Recent GS-based rendering has made significant progress for LiDAR, surpassing Neural Radiance Fields (NeRF) in both quality and speed. However, these methods exhibit artifacts in extrapolated novel view synthesis due to the incomplete reconstruction from single traversal scans. To address this limitation, we present LiDAR-GS++, a LiDAR Gaussian Splatting reconstruction method enhanced by diffusion priors for real-time and high-fidelity re-simulation on public urban roads. Specifically, we introduce a controllable LiDAR generation model conditioned on coarsely extrapolated rendering to produce extra geometry-consistent scans and employ an effective distillation mechanism for expansive LiDAR Gaussian reconstruction. By extending reconstruction to under-fitted regions, our approach ensures global geometric consistency for extrapolative novel views while preserving detailed scene surfaces captured by sensors. Experiments on multiple public datasets demonstrate that LiDAR-GS++ achieves state-of-the-art performance for both interpolated and extrapolated viewpoints, surpassing existing GS and NeRF-based methods.

Upper ocean response during tropical cyclones (TCs) represents a critical process in air-sea interactions, whose high-resolution observation is of great significance for TC intensity forecasting. Underwater gliders (UGs) are effective platforms for capturing high-resolution oceanographic data during TCs, but it remains challenging to perform high-efficiency trajectory planning of UGs in such dynamic environments. This study focuses on improving trajectory planning of UGs for high-efficiency TC observation using model predictive control (MPC) integrating genetic algorithm (briefed as MPC-GA). The upper ocean response of Typhoon Talim in 2023 is first analyzed based on UG observational data and remote sensing data, validating the UG’s capability in observing TCs. For planning UG trajectories with MPC-GA, we define the proportion of temperature anomalies to quantify UG’s observational efficiency, and apply a multilayer perceptron (MLP) model to predict the indicator based on spatiotemporal, TC scale, and oceanic parameters, which provides the optimization basis for the MPC-GA framework. Simulation results demonstrate that MPC-GA shows superior performance compared with the traditional MPC, improving the cumulative proportion of temperature anomalies by 27.5% under current-free conditions and 15.6% under ocean currents, while also reducing navigation distance. Sea trials during Typhoons Trami and Ginkgo in 2024 further validate the practicality of the proposed method, with a 27.84% improvement in cumulative proportion of temperature anomalies over the traditional MPC. This work provides a reliable and efficient framework for UG trajectory planning in TC observation, enhancing the capability to monitor the TC-induced upper ocean response.

Deep Neural Networks are vulnerable to data poisoning attacks, which inject a backdoor by poisoning the training data set with a predefined trigger pattern. However, most existing studies design trigger patterns as exogenous features introduced to clean samples (such as a checkerboard patch), whereas the endogenous features inherited from sample origins (such as deep generative models) have not been investigated yet. In this study, we investigate the efficacy of utilizing Generative Adversarial Network fingerprints to design trigger patterns by examining three attack patterns: the all-label attack, label-specific attack, and semantic-specific attack. Specifically, we select training data that satisfies the requirements of various attack patterns, train a GAN model, and employ samples embedded with GAN fingerprints to generate poisoned data sets. Our evaluations on three data sets (CIFAR-10, GTSRB, and LSUN) demonstrate that employing GAN fingerprints as trigger patterns 1) can achieve average attack success rate results of 39.40% in all-label attack, 89.84% in label-specific attack, and 91.06% in semantic-specific attack, 2) is stealthy by reducing the probability of being exposed, and 3) can resist six existing backdoor detection techniques, three backdoor erasing techniques, and two deepfake detection techniques. Furthermore, it exhibits practical applicability in federated learning scenario.

Sensor simulation is pivotal for scalable validation of autonomous driving systems, yet existing Neural Radiance Fields (NeRF) based methods face applicability and efficiency challenges in industrial workflows. This paper introduces a Gaussian Splatting (GS) based system to address these challenges: We first break down sensor simulator components and analyze the possible advantages of GS over NeRF. Then in practice, we refactor three crucial components through GS, to leverage its explicit scene representation and real-time rendering: (1) choosing the 2D neural Gaussian representation for physics-compliant scene and sensor modeling, (2) proposing a scene editing pipeline to leverage Gaussian primitives library for data augmentation, and (3) coupling a controllable diffusion model for scene expansion and harmonization. We implement this framework on a proprietary autonomous driving dataset supporting cameras and LiDAR sensors. We demonstrate through ablation studies that our approach reduces frame-wise simulation latency, achieves better geometric and photometric consistency, and enables interpretable explicit scene editing and expansion. Furthermore, we showcase how integrating such a GS-based sensor simulator with traffic and dynamic simulators enables full-stack testing of end-to-end autonomy algorithms. Our work provides both algorithmic insights and practical validation, establishing GS as a cornerstone for industrial-grade sensor simulation.

For partial differential equations on domains of arbitrary shapes, existing works of neural operators attempt to learn a mapping from geometries to solutions. It often requires a large dataset of geometry-solution pairs in order to obtain a sufficiently accurate neural operator. However, for many industrial applications, e.g., engineering design optimization, it can be prohibitive to satisfy the requirement since even a single simulation may take hours or days of computation. To address this issue, we propose reference neural operators (RNO), a novel way of implementing neural operators, i.e., to learn the smooth dependence of solutions on geometric deformations. Specifically, given a reference solution, RNO can predict solutions corresponding to arbitrary deformations of the referred geometry. This approach turns out to be much more data efficient. Through extensive experiments, we show that RNO can learn the dependence across various types and different numbers of geometry objects with relatively small datasets. RNO outperforms baseline models in accuracy by a large lead and achieves up to 80% error reduction.

Open-Set Object Detection (OSOD) aims to train detectors on closed-set datasets to detect known objects and identify unknown objects in open-set conditions. Traditional discriminative classifier-based OSOD methods struggle to accurately learn the decision boundary between known and unknown classes, often resulting in the misclassification of unknown samples. In this work, we aim to combine generative representation with discriminative classification to alleviate the issue of misclassification by transforming known-unknown recognition into a binary classification problem. The proposed two-stage OSOD approach proceeds as follows: during the generative representation stage, we employ Class-Conditioned Normalizing Flow (CCNF) to establish distribution mapping for each known category; In the discriminative classification stage, by utilizing a small number of unknown class samples, semi-push-pull supervised learning and entropy contrast learning are used to separate known and unknown classes. Extensive experiments demonstrate that our method significantly enhances OSOD performance, evidenced by a 25.8%-28.6% reduction in the Wilderness Index and a decrease of 4391-8870 units in Absolute Open-Set Errors on the test set VOC-COCO-T1.

Hybrid fuzzing, which combines fuzzing and concolic execution based on the observation that these two types of techniques are complementary, has recently become a research focus. Several hybrid fuzzing studies have shown that concolic execution can assist fuzzing in exploring deeper program states and discovering more vulnerabilities. Despite advances in hybrid fuzzing, most existing techniques employ a result-oriented scheme in which fuzzing and concolic execution cooperate by synchronizing generated test cases. Such cooperation underestimates the sophisticated analysis of concolic execution on the program. Based on the observation that concolic execution can generate abundant program states, which are desirable to be investigated for improving the performance of hybrid fuzzing, we propose a tightly-coupled hybrid fuzzing technique by excavating input specifications from concolic execution. Specifically, we define and excavate three input specification types: critical region, critical value, and type inference. We further design new fuzzing mutation algorithms to leverage them to guide the exploration of the program states. We implement three prototypes,Gear-Driller,Gear-DigFuzzandGear-QSYM, on top of Driller, DigFuzz and QSYM, respectively. Experimental results show thatGear-Driller,Gear-DigFuzzandGear-QSYMoutperform Driller, DigFuzz and QSYM with larger code coverage, more discovered vulnerabilities, and higher efficiency in finding vulnerabilities.

This project aims to explore the creation of wearable data sculptures by merging art with data visualization. By transforming abstract data into tangible physical forms, these sculptures provide a tactile and aesthetic experience. With a specific focus on bivalve species, the project seeks to highlight their biological characteristics and ecological significance. Through the use of data processing, mapping, and 3D printing techniques, the sculptures are transformed into wearable jewelry. This unique approach not only raises awareness of the close relationship between humans and bivalve species but also offers a novel and engaging way to interact with complex data.

Small object detection in remote sensing faces significant challenges such as their offset-sensitivity caused by the small area coverage, the dim targets in images, and their vulnerability to complex backgrounds, which often result in missed detections and false alarms. In this work, we propose aNoise-Adaptive Context-Aware Detector(NACAD) to alleviate the above problems, which mainly consists of a region proposal network withNoise Adaptive Module(NAM), aContext Aware Module(CAM) and aPosition Refined Module(PRM). The main contributions are threefold: 1) We leverage the information around small objects as positive-incentive noise (also known as π-noise), through enlarging the range of small objects by NAM, more anchors of them are preserved as positive samples, thus stimulating the model to detect small objects. 2) The CAM is designed to provide multiple observation perspectives and abundant contextual representations for the enhancement of object features. 3) To reduce the interference of pure noise in the complicated backgrounds around small objects, the spatial calibration along two coordinate axes is devised by PRM to optimally use information beyond object regions. The effectiveness of our proposed detector, particularly on small objects, has been validated by the experiments on two public datasets, ITCVD and HRRSD. In particular, the NAM improves the recall of small objects, CAM enhances small object features, and PRM helps address the pure noise in complicated backgrounds around small objects.

We study the task of single person dense pose estimation. Specifically, given a human-centric image, we learn to map all human pixels onto a 3D, surface-based human body model. Existing methods approach this problem by fitting deep convolutional networks on sparse annotated points where the regression on both surface coordinate components for each body part is uncorrelated and optimized separately. In this work, we devise a novel, unified loss function that explicitly characterizes the correlation for surface coordinates regression, achieving significant improvements in both accuracy and efficiency. Furthermore, based on an observation that the image-to-surface correspondence is intrinsically invariant to geometric transformations from input images, we propose to enforce a geometric equivariance consistency on the target mapping, thereby allowing us to enable reliable supervision on large amounts of unlabeled pixels. We conduct comprehensive studies on the effectiveness of our approach using a quite simple network. Extensive experiments on the DensePose-COCO dataset show that our model achieves superior performance against previous state-of-the-art methods with much less computation complexity. We hope that our work would serve as a solid baseline for future study in the field. The code will be available athttps://github.com/Johnqczhang/densepose.pytorch.

Coverage-based greybox fuzzing (CGF) has been approved to be effective in finding security vulnerabilities. Seed scheduling, the process of selecting an input as the seed from the seed pool for the next fuzzing iteration, plays a central role in CGF. Although numerous seed scheduling strategies have been proposed, most of them treat these seeds independently and do not explicitly consider the relationships among seeds.

BACKGROUND: The aim of gene expression-based clinical modelling in tumorigenesis is not only to accurately predict the clinical endpoints, but also to reveal the genome characteristics for downstream analysis for the purpose of understanding the mechanisms of cancers. Most of the conventional machine learning methods involved a gene filtering step, in which tens of thousands of genes were firstly filtered based on the gene expression levels by a statistical method with an arbitrary cutoff. Although gene filtering procedure helps to reduce the feature dimension and avoid overfitting, there is a risk that some pathogenic genes important to the disease will be ignored. RESULTS: In this study, we proposed a novel deep learning approach by combining a convolutional neural network with stationary wavelet transform (SWT-CNN) for stratifying cancer patients and predicting their clinical outcomes without gene filtering based on tumor genomic profiles. The proposed SWT-CNN overperformed the state-of-art algorithms, including support vector machine (SVM) and logistic regression (LR), and produced comparable prediction performance to random forest (RF). Furthermore, for all the cancer types, we firstly proposed a method to weight the genes with the scores, which took advantage of the representative features in the hidden layer of convolutional neural network, and then selected the prognostic genes for the Cox proportional-hazards regression. The results showed that risk stratifications can be effectively improved by using the identified prognostic genes as feature, indicating that the representative features generated by SWT-CNN can well correlate the genes with prognostic risk in cancers and be helpful for selecting the prognostic gene signatures. CONCLUSIONS: Our results indicated that gene expression-based SWT-CNN model can be an excellent tool for stratifying the prognostic risk for cancer patients. In addition, the representative features of SWT-CNN were validated to be useful for evaluating the importance of the genes in the risk stratification and can be further used to identify the prognostic gene signatures.

Video-based person re-identification plays an important role in surveillance video analysis, expanding image-based methods by learning features of multiple frames. Most existing methods fuse features by temporal average-pooling, without exploring the different frame weights caused by various viewpoints, poses, and occlusions. In this paper, we propose an attribute-driven method for feature disentangling and frame re-weighting. The features of single frames are disentangled into groups of sub-features, each corresponds to specific semantic attributes. The sub-features are re-weighted by the confidence of attribute recognition and then aggregated at the temporal dimension as the final representation. By means of this strategy, the most informative regions of each frame are enhanced and contributes to a more discriminative sequence representation. Extensive ablation studies demonstrate the effectiveness of feature disentangling as well as temporal re-weighting. The experimental results on the iLIDS-VID, PRID-2011 and MARS datasets demonstrate that our proposed method outperforms existing state-of-the-art approaches.

Person re-identification (re-ID), which aims at spotting a person of interest across multiple camera views, has gained more and more attention in computer vision community. In this paper, we propose a novel deep Siamese architecture based on convolutional neural network (CNN) and multi-level similarity perception. According to the distinct characteristics of diverse feature maps, we effectively apply different similarity constraints to both low-level and high-level feature maps, during training stage. Therefore, our network can efficiently learn discriminative feature representations at different levels, which significantly improves the re-ID performance. Besides, our framework has two additional benefits. Firstly, classification constraints can be easily incorporated into the framework, forming a unified multi-task network with similarity constraints. Secondly, as similarity comparable information has been encoded in the network's learning parameters via back-propagation, pairwise input is not necessary at test time. That means we can extract features of each gallery image and build index in an off-line manner, which is essential for large-scale real-world applications. Experimental results on multiple challenging benchmarks demonstrate that our method achieves splendid performance compared with the current state-of-the-art approaches.

In this paper, we propose an autoencoder-based generative adversarial network (GAN) for automatic image generation, which is called "stylized adversarial autoencoder". Different from existing generative autoencoders which typically impose a prior distribution over the latent vector, the proposed approach splits the latent variable into two components: style feature and content feature, both encoded from real images. The split of the latent vector enables us adjusting the content and the style of the generated image arbitrarily by choosing different exemplary images. In addition, a multiclass classifier is adopted in the GAN network as the discriminator, which makes the generated images more realistic. We performed experiments on hand-writing digits, scene text and face datasets, in which the stylized adversarial autoencoder achieves superior results for image generation as well as remarkably improves the corresponding supervised recognition task.

Anomalous events detection in real-world video scenes is a challenging problem due to the complexity of "anomaly" as well as the cluttered backgrounds, objects and motions in the scenes. Most existing methods use hand-crafted features in local spatial regions to identify anomalies. In this paper, we propose a novel model called Spatio-Temporal AutoEncoder (ST AutoEncoder or STAE), which utilizes deep neural networks to learn video representation automatically and extracts features from both spatial and temporal dimensions by performing 3-dimensional convolutions. In addition to the reconstruction loss used in existing typical autoencoders, we introduce a weight-decreasing prediction loss for generating future frames, which enhances the motion feature learning in videos. Since most anomaly detection datasets are restricted to appearance anomalies or unnatural motion anomalies, we collected a new challenging dataset comprising a set of real-world traffic surveillance videos. Several experiments are performed on both the public benchmarks and our traffic dataset, which show that our proposed method remarkably outperforms the state-of-the-art approaches.

Spectral clustering is one of the most popular clustering approaches with the capability to handle some challenging clustering problems. Only a little work of spectral clustering focuses on the explicit linear map which can be viewed as the distance metric learning. In practice, the selection of the affinity matrix exhibits a tremendous impact on the unsupervised learning. In this paper, we propose a novel method, dubbed Adaptive Affinity Matrix (AdaAM), to learn an adaptive affinity matrix and derive a distance metric. We assume the affinity matrix to be positive semidefinite with ability to quantify the pairwise dissimilarity. Our method is based on posing the optimization of objective function as a spectral decomposition problem. The provided matrix can be regarded as the optimal representation of pairwise relationship on the manifold. Extensive experiments on a number of image data sets show the effectiveness and efficiency of AdaAM.

We propose a novel method for feature description used for image matching in this paper. Our method is inspired by the autoencoder, an artificial neural network designed for learning efficient codings. Sparse and orthogonal constraints are imposed on the autoencoder and make it a highly discriminative descriptor. It is shown that the proposed descriptor is not only invariant to geometric and photometric transformations (such as viewpoint change, intensity change, noise, image blur and JPEG compression), but also highly efficient. We compare it with existing state-of-the-art descriptors on standard benchmark datasets, the experimental results show that our LSOD method yields better performance both in accuracy and efficiency.