Behind the rapid development of deep learning methods, massive data annotations are indispensable yet quite expensive. Many active learning (AL) and semi-supervised learning (SSL) methods have been proposed to address this problem in image classification tasks. However, these methods face a new challenge in object detection tasks, since object detection requires classification as well as localization information in the labeling process. Therefore, in this paper, an object detection framework combining active learning and semi-supervised learning is presented. Tailored for object detection tasks, the uncertainty of an unlabeled image is measured from two perspectives, namely classification stability and localization stability. The unlabeled images with low uncertainty are manually annotated as the AL part, and those with high uncertainty are pseudo-labeled with the detector’s prediction results as the SSL part. Furthermore, to better filter out the noisy pseudo-boxes brought by SSL, a novel pseudo-label mining strategy is proposed that includes a stability aggregation score (SAS) and dynamic adaptive threshold (DAT). The SAS aggregates the classification and localization stability scores to measure the quality of predicted boxes, while the DAT adaptively adjusts the thresholds for each category to alleviate the class imbalance problem. Extensive experimental results demonstrate that our proposed method significantly outperforms state-of-the-art AL and SSL methods.

Massive multiple-input multiple-output (MIMO) relay can significantly improve the capacity and throughput of wireless networks, thus has been a sought-after technique for future communication systems. However, the development of massive MIMO relay systems faces several major challenges. For example, the knowledge of instantaneous channel state information (CSI) is needed to estimate signals and optimize systems. Traditional estimation schemes need to transmit pilot sequences, which occupy the spectrum resources. In this paper, we propose a tensor-based method for joint signal and channel estimation for multi-user massive MIMO relay systems without using pilot sequences, and develop two tensor-based semi-blind receivers. Through multidimensional signaling scheme, the signals received by each user are formulated as the block Tucker2-PARAFAC (TP) tensor model. Then, two semi-blind receivers are proposed to jointly estimate the information signals and channel matrices. One is based on the tensor-based closed-form receiver, the other is based on the tensor-based iterative receiver. The proposed closed-form approach can also be used to initialize the iterative receiver for improving the convergence speed. In particular, the proposed schemes are practicable for both time division duplexing (TDD) and frequency division duplexing (FDD) modes. Uniqueness, identifiability and complexity are analyzed for our receivers. Compared with existing receivers, our receivers offer superior bit error rate (BER) and normalized mean square error (NMSE) performance. Numerical examples are shown to demonstrate the effectiveness of the proposed tensor-based receivers.

For multiple-antenna systems, the technologies of joint symbol and channel parameter estimation have been developed in recent works. However, existing technologies have a number of problems, such as performance degradation and the large cost of prior information. In this paper, a tensor space-time coding scheme in multiple-antenna systems was considered. This scheme allowed spreading, multiplexing, and allocating information symbols associated with multiple transmitted data streams. We showed that the received signal was formulated as a third-order tensor satisfying a Tucker-2 model, and then a robust semi-blind receiver was developed based on the optimized Levenberg–Marquardt (LM) algorithm. Under the assumption that the instantaneous channel state information (CSI) is unknown at the receiving end, the proposed semi-blind receiver jointly estimates the information symbol and channel parameters efficiently. The proposed receiver had a better estimation performance compared with existing semi-blind receivers, and still performed well when the channel became strongly correlated. Moreover, the proposed semi-blind receiver could be extended to the multi-user massive multiple-input multiple-output (MIMO) system for joint symbol and channel estimation. Computer simulation results were shown to demonstrate the effectiveness of the proposed receiver.

Multi-modal retrieval is a challenge due to heterogeneous gap and a complex semantic relationship between different modal data. Typical research map different modalities into a common subspace with a one-to-one correspondence or similarity/dissimilarity relationship of inter-modal data, in which the distances of heterogeneous data can be compared directly; thus, inter-modal retrieval can be achieved by the nearest neighboring search. However, most of them ignore intra-modal relations and complicated semantics between multi-modal data. In this paper, we propose a deep multi-modal metric learning method with multi-scale semantic correlation to deal with the retrieval tasks between image and text modalities. A deep model with two branches is designed to nonlinearly map raw heterogeneous data into comparable representations. In contrast to binary similarity, we formulate semantic relationship with multi-scale similarity to learn fine-grained multi-modal distances. Inter-modal and intra-modal correlations constructed on multi-scale semantic similarity are incorporated to train the deep model in an end-to-end way. Experiments validate the effectiveness of our proposed method on multi-modal retrieval tasks, and our method outperforms state-of-the-art methods on NUS-WIDE, MIR Flickr, and Wikipedia datasets.

The direction-of-departure (DOD) and the direction-of-arrival (DOA) are important localization parameters in bistatic MIMO radar. In this paper, we are interested in DOD/DOA estimation of both single-pulse and multiple-pulse multiple-input multiple-output (MIMO) radars. An iterative super-resolution target localization method is firstly proposed for single-pulse bistatic MIMO radar. During the iterative process, the estimated DOD and DOA can be moved from initial angles to their true values with high probability, and thus can achieve super-resolution estimation. It works well even if the number of targets is unknown. We then extend the proposed method to multiple-pulse configuration to estimate target numbers and localize targets. Compared with existing methods, both of our proposed algorithms have a higher localization accuracy and a more stable performance. Moreover, the proposed algorithms work well even with low sampling numbers and unknown target numbers. Simulation results demonstrate the effectiveness of the proposed methods.

With the rapid development of social networks, short videos have become a popular form of content, especially dance videos. In this context, research on automatically generating music for dance videos shows significant practical value. However, existing studies face challenges such as limited richness in music timbre and lack of synchronization with dance movements. In this paper, we propose Dance2Music-Diffusion, a novel framework for music generation from dance videos using latent diffusion models. Our approach includes a motion encoder module for extracting motion features and a music diffusion generation module for generating latent music representations. By integrating dance type monitoring and latent diffusion techniques, our framework outperforms existing methods in generating complex and rich dance music. We conducted objective and subjective evaluations of the results produced by various existing models on the AIST++ dataset. Our framework shows outstanding performance in terms of beat recall rate, consistency with GT beats, and coordination with dance movements. This work represents the state of the art in automatic music generation from dance videos, is easy to train, and has implications for enhancing entertainment experiences and inspiring innovative dance productions. Sample videos of our generated music and dance can be viewed at https://youtu.be/eCvLdLdkX-Y . The code is available at https://github.com/hellto/dance2music-diffusion .