The latest advancements in scene relighting have been predominantly driven by inverse rendering with 3D Gaussian Splatting (3DGS). However, existing methods remain overly reliant on precise camera parameters under static illumination conditions, which is prohibitively expensive and even impractical in real-world scenarios. In this paper, we propose a novel learning from Unposed views under Varied illuminations Relightable 3D Gaussian Splatting (dubbed UV-RGS), to address this challenge by jointly optimizing camera poses, 3DGS representations, surface materials, and environment illuminations (i.e., unknown and varied lighting conditions in training) using only unposed views under varied lightings. Firstly, UV-RGS presents a viewpoint dividing strategy to group inputs into constituent units, enabling each unit can perform similar poses and illuminations. Next, for each unit, to get the constituent model, UV-RGS establishes an incrementally pose learning module to estimate coarse camera parameters, which also enjoy a proxy-view refinement to alleviate the sparse view learning. Additionally, for all constituent unit models, we introduce a holistic model learning strategy that integrates progressive unit aggregation component and the 3DGS coupled with camera poses joint optimization, which realizes the scene high-fidelity perception by the physical-based rendering. Extensive experiments on both real-world and synthetic challenging datasets demonstrate the effectiveness of UV-RGS, achieving the state-of-the-art performance for scene inverse rendering by learning 3DGS from only unposed views under varied illuminations.

In indoor scenes, the diverse distribution of object locations and scales makes the visual 3D perception task a big challenge. Previous works (e.g., NeRF-Det) have demonstrated that implicit representation has the capacity to benefit the visual 3D perception task in indoor scenes with high amount of overlap between input images. However, previous works cannot fully utilize the advancement of implicit representation because of fixed sampling and simple multi-view feature fusion. In this paper, inspired by sparse fashion method (e.g., DETR3D), we propose a simple yet effective method, NeRF-DetS, to address above issues. NeRF-DetS includes two modules: Progressive Adaptive Sampling Strategy (PASS) and Depth-Guided Simplified Multi-Head Attention Fusion (DS-MHA). Specifically, (1) PASS can automatically sample features of each layer within a dense 3D detector, using offsets predicted by the previous layer. (2) DS-MHA can not only efficiently fuse multi-view features with strong occlusion awareness but also reduce computational cost. Extensive experiments on ScanNetV2 dataset demonstrate our NeRF-DetS outperforms NeRF-Det, by achieving +5.02% and +5.92% improvement in mAP under IoU25 and IoU50, respectively. Also, NeRF-DetS shows consistent improvements on ARKITScenes.

Recent advances in 3D scene representation, particularly 3D Gaussian Splatting (3DGS), have demonstrated remarkable photorealistic rendering capabilities. However, the heavy reliance on dense and precisely calibrated camera configurations limits effectiveness in sparse view and unposed scenarios. In this paper, we present Tri-consistency 3D Gaussian Splatting (dubbed TriGS), a novel framework that jointly optimizes 3DGS parameters and camera poses only from sparse and unposed images via triple consistency supervisions coupled with the adaptive regularization strategy. We first estimate coarse camera poses by exploiting 3DGS's anisotropic properties through iterative relative pose optimization. Building upon this foundation, we introduce cross-view consistency enforcement through synchronized photometric color, geometric structure, and deep feature, effectively resolving rendering ambiguities with auxiliary supervisions. A unified rendering paradigm is also proposed to jointly refine Gaussian primitives and camera poses by transforming positions, covariances, and spherical harmonics. To combat overfitting inherent in joint optimization, we devise an adaptive regularization mechanism that strategically samples hard viewpoints based on baseline distances and training dynamics, enforcing projection consistency through deep feature priors. Extensive experiments on multiple challenging real-world datasets validate the effectiveness of TriGS, which achieves satisfactory results to set a new state-of-the-art without the reliance on external pose priors only under sparse and unposed view inputs.

This paper explores the asymptotic synchronization of drive-response Markovian jump Boolean networks (MJBNs) using an algebraic state space representation. For two switching signals, an augmented variable is introduced, recasting the synchronization problem into an asymptotic set stability challenge. Initially, a criterion is developed to identify all nonnegative solutions of a related equation via stochastic processes. Then, an alternative criterion based on invariant subsets and the largest singular value is proposed, where the equivalence of the proposed two criteria is demonstrated. Contrasting with deterministic BNs, where synchronization methods depend on finite power of state transition matrices, the criteria for MJBNs involve a more intricate approach. Numerical examples are included to validate the effectiveness of the proposed theoretical concepts.

The latest progress in novel view synthesis can be attributed to the Neural Radiance Field (NeRF), which requires densely sampled images with precise camera poses. However, collecting dense input images for a NeRF with accurate camera poses is highly expensive in many real-world scenarios. In this paper, we propose to learn Geometry Consistent Neural Radiance Field (GC-NeRF), to tackle this challenge by jointly optimizing a NeRF and its corresponding camera poses with sparse (as low as 2) and unposed views. First, the proposed GC-NeRF establishes image-level geometric consistencies, by producing photometric constraints from inter- and intra-views to update the NeRF and the camera poses in a fine-grained manner. Then, we adopt geometry projection with camera extrinsic parameters to further provide region-level consistency supervisions, which constructs pseudo-pixel labels to capture critical matching correlations. Moreover, we present an adaptive high-frequency mapping function to augment the geometry and texture information of the 3D scene. Extensive experiments on multiple challenging real-world datasets validate the effectiveness of the proposed GC-NeRF, which sets a new state-of-the-art for effectively learning NeRF with sparse and unposed views.

In real networks, communication constraints often prevent the full exchange of information between nodes, which is inevitable. This brief investigates the problem of time delay and randomly missing data in Boolean networks (BNs). A Bernoulli random variable is assigned to each node to characterize the probability of data packet dropout. Time delay and missing data are modeled by independent random variables. A novel data-sending rule that incorporates both communication constraints is proposed. An augmented system, comprising current states, delayed information, and successfully transmitted data, is established for theoretical analysis. Using the semitensor product (STP), the necessary and sufficient condition for asymptotic stability of delayed BNs with random data dropouts is derived. The convergence rate is also obtained.

Two synchronization problems, synchronization with probability one and synchronization in probability, are investigated for an array of coupled probabilistic Boolean networks (CPBNs). Compared with the former one, the in-probability problem considers a more general situation, in which synchronization can be achieved with a positive probability, instead of strictly 100%. It reflects the intrinsic randomness of biological systems. For both problems, some necessary and sufficient conditions are proposed, based on which two feasible algorithms are presented for checking two kinds of synchronization, respectively. CPBNs can be seemed as a combination of coupled Boolean networks (CBNs) with assigned probabilities. There are also detailed discussions on the impact of the synchronism of CBNs on the two addressed synchronization problems. The existence of invariant synchronization subsets is studied, which deepens our understanding on the difference and difficulty of these problems. Finally, numerical simulations show the effectiveness of the theoretical results.

Multi-label text classification (MLTC) aims to annotate documents with the most relevant labels from a number of candidate labels. In real applications, the distribution of label frequency often exhibits a long tail, i.e., a few labels are associated with a large number of documents (a.k.a. head labels), while a large fraction of labels are associated with a small number of documents (a.k.a. tail labels). To address the challenge of insufficient training data on tail label classification, we propose a Head-to-Tail Network (HTTN) to transfer the meta-knowledge from the data-rich head labels to data-poor tail labels. The meta-knowledge is the mapping from few-shot network parameters to many-shot network parameters, which aims to promote the generalizability of tail classifiers. Extensive experimental results on three benchmark datasets demonstrate that HTTN consistently outperforms the state-of-the-art methods. The code and hyper-parameter settings are released for reproducibility.

The synchronization of a class variable-coefficient complex networks with reaction-diffusion terms is investigated. The objective of this article is to synthesize a state-feedback controller, which is designed based on a Takagi-Sugeno (T-S) fuzzy model of the variable-coefficient complex network with reaction-diffusion terms such that the closed-loop system is synchronized. With the support of Green formula and some matrix inequality techniques, and utilizing the upper and lower bounds of the membership functions, membership-function-dependent (MFD) synchronization conditions guaranteeing the system's synchronization are obtained in the form of linear matrix inequalities (LMIs). A numerical example is presented to verify the analysis results and illustrate the effectiveness of the proposed synchronization conditions.

This article studies the stability in probability of probabilistic Boolean networks and stabilization in the probability of probabilistic Boolean control networks. To simulate more realistic cellular systems, the probability of stability/stabilization is not required to be a strict one. In this situation, the target state is indefinite to have a probability of transferring to itself. Thus, it is a challenging extension of the traditional probability-one problem, in which the self-transfer probability of the target state must be one. Some necessary and sufficient conditions are proposed via the semitensor product of matrices. Illustrative examples are also given to show the effectiveness of the derived results.

This study is concerned with probabilistic Boolean control networks (PBCNs) with state feedback control. A novel definition of bisimilar PBCNs is proposed to lower computational complexity. To understand more on bisimulation relations between PBCNs, we resort to a powerful matrix manipulation called semi-tensor product (STP). Because stabilization of networks is of critical importance, the propagation of stabilization with probability one between bisimilar PBCNs is then considered and proved to be attainable. Additionally, the transient periods (the maximum number of steps to implement stabilization) of two PBCNs are certified to be identical if these two networks are paired with a bisimulation relation. The results are then extended to the probabilistic Boolean networks.

Personalized microblog recommendations face challenges of user cold-start problems and the interest evolution of topics. In this paper, we propose a collaborative filtering recommendation algorithm based on a temporal interest evolution model and social tag prediction. Three matrices are first prepared to model the relationship between users, tags, and microblogs. Then the scores of the tags for each microblog are optimized according to the interest evolution model of tags. In addition, to address the user cold-start problem, a social tag prediction algorithm based on community discovery and maximum tag voting is designed to extract candidate tags for users. Finally, the joint probability of a tag for each user is calculated by integrating the Bayes probability on the set of candidate tags, and the top n microblogs with the highest joint probabilities are recommended to the user. Experiments using datasets from the microblog of Sina Weibo showed that our algorithm achieved good recall and precision in terms of both overall and temporal performances. A questionnaire survey proved user satisfaction with recommendation results when the cold-start problem occurred.

Communication constraints, which may lead to the degradation of performance, are common and unavoidable in a real-world network. In this paper, two kinds of communication constraints are considered during the process of information transmission in Takagi-Sugeno (TS) fuzzy complex network: 1) partial couplings, where only some part of nodes' state information can be transmitted and the channel matrices are introduced to reflect such a phenomenon; and 2) discrete-time couplings, where the nodes' information are sampled at certain time instants. This is the first time when both communication constraints are simultaneously considered in fuzzy complex networks. Compared with the perfect communication, much less information is available for synchronization. To overcome this difficulty, a regrouping method is employed to reconstruct the fuzzy network. The concise conditions are then proposed to ensure pinning synchronization of fuzzy complex networks with partial and discrete-time couplings. Simulation examples are also provided to demonstrate the effectiveness of the theoretical results.

This paper is concerned with the distributed H∞filtering problem for a class of sensor networks with hybrid communication constraints. Three kinds of communications constraints are considered during the process of information transmission among the sensors: (i) the estimation of sensors needs to be sampled before transmitting; (ii) at each sampling instant, the packet dropouts would happen to the sampled data of sensors; (iii) the noise and disturbance exist. It should be noted that the constraints of sampled information and data packet dropouts would lead that less information can be employed for each sensor, which makes the filtering problem in sensor networks more challenging and practical. Some criteria concerning the connection gains are derived and used to design efficient distributed H∞filter to achieve the following objectives: (i) the filtering error system is exponentially mean-square stable in the absence of disturbance and noise; (ii) the prescribed H∞performance constraint is satisfied. A numerical example is utilized to illustrate the effectiveness of the theoretical results.

In this paper, a new control strategy is proposed for the synchronization of stochastic dynamical networks with nonlinear coupling. Pinning state feedback controllers have been proved to be effective for synchronization control of state-coupled dynamical networks. We will show that pinning impulsive controllers are also effective for synchronization control of the above mentioned dynamical networks. Some generic mean square stability criteria are derived in terms of algebraic conditions, which guarantee that the whole state-coupled dynamical network can be forced to some desired trajectory by placing impulsive controllers on a small fraction of nodes. An effective method is given to select the nodes which should be controlled at each impulsive constants. The proportion of the controlled nodes guaranteeing the stability is explicitly obtained, and the synchronization region is also derived and clearly plotted. Numerical simulations are exploited to demonstrate the effectiveness of the pinning impulsive strategy proposed in this paper.

Based on SMIC 0.18 μm 1.8v six-layer-metal CMOS process, we implement a 64-bit high speed pipelined floating point adder which satisfied IEEE 754 standard. After the critical path analysis of the pipelined structure, we custom design three macro modules in order to reduce critical path delay. After placement in datapath style and routing, we implement the layout of floating point adder. The chip area is 1.44 mm2 and clock frequency is 518MHz.