Repetitive Action Counting (RAC) aims to estimate the number of repetitive actions in given videos, commonly found in human-centric domains like sports and exercise. However, existing methods focus on single-repetition assumption where only repetitive actions of one instance are involved, which fails to perform multi-repetition counting in real-world scenarios. In this paper, we introduce the novel task of Multi-instance Repetitive Action Counting (MRAC), which aims to simultaneously detect multiple human instances, track them over time, and count the number of repetitive actions. To this end, we propose MultiCounter+, an efficient and robust deep learning framework that incorporates several key components. Specifically, MultiCounter+ first employs the mixed spatiotemporal interaction for efficient context correlation across consecutive frames. Secondly, MultiCounter+ designs task-specific heads with spatial-temporal consistency and long-short period awareness for accurate repetition counting and robust generalization to action-agnostic repetitions. Finally, we develop an MRAC dataset (MultiRep) to train MultiCounter+ and further exploit a large-scale synthetic data pre-training pipeline to strengthen model generalizability, providing a solid foundation for adaptation to diverse action patterns and human instance counts. Extensive experiments on MultiRep and existing RAC datasets demonstrate the superior performance and generalization ability of MultiCounter+. The code and models are available at MultiCounterPlus.

As society progresses, liquid identification plays an increasingly important role in human life. But for now, minority of existing liquid identification solutions on the market can meet daily requirements of being ubiquitous, cost-effective and non-intrusive enough. In this work, we propose ASLiquid, the first liquid counterfeit identification system with commercial off-the-shelf earphones. Our core insight is that earphones can effectively induce acoustic resonance in container, and this phenomenon is observed highly associated with the changes in liquid density and solute compositions. Deploying ASLiquid introduces three main challenges: hardware heterogeneity among different earphones, diversity of user operations, and data complexity due to variations in liquid volume and device placement. To address these issues, we first propose to eliminate the existence of hardware noise and frequency response diversity for an earphone-irrelevant solution. Afterwards, we design a user operation adaptation algorithm to extract valuable feature data during each measurement period. To alleviate problems in data complexity, we propose a spectrum projection algorithm that can effectively generate CFR data of unknown liquid volumes and a VAE based anomaly detection model for counterfeit identification. We evaluate our system with six different earphones and under various conditions. Experimental results reveal that ASLiquid can achieve F1 scores of 95%-99.25% for seven frequently occurring liquid counterfeit tasks, even in specialized attacks on liquids with 1% difference in mass fraction and different types of solutions but with the same density.