Sorry, you need to enable JavaScript to visit this website.

With the growing applications of water operations, water surface object detection tasks are facing new challenges. In this paper, we focus on improving the performance of water surface small object detection. Due to the limitations of single sensor in water environments, we propose RCFNet, a novel small object detection method based on radar-vision fusion. RCFNet fuses features captured by radar and camera in multiple stages to generate more effective target feature representations for small object detection on water surfaces.

Person-job fit is an essential part of online recruitment platforms in serving various downstream applications like Job Search and Candidate Recommendation. Recently, pretrained large language models have further enhanced the effectiveness by leveraging richer textual information in user profiles and job descriptions apart from user behavior features and job metadata. However, the general domain-oriented design struggles to capture the unique structural information within user profiles and job descriptions, leading to a loss of latent semantic correlations.

Generalized sliced-Wasserstein distance is a variant of sliced-Wasserstein distance that exploits the power of non-linear projection through a given defining function to better capture the complex structures of probability distributions. Similar to the sliced-Wasserstein distance, generalized sliced-Wasserstein is defined as an expectation over random projections which can be approximated by the Monte Carlo method. However, the complexity of that approximation can be expensive in high-dimensional settings.

The three-dimensional (3D) location optimization for reconfigurable intelligent surface (RIS) aided millimeter wave network is investigated. We first formulate the signal-to-noise ratio (SNR) maximization model by jointly optimizing the precoding vector, the RIS location and its parameter matrix in a multiple-input single-output downlink network. The optimal maximum ratio transmission precoding is applied, and the alternating direction method of multipliers is proposed for the highly nonlinear combinatorial problem.

3D object detection plays a crucial role in intelligent vision systems. Detection in the open world inevitably encounters various adverse scenes while most of existing methods fail in these scenes. To address this issue, this paper proposes a monocular 3D detection model, termed AEAM3D, which effectively mitigates the degradation of detection performance in various harsh environments. Additionally, we assemble a new adverse 3D object detection dataset encompassing some challenging scenes, including rainy, foggy, and low light

Unsupervised anomaly detection (UAD) is a widely adopted approach in industry due to rare anomaly occurrences and data imbalance. A desirable characteristic of an UAD model is contained generalization ability which excels in the reconstruction of seen normal patterns but struggles with unseen anomalies. Recent studies have pursued to contain the generalization capability of their UAD models in reconstruction from different perspectives, such as design of neural network (NN) structure and training strategy.

Partially Observable Markov Decision Process (POMDP) is a general framework for a wide range of control tasks, which can benefit from enabling semantic communicatons among different agents. Semantic communications aim to exchange compact messages that can convey task-relevant information between agents. A critical problem in semantic communication is source representation learning, which is governed by a fundamental tradeoff between compactness and sufficiency. Such a tradeoff is still underinvestigated in the context of POMDP.

Utilizing task-invariant prior knowledge extracted from related tasks, meta-learning is a principled framework that empowers learning a new task especially when data records are limited. A fundamental challenge in meta-learning is how to quickly "adapt" the extracted prior in order to train a task-specific model within a few optimization steps. Existing approaches deal with this challenge using a preconditioner that enhances convergence of the per-task training process.

With the increasing popularity of 3D objects in industry and everyday life, 3D object security has become essential. While there exists methods for 3D selective encryption, where a clear 3D object is encrypted so that the result has the desired level of visual security, to our knowledge, no method exists for decrypting encrypted 3D objects hierarchically. In this paper, we are the first to propose propose a method which allows us to hierarchically decrypt an encrypted 3D object according to a generated ring of keys.

Several signal processing tools are integrated into machine learning models for performance and computational cost improvements. Fourier transform (FT) and its variants, which are powerful tools for spectral analysis, are employed in the prediction of univariate time series by converting them to sequences in the spectral domain to be processed further by recurrent neural networks (RNNs). This approach increases the prediction performance and reduces training time compared to conventional methods.