Long Activity Video Understanding using Functional Object-Oriented Network

TL;DR

This paper introduces a four-stage pipeline for comprehensive video understanding that recognizes atomic actions and overall activity by integrating object and motion recognition with a graph-based knowledge network, demonstrated on cooking videos.

Contribution

It presents a novel functional object-oriented network for encoding manipulation task knowledge, enhancing the accuracy of action and activity recognition in videos.

Findings

Improved activity classification accuracy on cooking videos.

Effective integration of object, motion, and knowledge-based confidence scores.

Significant enhancement over baseline methods in video understanding tasks.

Abstract

Video understanding is one of the most challenging topics in computer vision. In this paper, a four-stage video understanding pipeline is presented to simultaneously recognize all atomic actions and the single on-going activity in a video. This pipeline uses objects and motions from the video and a graph-based knowledge representation network as prior reference. Two deep networks are trained to identify objects and motions in each video sequence associated with an action. Low Level image features are then used to identify objects of interest in that video sequence. Confidence scores are assigned to objects of interest based on their involvement in the action and to motion classes based on results from a deep neural network that classifies the on-going action in video into motion classes. Confidence scores are computed for each candidate functional unit associated with an action using a knowledge representation network, object confidences, and motion confidences. Each action is therefore associated with a functional unit and the sequence of actions is further evaluated to identify the single on-going activity in the video. The knowledge representation used in the pipeline is called the functional object-oriented network which is a graph-based network useful for encoding knowledge about manipulation tasks. Experiments are performed on a dataset of cooking videos to test the proposed algorithm with action inference and activity classification. Experiments show that using functional object oriented network improves video understanding significantly.