Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the large visual variations and uncontrolled frame rates. There are two steps crucial to person re-id, namely discriminative feature learning and metric learning. However, existing approaches consider the two steps independently, and they do not make full use of the temporal and spatial information in videos. In this paper, we propose a Siamese attention architecture that jointly learns spatio-temporal video representations and their similarity metrics. The network extracts local convolutional features from regions of each frame, and enhance their discriminative capability by focusing on distinct regions when measuring the similarity with another pedestrian video. The attention mechanism is embedded into spatial gated recurrent units to selectively propagate relevant features and memorize their spatial dependencies through the network. The model essentially learns which parts (where) from which frames (when) are relevant and distinctive for matching persons and attaches higher importance therein. The proposed Siamese model is end-to-end trainable to jointly learn comparable hidden representations for paired pedestrian videos and their similarity value. Extensive experiments on three benchmark datasets show the effectiveness of each component of the proposed deep network while outperforming state-of-the-art methods.

Federated learning (FL) is a novel machine learning setting that enables on-device intelligence via decentralized training and federated optimization. Deep neural networks' rapid development facilitates the learning techniques for modeling complex problems and emerges into federated deep learning under the federated setting. However, the tremendous amount of model parameters burdens the communication network with a high load of transportation. This paper introduces two approaches for improving communication efficiency by dynamic sampling and top-k selective masking. The former controls the fraction of selected client models dynamically, while the latter selects parameters with top- $k$ largest values of difference for federated updating. Experiments on convolutional image classification and recurrent language modeling are conducted on three public datasets to show our proposed methods' effectiveness.

The current unsupervised cross‐domain detection methods need source domain data to retrain the detection model in target domain. However, the source domain data may be unavailable due to privacy, decentralization, or computation resource restrictions. A natural idea is to optimize the parameters of the source domain model by self‐supervised learning based on pseudo labels. We propose another approach from the viewpoint of noise perturbation without pseudo‐labeling. It can be assumed that the source and target domains are actually derived from a domain invariant space through domain‐specific perturbations, respectively. A super target domain can be constructed by augmenting more target domain perturbations to the target domain images. The optimal direction of the target domain to the domain invariant space can be approximated as the alignment direction from the super target domain to the target domain. Based on this idea, we propose a novel method called SOAP (SOurce data‐free domain Adaptation through domain Perturbation) which can remove domain perturbation from the target domain. The image‐level, instance‐level, and category consistency regularizations based on Mean Teacher structure are proposed to learn the correct alignment direction. Specifically, the category consistency can also further improve the classification accuracy. Extensive experiments on multiple domain adaptation scenarios demonstrate that SOAP achieves better performance surpassing the baseline (Faster R‐CNN) and multiple state‐of‐the‐art domain adaptation methods which need to access source domain data.

Milk production and body conformation traits are critical economic traits for dairy cows. To understand the basic genetic structure for those traits, a genome wide association study was performed on milk yield, milk fat yield, milk fat percentage, milk protein yield, milk protein percentage, somatic cell score, body form composite index, daily capacity composite index, feed, and leg conformation traits, based on the Illumina Bovine HD100k BeadChip. A total of 57, 12 and 26 SNPs were found to be related to the milk production, somatic cell score and body conformation traits in the Holstein cattle. Genes with pleiotropic effect were also found in this study. Seven significant SNPs were associated with multi-traits and were located on the PLEC, PLEKHA5, TONSL, PTGER4, and LCORL genes. In addition, some important candidate genes, like GPAT3, CEBPB, AGO2, SLC37A1, and FNDC3B, were found to participate in fat metabolism or mammary gland development. These results can be used as candidate genes for milk production, somatic cell score, and body conformation traits of Holstein cows, and are helpful for further gene function analysis to improve milk production and quality.