We propose a novel hybrid calibration-free method FreeCap to accurately capture global multi-person motions in open environments. Our system combines a single LiDAR with expandable moving cameras, allowing for flexible and precise motion estimation in a unified world coordinate. In particular, We introduce a local-to-global pose-aware cross-sensor human-matching module that predicts the alignment among each sensor, even in the absence of calibration. Additionally, our coarse-to-fine sensor-expandable pose optimizer further optimizes the 3D human key points and the alignments, it is also capable of incorporating additional cameras to enhance accuracy. Extensive experiments on Human-M3 and FreeMotion datasets demonstrate that our method significantly outperforms state-of-the-art single-modal methods, offering an expandable and efficient solution for multi-person motion capture across various applications.

Humans naturally interact with both others and the sur-rounding multiple objects, engaging in various social activi-ties. However, recent advances in modeling human-object interactions mostly focus on perceiving isolated individuals and objects, due to fundamental data scarcity. In this pa-per, we introduce HOI-M3, a novel large-scale dataset for modeling the interactions of Multiple huMans and Multiple objects. Notably, it provides accurate 3D tracking for both humans and objects from dense RGB and object-mounted IMU inputs, covering 199 sequences and 181M frames of diverse humans and objects under rich activities. With the unique HOI-M3dataset, we introduce two novel data-driven tasks with companion strong baselines: monocular capture and unstructured generation of multiple human-object interactions. Extensive experiments demonstrate that our dataset is challenging and worthy of further research about multiple human-object interactions and behavior analysis. Our HOI-M3 dataset, corresponding codes, and pre-trained models will be disseminated to the community for future research, which can be found at https://juzezhang.github.io/HOIM3_ProjectPage/

Collaborative Filtering (CF) algorithm is the common solution to Recommender System (RS). With the development of network and storage technology, the amount of users and items in RS system is exclusively growing. How to increase the scalability and recommendation accuracy of CF are the main concerns in the related research. In this paper, an efficient implementation for user-based CF algorithm on MapReduce is presented. We exploit Bag of Word (BoW) method and design a hierarchical inverted index to further increase the scalability of our method. Meanwhile, a soft-assignment mechanism for the hierarchical inverted index is proposed to make up the recommendation accuracy decrease caused by the index. The Mapreduce implementations of our methods are detailed discussed and analyzed on both simulated data and real data, demonstrating that our implementation has the ability to scale to huge numbers of users and items, eanwhile ensures recommendation accuracy.