Semantic Decomposition and Recognition of Long and Complex Manipulation Action Sequences

TL;DR

This paper presents a novel semantic segmentation method for long, complex human manipulation actions using Semantic Event Chains, which effectively captures spatiotemporal structures invariant to motion and scene variations.

Contribution

Introduces a new SEC-based framework for automatic parsing and recognition of complex manipulation sequences without prior object knowledge.

Findings

Effective segmentation of complex actions

Robust recognition across diverse datasets

Invariant to motion and scene variations

Abstract

Understanding continuous human actions is a non-trivial but important problem in computer vision. Although there exists a large corpus of work in the recognition of action sequences, most approaches suffer from problems relating to vast variations in motions, action combinations, and scene contexts. In this paper, we introduce a novel method for semantic segmentation and recognition of long and complex manipulation action tasks, such as "preparing a breakfast" or "making a sandwich". We represent manipulations with our recently introduced "Semantic Event Chain" (SEC) concept, which captures the underlying spatiotemporal structure of an action invariant to motion, velocity, and scene context. Solely based on the spatiotemporal interactions between manipulated objects and hands in the extracted SEC, the framework automatically parses individual manipulation streams performed either sequentially or concurrently. Using event chains, our method further extracts basic primitive elements of each parsed manipulation. Without requiring any prior object knowledge, the proposed framework can also extract object-like scene entities that exhibit the same role in semantically similar manipulations. We conduct extensive experiments on various recent datasets to validate the robustness of the framework.