This study addresses the critical challenge of quickest mean-change detection (QMCD), which involves promptly detecting changes in the mean of a sequence of independent observations, particularly under the challenging condition where both pre-change and post-change distributions are unknown. A novel detector is proposed to tackle the QMCD problem. It recursively computes the backward sample average and checks whether the result escapes the forward confidence sequence, hence the name BAckward Recursive AVerage escapes Outside Confidence Sequence (BRAVO-CS). Rigorous analysis demonstrates that the proposed BRAVO-CS detector achieves an average detection delay that scales inversely with the magnitude of the mean shift-significantly better than the inverse quadratic scaling of current state-of-the-art approaches when the change is subtle. Furthermore, BRAVO-CS incurs linear time complexity, in stark contrast to the quadratic time complexity of state-of-the-art methods. Extensive simulations further confirm its robustness and efficiency across diverse scenarios, establishing BRAVO-CS as a compelling solution for real-time systems requiring rapid and reliable mean change detection.

In cross-modal music processing, translation between visual, auditory, and semantic content opens up new possibilities as well as challenges. The construction of such a transformative scheme depends upon a benchmark corpus with a comprehensive data infrastructure. In particular, the assembly of a large-scale cross-modal dataset presents major challenges. In this paper, we present the MOSA (Music mOtion with Semantic Annotation) dataset, which contains high quality 3-D motion capture data, aligned audio recordings, and note-by-note semantic annotations of pitch, beat, phrase, dynamic, articulation, and harmony for 742 professional music performances by 23 professional musicians, comprising more than 30 hours and 570 K notes of data. To our knowledge, this is the largest cross-modal music dataset with note-level annotations to date. To demonstrate the usage of the MOSA dataset, we present several innovative cross-modal music information retrieval (MIR) and musical content generation tasks, including the detection of beats, downbeats, phrases, and expressive contents from audio, video and motion data, and the generation of musicians' body motion from given music audio. The dataset and codes are available alongside this publication (https://github.com/yufenhuang/MOSA-Music-mOtion-and-Semantic-Annotation-dataset).