Probabilistic time series forecasting has attracted an increasing attention in machine learning community for its potential applications in the fields of renewable energy, traffic management, healthcare, etc. Previous research mainly focused on extracting long-range dependencies for point-wise prediction, which fail to capture complex temporal patterns and statistical characteristics for probabilistic analysis. In this paper, we propose a novel pattern-mixture decomposition method that decomposes long-term series into quantile drift, divergence patterns, and Gaussian mixture components, which can effectively capture the intricate temporal patterns and stochastic characteristics in time series. Based on pattern-mixture decomposition, we propose a novel Transformer-based model called QuantileFormer for probabilistic time series forecasting. It takes the the comprehensive drift-divergence mixture patterns as features, and designs a variational inference based fusion Transformer architecture to generate quantile prediction results. Extensive experiments show that the proposed method consistently boosts the baseline methods by a large margin and achieves state-of-the-art performance on six real-world benchmarks.

In this work, we present RepKPU, an efficient network for point cloud upsampling. We propose to promote upsampling performance by exploiting better shape representation and point generation strategy. Inspired by KPConv [47], we propose a novel representation called RepKPoints to effectively characterize the local geometry, whose advan-tages over prior representations are as follows: (1) density-sensitive; (2) large receptive fields; (3) position-adaptive, which makes RepKPoints a generalized form of previous representations. Moreover, we propose a novel paradigm, namely Kernel-to-Displacement generation, for point generation, where point cloud upsampling is reformulated as the deformation of kernel points. Specifically, we propose KP-Queries, which is a set of kernel points with predefined positions and learned features, to serve as the initial state of upsampling. Using cross-attention mechanisms, we achieve interactions between RepKPoints and KP-Queries, and subsequently KP-Queries are converted to displacement features, followed by a MLP to predict the new positions of KP-Queries which serve as the generated points. Extensive experimental results demonstrate that RepKPU outperforms state-of-the-art methods on several widely-used benchmark datasets with high efficiency. Codes will be available at https://github.com/EasyRy/RepKPU.

Human Activity Recognition (HAR) as an emerging research field has attracted widespread academic attention due to its wide range of practical applications in areas such as healthcare, environmental monitoring, and sports training. Given the high cost of annotating sensor data, many unsupervised and semi-supervised methods have been applied to HAR to alleviate the problem of limited data. In this paper, we propose a novel video-enhanced cross-modal collaborative learning method, Vi2ACT, to address the issue of few-shot HAR. We introduce a new data augmentation approach that utilizes a text-to-video generation model to generate class-related videos. Subsequently, a large quantity of video semantic representations are obtained through fine-tuning the video encoder for cross-modal co-learning. Furthermore, to effectively align video semantic representations and time series representations, we enhance HAR at the representation-level using conditional Generative Adversarial Nets (cGAN). We design a novel Representation Conditional Discriminator that is trained to assess samples as originating from video representations rather than those generated by the time series encoder as accurately as possible. We conduct extensive experiments on four commonly used HAR datasets. The experimental results demonstrate that our method outperforms other baseline models in all few-shot scenarios.

Speech is a natural communication way between people and a good way for human-computer interaction. However, speech with audible voices often faces the following problems, e.g., being affected by surrounding noises, breaking the quiet environment, leaking privacy, etc. Therefore, silent speech was proposed, especially lip reading, which aims to recognize speech content based on lip movements. In this paper, we utilize inaudible acoustic signals generated from mobile device to sense and recognize lip movements for lip reading. Considering the lack of public dataset in acoustic-based lip reading, we propose and release a large-scale lip-reading dataset${\sf LIPCMD}$with 30000 acoustic-based recordings. To advance the further research in lip reading, we provide benchmark evaluation on${\sf LIPCMD}$, while using traditional machine learning solutions and recent deep learning approaches. To recognize weak acoustic signals as words for lip reading, we propose a self distillation based approachLipReader, which distills the probability distribution and attention map in convolutional neural network itself for better classification. Finally, we implementLipReaderon smartphone and evaluate it on${\sf LIPCMD}$dataset as well as under complex scenarios. Experimental results show thatLipReadercan achieve a good recognition accuracy for lip reading, i.e., 91.58%, while outperforming baseline solutions and existing work.

There are two problems that widely exist in current end-to-end sign language processing architecture. One is the CTC spike phenomenon which weakens the visual representational ability in Continuous Sign Language Recognition (CSLR). The other one is the exposure bias problem which leads to the accumulation of translation errors during inference in Sign Language Translation (SLT). In this paper, we tackle these issues by introducing contrast learning, aiming to enhance both visual-level feature representation and semantic-level error tolerance. Specifically, to alleviate CTC spike phenomenon and enhance visual-level representation, we design a visual contrastive loss by minimizing visual feature distance between different augmented samples of frames in one sign video, so that the model can further explore features by utilizing numerous unlabeled frames in an unsupervised way. To alleviate exposure bias problem and improve semantic-level error tolerance, we design a semantic contrastive loss by re-inputting the predicted sentence into semantic module and comparing features of ground-truth sequence and predicted sequence, for exposing model to its own mistakes. Besides, we propose two new metrics, i.e., Blank Rate and Consecutive Wrong Word Rate to directly reflect our improvement on the two problems. Extensive experimental results on current sign language datasets demonstrate the effectiveness of our approach, which achieves state-of-the-art performance.

BACKGROUND: Metagenomics is gaining attention as a powerful tool for identifying how agricultural management practices influence human and animal health, especially in terms of potential to contribute to the spread of antibiotic resistance. However, the ability to compare the distribution and prevalence of antibiotic resistance genes (ARGs) across multiple studies and environments is currently impossible without a complete re-analysis of published datasets. This challenge must be addressed for metagenomics to realize its potential for helping guide effective policy and practice measures relevant to agricultural ecosystems, for example, identifying critical control points for mitigating the spread of antibiotic resistance. RESULTS: Here we introduce AgroSeek, a centralized web-based system that provides computational tools for analysis and comparison of metagenomic data sets tailored specifically to researchers and other users in the agricultural sector interested in tracking and mitigating the spread of ARGs. AgroSeek draws from rich, user-provided metagenomic data and metadata to facilitate analysis, comparison, and prediction in a user-friendly fashion. Further, AgroSeek draws from publicly-contributed data sets to provide a point of comparison and context for data analysis. To incorporate metadata into our analysis and comparison procedures, we provide flexible metadata templates, including user-customized metadata attributes to facilitate data sharing, while maintaining the metadata in a comparable fashion for the broader user community and to support large-scale comparative and predictive analysis. CONCLUSION: AgroSeek provides an easy-to-use tool for environmental metagenomic analysis and comparison, based on both gene annotations and associated metadata, with this initial demonstration focusing on control of antibiotic resistance in agricultural ecosystems. Agroseek creates a space for metagenomic data sharing and collaboration to assist policy makers, stakeholders, and the public in decision-making. AgroSeek is publicly-available at https://agroseek.cs.vt.edu/ .