Image restoration techniques are widely used in various fields, such as autonomous driving, medical imaging, and satellite imagery. These techniques typically aim to restore an entire degraded image to its original state. However, in many cases, users may wish to focus on restoring specific areas to achieve desired effects in the image, tailored to their preferences. In this work, we propose Restore Anything anyWhere (RAW), a framework that enables users to restore specific types of degradation on any selected object in an image by specifying point or text prompts. Our framework first employs the Multimodal Segmentation module to generate mask priors for the target objects. Then, the text-guided restoration model performs targeted restoration on the areas defined by the object mask priors. To improve segmentation performance, we propose a Text-To-Segmentation Refinement method that combines existing techniques with the capabilities of Segment Anything, enhancing text-to-segmentation accuracy. Additionally, we introduce a streamlined text-guided restoration method to provide better control over degradation restoration, delivering highly effective results. RAW provides excellent object-level control in restoration and significantly improves the Laion Aesthetics score.

This paper presents a “Microservices-based Agile Campus Surveillance Platform (MACSP)”, which aims to augment the existing Intelligent Surveillance system, CK-Fence, in order to solve the problems of high hardware resource usage and long alert latency. The MACSP has made significant progress and succeeded in reducing the memory usage and the system latency by 61.33% and 81.33%, respectively. The microservices architecture allows for step-by-step implementation and integration of various requirements into MACSP, making it scalable, extensible and reliable. It can be applied not only to campuses but can also be extended to other hazardous environments, such as urban and public area scenarios, making it a comprehensive solution that meets the ever-changing requirements in the field of Intelligent Surveillance.

Hyperbolic spaces have been quite popular in the recent past for representing hierarchically organized data. Further, several classification algorithms for data in these spaces have been proposed in the literature. These algorithms mainly use either hyperplanes or geodesics for decision boundaries in a large margin classifiers setting leading to a non-convex optimization problem. In this paper, we propose a novel large margin classifier based on horospherical decision boundaries that leads to a geodesically convex optimization problem that can be optimized using any Riemannian gradient descent technique guaranteeing a globally optimal solution. We present several experiments depicting the competitive performance of our classifier in comparison to SOTA.

Hyperbolic neural networks have been popular in the recent past due to their ability to represent hierarchical data sets effectively and efficiently. The challenge in developing these networks lies in the nonlinearity of the embedding space namely, the Hyperbolic space. Hyperbolic space is a homogeneous Riemannian manifold of the Lorentz group which is a semi-Riemannian manifold, i.e. a manifold equipped with an indefinite metric. Most existing methods (with some exceptions) use local linearization to define a variety of operations paralleling those used in traditional deep neural networks in Euclidean spaces. In this paper, we present a novel fully hyperbolic neural network which uses the concept of projections (embeddings) followed by an intrinsic aggregation and a nonlinearity all within the hyperbolic space. The novelty here lies in the projection which is designed to project data on to a lower-dimensional embedded hyperbolic space and hence leads to a nested hyperbolic space representation independently useful for dimensionality reduction. The main theoretical contribution is that the proposed embedding is proved to be isometric and equivariant under the Lorentz transformations, which are the natural isometric transformations in hyperbolic spaces. This projection is computationally efficient since it can be expressed by simple linear operations, and, due to the aforementioned equivariance property, it allows for weight sharing. The nested hyperbolic space representation is the core component of our network and therefore, we first compare this representation - independent of the network - with other dimensionality reduction methods such as tangent PCA, principal geodesic analysis (PGA) and HoroPCA. Based on this equivariant embedding, we develop a novel fully hyperbolic graph convolutional neural network architecture to learn the parameters of the projection. Finally, we present experiments demonstrating comparative performance of our network on several publicly available data sets.

In a number of disciplines, the data (e.g., graphs, manifolds) to be analyzed are non-Euclidean in nature. Geometric deep learning corresponds to techniques that generalize deep neural network models to such non-Euclidean spaces. Several recent papers have shown how convolutional neural networks (CNNs) can be extended to learn with graph-based data. In this work, we study the setting where the data (or measurements) are ordered, longitudinal or temporal in nature and live on a Riemannian manifold -- this setting is common in a variety of problems in statistical machine learning, vision and medical imaging. We show how recurrent statistical recurrent network models can be defined in such spaces. We give an efficient algorithm and conduct a rigorous analysis of its statistical properties. We perform extensive numerical experiments demonstrating competitive performance with state of the art methods but with significantly less number of parameters. We also show applications to a statistical analysis task in brain imaging, a regime where deep neural network models have only been utilized in limited ways.

Low-duty-cycle mechanisms can reduce the energy consumption in wireless sensor networks. Many related researches have been made in recent years. In the low-duty-cycle environment, the latency of sending packets from a sink to each node is much longer than traditional WSNs because nodes stay asleep most of the time. In this paper, the Centralized Cluster-based Location Finding (CCLF) algorithm is proposed to reduce the high latency in low-duty-cycle WSNs by finding a suitable position for the sink. The algorithm mainly consisted of three steps: (1) Cluster construction, (2) The fast look-up table (FLU-table) construction, and (3) Sink location decision. The simulation results show that the performance of the CCLF algorithm approaches the performance of the optimal algorithm. Moreover, the CCLF algorithm requires less operation time compared with the optimal algorithm.

The rapid development of underwater technology has opened up new possibilities and introduced new challenges for MAC and protocol designs. The packet delay reduction becomes critical issues in underwater sensor networks (USNs) since the propagation speed of water is rather slow compared with radio waves. In addition, due to the property of intermittent link connectivity in underwater, the existing message-based and synchronization-based approaches can not meet packet delivery requirements. In this paper, a tailored multihop routing protocol is designed for transmission delay reduction without packet exchanges and retransmissions. The observation of delivery analysis with different link qualities gives insights on relay nodes selection for lower delivery loss rate. To prevent excessive redundant packets, this work includes a strategy of adjusting the number of packet cloning dynamically between each hop.

The paper is about a comment on variable-range transmission power control in wireless ad hoc networks.