The underwater 3D scene reconstruction is a challenging, yet interesting problem with applications ranging from naval robots to VR experiences. The problem was successfully tackled by fully volumetric NeRF-based methods which can model both the geometry and the medium (water). Unfortunately, these methods are slow to train and do not offer real-time rendering. More recently, 3D Gaussian Splatting (3DGS) method offered a fast alternative to NeRFs. However, because it is an explicit method that renders only the geometry, it cannot render the medium and is therefore unsuited for underwater reconstruction. Therefore, we propose a novel approach that fuses volumetric rendering with 3DGS to handle underwater data effectively. Our method employs 3DGS for explicit geometry representation and a separate volumetric field (queried once per pixel) for capturing the scattering medium. This dual representation further allows the restoration of the scenes by removing the scattering medium. Our method outperforms state-of-the-art NeRF-based methods in rendering quality on the underwater SeaThru-NeRF dataset. Furthermore, it does so while offering real-time rendering performance, addressing the efficiency limitations of existing methods.

Dense video captioning is crucial for enhancing video understanding in daily applications and presents a significant challenge in multimodal analysis. Existing methods often overlook video-to-dynamic-space mapping at varying scales, resulting in captions that lack specificity and remain overly general, failing to capture real-world physical detail. To address this limitation, we propose a multi-granularity Spatio-Temporal Reasoning (STaR) approach, which integrates: (i) efficient global feature integration to model long-term temporal dependencies, (ii) spatial attention mechanisms with position encoding to capture absolute spatial information, and (iii) cross-modal feature fusion to align and unify global, local, and spatial representations. Moreover, we enhance the framework using a Large Language Model (LLM) to improve the richness and naturalness of the generated descriptions. Comparative experiments have been conducted to evaluate the effectiveness of the proposed method on SoccerNet dataset. Experimental results demonstrate that our model effectively enhances localization accuracy and generates captions with superior temporal and spatial detail fidelity. The code is available at https://github.com/bread-555/STaR.

Recognizing arbitrary or previously unseen categories is essential for comprehensive real-world 3D scene understanding. Currently, all existing methods rely on 2D or textual modalities during training or together at inference. This highlights the clear absence of a model capable of processing 3D data alone for learning semantics end-to-end, along with the necessary data to train such a model. Meanwhile, 3D Gaussian Splatting (3DGS) has emerged as the de facto standard for 3D scene representation across various vision tasks. However, effectively integrating semantic reasoning into 3DGS in a generalizable manner remains an open challenge. To address these limitations, we introduce SceneSplat, to our knowledge the first large-scale 3D indoor scene understanding approach that operates natively on 3DGS. Furthermore, we propose a self-supervised learning scheme that unlocks rich 3D feature learning from unlabeled scenes. To power the proposed methods, we introduce SceneSplat-7K, the first large-scale 3DGS dataset for indoor scenes, comprising 7916 scenes derived from seven established datasets, such as ScanNet and Matterport3D. Generating SceneSplat-7K required computational resources equivalent to 150 GPU days on an L4 GPU, enabling standardized benchmarking for 3DGS-based reasoning for indoor scenes. Our exhaustive experiments on SceneSplat-7K demonstrate the significant benefit of the proposed method over the established baselines.

In this paper, we deal with the nonlinear coupled time fractional BoussinesqCBurger equation. By using (G‘/G)- expansion method, the more new exact solutions of the nonlinear coupled time fractional Boussinesq-Burger equation are obtained in three cases. For the first two cases, we show the$\mathbf{3D}$-graphs, contour graphs and$\mathbf{2D}$-graphs through Matlab software to illustrate the effectiveness of the wave solutions.

Occupancy models have been popular in modeling imperfect detection in ecological surveys where the occupancy rate of a species is of most interest. In this paper, we incorporate the occupancy rate into likelihood and propose an empirical likelihood (EL) estimation approach associated with an EL ratio confidence interval. We show theoretically that the maximum EL estimator coincides with the maximum likelihood estimator and the EL ratio statistic of the occupancy rate asymptotically follows a chi-square distribution with one degree of freedom. An expectation-maximization (EM) algorithm is further developed from the computational perspective. Our simulation results indicate that compared with the Wald-type confidence interval, the coverage accuracy of the EL ratio confidence interval is generally more accurate, especially when the detection probability is small.

Secure Remote Password (SRP) protocol is an essential password-authenticated key exchange (PAKE) protocol based on the discrete logarithm problem (DLP). The protocol is specifically designed to obtain a session key and it has been widely used in various scenarios due to its attractive security features. In the SRP protocol, the server is not required to save any data directly associated with passwords. And this makes attackers who manage to corrupt the server fail to impersonate the client unless performing a brute-force search for the password. However, the development of quantum computing has potentially made classic DLP-based public-key cryptography schemes not secure, including the SRP protocol. So it is significant to design a quantum-resistant SRP protocol. In this paper, based on the original scheme, we propose a post-quantum SRP protocol from the learning with errors (LWE) problem. And we give rigorous proof and analyses on the correctness and security of the scheme. Besides being resistant to known quantum attacks, it maintains the various secure qualities of the original protocol.