Location-based services and identification hold promise for future smart home applications. Through them, we can provide customized services for specific users in current locations. Recent studies have demonstrated that Wi-Fi signals can be leveraged to achieve device-free tracking and gait recognition. Despite their good performance, these two technologies are not effectively integrated for the following reasons: First, the device-free tracking method might yield tracking results that conflict with human gait. Second, extracting gait features relies on knowing or accurately estimating the user's trajectory. Consequently, gait recognition and tracking are inherently linked, but there has been no effective approach to integrate these two techniques. In this paper, we present STAGR, a system capable ofSimultaneousTrackingAndGaitRecognition. The main contribution of our technique is that we establish a theoretical model that reveals how to transform path-dependent spectra into path-independent spectra directly. Specifically, we conduct a preliminary study to demonstrate the need for simultaneous tracking and gait recognition. Second, we propose a novel method to extract path-independent gait features, which can significantly save execution time compared with the learning-based method. Third, we design a polar-coordinate filtering method to retain the gait features while correcting the trajectory. We implement a prototype STAGR system and conduct extensive experiments to verify the proposed mechanism. The experimental results show that we can realize simultaneous tracking and gait recognition. The median tracking error is$ 0.45m$, while the recognition accuracy is 95.3% for 6 users.

Leveraging the abundant knowledge learned from pre-trained multi-modal models like CLIP has recently proved to be effective for text-guided image editing. Though convincing results have been made when combining the image generator StyleGAN with CLIP, most methods need to train separate models for different prompts, and irrelevant regions are often changed after editing due to the lack of spatial disentanglement. We propose a novel framework that can edit different images according to different prompts in one model. Besides, an innovative region-based spatial attention mechanism is adopted to explicitly guarantee the locality of editing. Experiments mainly in the face domain verify the feasibility of our framework and show that when multi-text editing and local editing are accomplishable, our method can complete practical applications like sequential editing and regional style transfer.

Computational strategies for identifying new drug-target interactions (DTIs) can guide the process of drug discovery, reduce the cost and time of drug development, and thus promote drug development. Most recently proposed methods predict DTIs via integration of heterogeneous data related to drugs and proteins. However, previous methods have failed to deeply integrate these heterogeneous data and learn deep feature representations of multiple original similarities and interactions related to drugs and proteins. We therefore constructed a heterogeneous network by integrating a variety of connection relationships about drugs and proteins, including drugs, proteins, and drug side effects, as well as their similarities, interactions, and associations. A DTI prediction method based on random walk and convolutional neural network was proposed and referred to as DTIPred. DTIPred not only takes advantage of various original features related to drugs and proteins, but also integrates the topological information of heterogeneous networks. The prediction model is composed of two sides and learns the deep feature representation of a drug-protein pair. On the left side, random walk with restart is applied to learn the topological vectors of drug and protein nodes. The topological representation is further learned by the constructed deep learning frame based on convolutional neural network. The right side of the model focuses on integrating multiple original similarities and interactions of drugs and proteins to learn the original representation of the drug-protein pair. The results of cross-validation experiments demonstrate that DTIPred achieves better prediction performance than several state-of-the-art methods. During the validation process, DTIPred can retrieve more actual drug-protein interactions within the top part of the predicted results, which may be more helpful to biologists. In addition, case studies on five drugs further demonstrate the ability of DTIPred to discover potential drug-protein interactions.

Achieving backward compatibility when rolling out new models can highly reduce costs or even bypass feature re-encoding of existing gallery images for in-production visual retrieval systems. Previous related works usually leverage losses used in knowledge distillation which can cause performance degradations or not guarantee compatibility. To address these issues, we propose a general framework called Learning Compatible Embeddings (LCE) which is applicable for both cross model compatibility and compatible training in direct/forward/backward manners. Our compatibility is achieved by aligning class centers between models directly or via a transformation, and restricting more compact intra-class distributions for the new model. Experiments are conducted in extensive scenarios such as changes of training dataset, loss functions, network architectures as well as feature dimensions, and demonstrate that LCE efficiently enables model compatibility with marginal sacrifices of accuracies. The code will be available at https://github.com/IrvingMeng/LCE.