The automatic characterization of pedestrians in surveillance footage is a tough challenge, particularly when the data is extremely diverse with cluttered backgrounds, and subjects are captured from varying distances, under multiple poses, with partial occlusion. Having observed that the state-of-the-art performance is still unsatisfactory, this paper provides a novel solution to the problem, with two-fold contributions: 1) considering the strong semantic correlation between the different full-body attributes, we propose a multi-task deep model that uses an element-wise multiplication layer to extract more comprehensive feature representations. In practice, this layer serves as a filter to remove irrelevant background features, and is particularly important to handle complex, cluttered data; and 2) we introduce a weighted-sum term to the loss function that not only relativizes the contribution of each task but also is crucial for performance improvement in multiple-attribute inference settings. Our experiments were performed on two well-known datasets (RAP and PETA) and point for the superiority of the proposed method with respect to the state-of-the-art. The code is available at https://github.com/Ehsan-Yaghoubi/MAN-PAR-.

监视录像中行人的自动特征识别是一个艰巨的挑战，尤其是当数据杂乱无章且背景杂乱无章，并且在多个姿势下部分距离遮挡时，可以从不同的距离捕获对象。观察到最新技术的性能仍然不能令人满意，本文提供了一个新颖的解决方案，其有两个方面的贡献：1）考虑到不同全身属性之间的强语义相关性，我们提出了多任务深度模型，该模型使用逐元素乘法层提取更全面的特征表示。在实践中，该层用作过滤器以删除不相关的背景特征，对于处理复杂，混乱的数据尤其重要。2）我们为损失函数引入了加权和项，它不仅使每个任务的贡献相对化，而且对于改善多属性推理设置中的性能至关重要。我们的实验是在两个著名的数据集（RAP和PETA）上进行的，这表明了该方法相对于最新技术的优越性。该代码位于https://github.com/Ehsan-Yaghoubi/MAN-PAR-。