The use of millimeter-wave radar (mmWave radar) for human motion detection is essential in the realm of smart home Internet-of-Things (IoT) scenarios due to its non-intrusive nature, privacy considerations, interactive capabilities, and cost-effectiveness. However, the existing methods fail to address the issue of low real-time detection rates. Moreover, the design of the action does not align with the requirements of smart home IoT systems, while the complexity of the algorithm leads to high computing hardware costs. To address these problems, we propose mmMotion, a novel mmWave radar-based human motion detection system capable of accurately estimating six well-designed human motions (sit down, stand up, get up, lie down, wave hands, and punch) commonly observed in smart home scenarios with cost-effectiveness and real-time processing speed. By incorporating the spatial feature of “Height”, we are the first to propose a novel feature extraction method using the “Doppler-Height-Time” (DHT) feature maps as system input for human motion detection. A combined lightweight Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture is developed to simultaneously capture spatial and temporal features, leveraging the strengths of both architectures. Furthermore, we propose a novel Real-time Classifier combined with the Static Clutter Removal (SCR) method and Duo Filter algorithm to enhance the real-time detection capability of mm-Motion. Experiment results demonstrate that mmMotion achieves an impressive offline training accuracy rate of 98.13% and a real-time motion recognition rate of 90.5% for six designated motions. Furthermore, it exhibits excellent generalization ability across different individuals and robustness to the interference of large and small actions during real-time performance testing.

The Coastal underwater evidence search system with surface-underwater collaboration is designed to revolutionize the search for artificial objects in coastal underwater en-vironments, overcoming limitations associated with traditional methods such as divers and tethered remotely operated vehicles. Our innovative multi-robot collaborative system consists of three parts: an autonomous surface vehicle as a mission control center, a towed underwater vehicle for wide-area search, and a biomimetic underwater robot inspired by marine organisms for detailed inspections of identified areas. We conduct extensive simulations and real-world experiments in pond environments and coastal fields to demonstrate the system's potential to sur-pass the limitations of conventional underwater search methods, offering a robust and efficient solution for law enforcement and recovery operations in marine settings. (Video11https://youtu.be/tEtTLpGrO2c)

We propose a novel mmWave radar-based system capable of accurately estimating six human motions (Sit down, stand up, snap, swing hands, get up, and lie down) commonly observed in smart home scenarios with cost-effectiveness and real-time processing speed. We are the first to propose the “Doppler-Height-SNR-Time” feature maps as system input for human motion estimation. We propose a novel approach that combines lightweight CNN and LSTM architectures. Our approach leverages the strengths of both models to enhance system accuracy by effectively capturing spatial and doppler velocity features using CNN while extracting temporal features related to motion continuity using LSTM. Our model achieves an impressive offline testing accuracy of 96.7% and demonstrates a 73.33% recognition rate for predefined actions in real-time scenarios, along with robustness against non-target motions in experiments.

Pre-trained vision-language(VL) model improves the performance in vision-language tasks, but requires a large amount of labeled data to apply the model to downstream tasks. It is challenging to obtain good results with limited training data. Prompt Tuning(PT), which freezes pre-train language models(PLMs) and only tunes soft prompts, provides an effective solution for adapting PLMs to downstream tasks. However, PT performs comparably with Full-model Tuning(FT) when the data are sufficient and performs much worse in few-shot settings, primarily due to the initialization of soft prompts. In this paper, we propose a new training framework Pre-train a Prompt Pool for Vision-Language Models called “P3VLM”, to give better initialization to PT. The objective of P3VLM is to optimize prompts selected by the visual feature, allowing the prompt to learn relevant knowledge in different data domains and store it in the prompt pool. Then we use diverse prompts in the prompt pool as the initialization of PT instead of a single pre-trained prompt. In the pre-train stage, the training samples are used to train a prompt pool by selecting prompts that best match the visual features. In the downstream datasets, the model selects the best matching prompts as the initialization for PT, freezes the PLM, and only tunes the prompts. Extensive experiments show that our method obtains strong performance on two image caption datasets in both zero-shot and few-shot scenarios.

Multi-view clustering has attracted increasing attention in recent years by exploiting common clustering structure across multiple views. Most existing multi-view clustering algorithms use shallow and linear embedding functions to learn the common structure of multi-view data. However, these methods cannot fully utilize the non-linear property of multi-view data, which is important to reveal complex cluster structure underlying multi-view data. In this paper, we propose a novel multi-view clustering method, named Deep Adversarial Multi-view Clustering (DAMC) network, to learn the intrinsic structure embedded in multi-view data. Specifically, our model adopts deep auto-encoders to learn latent representations shared by multiple views, and meanwhile leverages adversarial training to further capture the data distribution and disentangle the latent space. Experimental results on several real-world datasets demonstrate that the proposed method outperforms the state-of art methods.

Due to the importance and efficiency of learning complex structures hidden in data, graph-based methods have been widely studied and get successful in unsupervised learning. Generally, most existing graph-based clustering methods require post-processing on the original data graph to extract the clustering indicators. However, there are two drawbacks with these methods: (1) the cluster structures are not explicit in the clustering results; (2) the final clustering performance is sensitive to the construction of the original data graph. To solve these problems, in this paper, a novel learning model is proposed to learn a graph based on the given data graph such that the new obtained optimal graph is more suitable for the clustering task. We also propose an efficient algorithm to solve the model. Extensive experimental results illustrate that the proposed model outperforms other state-of-the-art clustering algorithms.

Linear Discriminant analysis (LDA) has been widely used for face recognition. However, when identifying faces in the wild, the existence of outliers that deviate significantly from the rest of data can arbitrarily skew the desired solution. This usually deteriorates LDA's performance dramatically, thus preventing it from mass deployment in real-world applications. To handle this problem, we propose an effective distance metric learning method based LDA, namely Euler LDA-L21 (e-LDA-L21). e-LDA-L21 is carried out in two stages, in which each image is mapped into a complex space by Euler transform in the first stage and the ℓ2,1-norm is adopted as the distance metric in the second stage. This not only reveals nonlinear features but also exploits the geometric structure of data. To solve e-LDA-L21 efficiently, we propose an iterative algorithm, which is a closed-form solution at each iteration with convergence guaranteed. Finally, we extend e-LDA-L21 to Euler 2DLDA-L21 (e-2DLDA-L21) which further exploits the spatial information embedded in image pixels. Experimental results on several face databases demonstrate its superiority over the state-of-the-art algorithms.