Related papers: Decorrelating the Future: Joint Frequency Domain L…

Semantic communication can significantly improve bandwidth utilization in wireless systems by exploiting the meaning behind raw data. However, the advancements achieved through semantic communication are closely dependent on the development…

Glaucoma is one of the major eye diseases that leads to progressive optic nerve fiber damage and irreversible blindness, afflicting millions of individuals. Glaucoma forecast is a good solution to early screening and intervention of…

Leveraging spatio-temporal correlations among wind farms can significantly enhance the accuracy of ultra-short-term wind power forecasting. However, the complex and dynamic nature of these correlations presents significant modeling…

Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial…

This paper proposes a new loss using short-time Fourier transform (STFT) spectra for the aim of training a high-performance neural speech waveform model that predicts raw continuous speech waveform samples directly. Not only amplitude…

Federated learning (FL) is a useful tool in distributed machine learning that utilizes users' local datasets in a privacy-preserving manner. When deploying FL in a constrained wireless environment; however, training models in a…

Cross-domain few-shot learning (CD-FSL) aims to recognize novel classes with only a few labeled examples under significant domain shifts. While recent approaches leverage a limited amount of labeled target-domain data to improve…

Domain adaptation addresses the challenge of model performance degradation caused by domain gaps. In the typical setup for unsupervised domain adaptation, labeled data from a source domain and unlabeled data from a target domain are used to…

Spatio-temporal (ST) data, which represent multiple time series data corresponding to different spatial locations, are ubiquitous in real-world dynamic systems, such as air quality readings. Forecasting over ST data is of great importance…

Many super-resolution (SR) models are optimized for high performance only and therefore lack efficiency due to large model complexity. As large models are often not practical in real-world applications, we investigate and propose novel loss…

Federated learning (FL) has emerged as a new paradigm for privacy-preserving collaborative training. Under domain skew, the current FL approaches are biased and face two fairness problems. 1) Parameter Update Conflict: data disparity among…

In the current monocular depth research, the dominant approach is to employ unsupervised training on large datasets, driven by warped photometric consistency. Such approaches lack robustness and are unable to generalize to challenging…

Time series forecasting has played the key role in different industrial, including finance, traffic, energy, and healthcare domains. While existing literatures have designed many sophisticated architectures based on RNNs, GNNs, or…

Extrapolating future weather radar echoes from past observations is a complex task vital for precipitation nowcasting. The spatial morphology and temporal evolution of radar echoes exhibit a certain degree of correlation, yet they also…

As deep spatio-temporal neural networks are increasingly utilised in urban computing contexts, the deployment of such methods can have a direct impact on users of critical urban infrastructure, such as public transport, emergency services,…

Time series forecasting (TSF) holds significant importance in modern society, spanning numerous domains. Previous representation learning-based TSF algorithms typically embrace a contrastive learning paradigm featuring segregated…

Multimodal time series forecasting is crucial in real-world applications, where decisions depend on both numerical data and contextual signals. The core challenge is to effectively combine temporal numerical patterns with the context…

Deep learning models are modern tools for spatio-temporal graph (STG) forecasting. Though successful, we argue that data scarcity is a key factor limiting their recent improvements. Meanwhile, contrastive learning has been an effective…

Individual trajectories, rich in human-environment interaction information across space and time, serve as vital inputs for geospatial foundation models (GeoFMs). However, existing attempts at learning trajectory representations have…

Stereo matching and flow estimation are two essential tasks for scene understanding, spatially in 3D and temporally in motion. Existing approaches have been focused on the unsupervised setting due to the limited resource to obtain the…