpretability.

Contribution

The paper proposes a novel hierarchical object-oriented reasoning framework for Video QA, emphasizing object interactions and hierarchically abstracted representations.

Findings

Achieves new state-of-the-art results on multiple Video QA datasets.

Object-oriented reasoning enhances interpretability and efficiency.

The model effectively captures dynamic object interactions over space and time.

Abstract

Video Question Answering (Video QA) is a powerful testbed to develop new AI capabilities. This task necessitates learning to reason about objects, relations, and events across visual and linguistic domains in space-time. High-level reasoning demands lifting from associative visual pattern recognition to symbol-like manipulation over objects, their behavior and interactions. Toward reaching this goal we propose an object-oriented reasoning approach in that video is abstracted as a dynamic stream of interacting objects. At each stage of the video event flow, these objects interact with each other, and their interactions are reasoned about with respect to the query and under the overall context of a video. This mechanism is materialized into a family of general-purpose neural units and their multi-level architecture called Hierarchical Object-oriented Spatio-Temporal Reasoning (HOSTR) networks. This neural model maintains the objects' consistent lifelines in the form of a hierarchically nested spatio-temporal graph. Within this graph, the dynamic interactive object-oriented representations are built up along the video sequence, hierarchically abstracted in a bottom-up manner, and converge toward the key information for the correct answer. The method is evaluated on multiple major Video QA datasets and establishes new state-of-the-arts in these tasks. Analysis into the model's behavior indicates that object-oriented reasoning is a reliable, interpretable and efficient approach to Video QA.