Large-scale point cloud semantic segmentation is a challenging task due to the complexity and diversity of real-world 3D scenes. Most existing methods primarily rely on spatial coordinates to learn geometric representations without fully exploring local structural relationships. Additionally, the semantic gap between the encoder and decoder in segmentation networks is an important factor that constrains model performance. To address these challenges, we propose a novel network architecture called GAF-Net, which comprises a Geometric Contextual Feature Aggregation (GCFA) module and a Multi-scale Feature Adaptive Fusion (MFAF) module. The GCFA module consists of three primary blocks: (1) a Geometric Edge Representation block, designed to leverage spatial relative position and orientation information between the center point and its neighbors to capture detailed local geometric structural relations; (2) a Point Geometry Prior block, aimed at extracting explicit geometric priors for each point from raw point clouds. This block is lightweight and parameter-free; (3) a Geometry-Aware Attentive Pooling block, which combines semantic features with learned geometric representations, enabling the learning and aggregation of informative local contextual features. Our proposed MFAF module integrates multi-scale features by introducing an adaptive fusion approach. It effectively bridges the semantic gap between the encoder and decoder and mitigates the information loss caused by random sampling. Extensive experimental results on three large-scale benchmark datasets including S3DIS, Toronto3D, and SemanticKITTI demonstrate the superior performance of our proposed GAF-Net.

The prognostics and health management of lithium-ion batteries is extremely important for the working performance and cost of energy storage systems. Accurately forecasting battery state of health (SOH) and remaining useful life (RUL) plays an important role in ensuring reliable system operation and minimizing maintenance costs. This paper is, thus, concerned with online short-term SOH estimation and long-term RUL prediction using Brownian motion (BM) based degradation model and particle filtering (PF). The proposed model tackles the capacity degradation as the traveling distance of a Brownian particle in a given time interval. Then, the PF is used to estimate the drift parameter of the BM. This framework leads an accurate short-term SOH estimation result and gives a clear explanation for long-term RUL prediction because the first hitting time of BM follows the inverse Gaussian distribution. The predictive capability and effectiveness of the method are demonstrated by degradation datasets from different types of lithium-ion batteries. Through comparisons with other methods, the experimental results show the superiority of the proposed method in battery health prognosis and it can provide accurate and robust SOH and RUL forecasting.

For many face-related multimedia applications, low-resolution face images may greatly degrade the face recognition performance and necessitate face super-resolution(SR). Among the current SR methods, MSE-oriented SR methods often produce over-smoothed outputs and could miss some texture details while GAN-oriented SR methods may generate artifacts which are harmful to face recognition. To resolve the above issues, this paper presents a supervised pixel-wise Generative Adversarial Network (SPGAN) that can resolve a very low resolution face image of 16X16 or smaller pixel-size to its larger version of multiple scaling factors(2X, 4X, 8X and even 16X) in a unified framework. Being different from traditional unsupervised discriminators which generate a single number to represent the likelihood whether the input image is real or fake, the proposed supervised pixel-wise discriminator mainly focus on whether each pixel of the generated SR face image is as photo-realistic as its corresponding pixel in the ground-truth HR (high-resolution) face image. To further improve the face recognition performance of SPGAN, we take advantage of the face identity prior by sending two inputs to the discriminator, including an input face image (either a real HR face image or its corresponding SR face image) and its face features which are extracted from a pre-trained face recognition model. Due to the introduced face identity prior, the identity-based discriminator can pay more attention to texture details which are closely related to face recognition. Extensive experiments demonstrate that the proposed SPGAN can achieve more photo-realistic SR images and higher face recognition accuracy than some state-of-the-art methods.

As the videos captured by hand-held cameras are often perturbed by high-frequency jitters, stabilization of these videos is an essential task. Many video stabilization methods have been proposed to stabilize shaky videos. However, most methods estimate one global homography or several homographies based on fixed meshes to warp the shaky frames into their stabilized views. Due to the existence of parallax, such single or a few homographies can not well handle the depth variation. In contrast to these traditional methods, we propose a novel video stabilization network, called PWStableNet, which comes up pixel-wise warping maps, i.e., potentially different warping for different pixels, and stabilizes each pixel to its stabilized view. To our best knowledge, this is the first deep learning based pixel-wise video stabilization. The proposed method is built upon a multi-stage cascade encoder-decoder architecture and learns pixel-wise warping maps from consecutive unstable frames. Inter-stage connections are also introduced to add feature maps of a former stage to the corresponding feature maps at a latter stage, which enables the latter stage to learn the residual from the feature maps of former stages. This cascade architecture can produce more precise warping maps at latter stages. To ensure the correct learning of pixel-wise warping maps, we use a well-designed loss function to guide the training procedure of the proposed PWStableNet. The proposed stabilization method achieves comparable performance with traditional methods, but stronger robustness and much faster processing speed. Moreover, the proposed stabilization method outperforms some typical CNN-based stabilization methods, especially in videos with strong parallax. Codes will be provided at https://github.com/mindazhao/pix-pix-warping-video-stabilization.

This technical note is mainly concerned with bit rate conditions to stabilize a continuous-time scalar linear control system which transmits its feedback information through digital communication networks. It shows that when a packet is received, not only the bits inside that packet but also the receiving time instant of that packet carry information. The latter could carry a huge amount of information and can be obtained through simply receiving a packet without additional communication cost. Therefore it is an efficient way to encode information into the receiving time instant of a packet. The receiving time instant, however, cannot be accurately controlled by the sensor/sampler which can determine only sampling time instants. The difference between the sampling and receiving time instants of a packet is up to two delays, including the delay to process and encode the packet and the network delay to transmit that packet. These delays cannot be precisely known and have negative effects on the amount of information carried by receiving time instants. Under the boundedness assumption of these delays, this technical note provides some bit rate conditions to guarantee the system's input-to-state stability by making a good use of receiving time instants. Through event-triggering schemes, we realize these conditions which may require much lower stabilizing bit rates than periodic sampling schemes. Simulations are done to confirm the effectiveness of the obtained stabilizing bit rate conditions.