我們提出了一種基于圖形多任務模組化的長視訊人體動作評價(HAE)新方法。以前在活動評估中的工作要麼直接使用檢測到的骨架計算度量，要麼使用場景資訊來回歸活動分數。這些方法對于準确的活動評估是不夠的，因為他們隻計算一個平均分數，并沒有考慮關節和身體動力學之間的相關性。此外，它們高度依賴場景，使得這些方法的可推廣性值得懷疑。我們提出了一種新的HAE多任務架構，該架構利用圖形卷積網絡主幹将人關節之間互連嵌入到特征中。在該架構中，我們将人類行為檢測(HAD)問題作為一個輔助任務來改進活動評估。HAD的頭部由一個編碼器-解碼器-時間卷積網絡提供動力，以檢測長視訊中的活動，并使用了基于長-短期記憶的架構。我們在UW-IOM和TUM廚房資料集上評估了我們的方法，并讨論了在這兩個資料集上的成功和失敗案例。
原文題目:A Multi-Task Learning Approach for Human Action Detection and Ergonomics Risk Assessment
原文：We propose a new approach to Human Action Evaluation (HAE) in long videos using graph-based multi-task modeling. Previous works in activity assessment either directly compute a metric using a detected skeleton or use the scene information to regress the activity score. These approaches are insufficient for accurate activity assessment since they only compute an average score over a clip, and do not consider the correlation between the joints and body dynamics. Moreover, they are highly scene-dependent which makes the generalizability of these methods questionable. We propose a novel multi-task framework for HAE that utilizes a Graph Convolutional Network backbone to embed the interconnection between human joints in the features. In this framework, we solve the Human Action Detection (HAD) problem as an auxiliary task to improve activity assessment. The HAD head is powered by an Encoder-Decoder Temporal Convolutional Network to detect activities in long videos and HAE uses a Long-Short-Term-Memory-based architecture. We evaluate our method on the UW-IOM and TUM Kitchen datasets and discuss the success and failure cases on these two datasets.
原文作者：Behnoosh Parsa, Ashis G. Banerjee
原文位址：https://arxiv.org/abs/2008.03014
人類行動檢測和人機工程學風險評估的多任務學習方法 (cs.CV).pdf