LiDAR-based 3D object detection is widely used in safety-critical systems. However, these systems remain vulnerable to backdoor attacks that embed hidden malicious behaviors during training. A key limitation of existing backdoor attacks is their lack of physical realizability, primarily due to the digital-to-physical domain gap. Digital triggers often fail in real-world settings because they overlook material-dependent LiDAR reflection properties. On the other hand, physically constructed triggers are often unoptimized, leading to low effectiveness or easy detectability. This paper introduces Material-Oriented Backdoor Attack (MOBA), a novel framework that bridges the digital–physical gap by explicitly modeling the material properties of real-world triggers. MOBA tackles two key challenges in physical backdoor design: 1) robustness of the trigger material under diverse environmental conditions, 2) alignment between the physical trigger's behavior and its digital simulation. First, we propose a systematic approach to selecting robust trigger materials, identifying titanium dioxide (TiO₂) for its high diffuse reflectivity and environmental resilience. Second, to ensure the digital trigger accurately mimics the physical behavior of the material-based trigger, we develop a novel simulation pipeline that features: (1) an angle-independent approximation of the Oren–Nayar BRDF model to generate realistic LiDAR intensities, and (2) a distance-aware scaling mechanism to maintain spatial consistency across varying depths. We conduct extensive experiments on state-of-the-art LiDAR-based and Camera-LiDAR fusion models, showing that MOBA achieves a 93.50% attack success rate, outperforming prior methods by over 41%. Our work reveals a new class of physically realizable threats and underscores the urgent need for defenses that account for material-level properties in real-world environments.

The rapid advancement of vision-language models (VLMs) has established a new paradigm in video anomaly detection (VAD): leveraging VLMs to simultaneously detect anomalies and provide comprehendible explanations for the decisions. Existing work in this direction often assumes the complex reasoning required for VAD exceeds the capabilities of pretrained VLMs. Consequently, these approaches either incorporate specialized reasoning modules during inference or rely on instruction tuning datasets through additional training to adapt VLMs for VAD. However, such strategies often incur substantial computational costs or data annotation overhead. To address these challenges in explainable VAD, we introduce a verbalized learning framework named VERA that enables VLMs to perform VAD without model parameter modifications. Specifically, VERA automatically decomposes the complex reasoning required for VAD into reflections on simpler, more focused guiding questions capturing distinct abnormal patterns. It treats these reflective questions as learnable parameters and optimizes them through data-driven verbal interactions between learner and optimizer VLMs, using coarsely labeled training data. During inference, VERA embeds the learned questions into model prompts to guide VLMs in generating segment-level anomaly scores, which are then refined into frame-level scores via the fusion of scene and temporal contexts. Experimental results on challenging benchmarks demonstrate that the learned questions of VERA are highly adaptable, significantly improving both detection performance and explainability of VLMs for VAD.

Few-shot learning (FSL) through the training of few labeled samples in the source domain and fine-tuning in target domain has gotten increasing attention in hyperspectral images (HSI) classification. However, in current FSL for HSI classification (HSIC), the number of classes trained in the source domain feature extractor is contingent upon the aligned class number with task classes, which restricts the availability and generalization of the transferable knowledge learned in the source domain. In this article, we propose a few-shot learning with class-number non-aligned training and feature differential network for hyperspectral image classification. Firstly, a class-number non-aligned FSL training framework on multiple independent sources is established, where each source trains respective classes, eliminating the need for aligning the number of classes with the target's. Secondly, in order to learn the feature brought by different domains at different scales, an attention-guided cross-scale feature differential network is constructed to obtain feature differentials between neighboring layers through a feature differential unit (FDU), which extracts detailed pixel's differential information and facilitates to exploit feature variations at different scales. Furthermore, to alleviate the training burden generated by multiple source domains from the non-aligned training strategy, a hybrid loss function is devised to augment the inter-class distance while reducing the intra-class distance. Experiments conducted on three public hyperspectral datasets demonstrate that the proposed model outperforms existing FSL methods for Hyperspectral image classification.

Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations ("slots") from images, unconditional generation of scenes from slots has received less attention. This is primarily because learning the multiobject relations necessary to imagine coherent scenes is difficult. We hypothesize that most existing slot-based models have a limited ability to learn object correlations. We propose two improvements that strengthen object correlation learning. The first is to condition the slots on a global, scene-level variable that captures higher-order correlations between slots. Second, we address the fundamental lack of a canonical order for objects in images by proposing to learn a consistent order to use for the autoregressive generation of scene objects. Specifically, we train an autoregressive slot prior to sequentially generate scene objects following a learned order. Ordered slot inference entails first estimating a randomly ordered set of slots using existing approaches for extracting slots from images, then aligning those slots to ordered slots generated autoregressively with the slot prior. Our experiments across three multiobject environments demonstrate clear gains in unconditional scene generation quality. Detailed ablation studies are also provided that validate the two proposed improvements.

Hyperspectral images (HSI) have spectral variability, which leads to spectral dependence in adjacent and non-adjacent regions, and this dependence is essential for the classification of regions with mixed pixels. Current neural architecture search (NAS) methods have achieved significant advantages in HSI classification, but these methods cannot capture spectral dependence in non-adjacent regions because only use feedforward connections. Meanwhile, the cost of the search process in NAS is proportional to the scale of the search space, which limits the expansion of the search space. To address these issues, we propose a sparse-coding-inspired feedback neural architecture search (SCIF-NAS) method for HSI classification. Firstly, we view HSI samples as sequences and introduce a feedback mechanism in NAS to model the spectral dependence of non-adjacent regions to mitigate the effects of spectral variation. Secondly, we design several feedforward operations according to the characteristics of HSI, to form the search space together with feedback operations. Meanwhile, a sparse-coding-inspired NAS accelerated strategy is introduced to alleviate the search time burden caused by the expansion of search space. Thirdly, we integrate center loss with cross-entropy loss to construct a hybrid loss function that helps to obtain a better classification boundary. Finally, we conduct experiments on three popular HSI benchmarks, which show that SCIF-NAS outperforms the state-of-the-art methods in HSI classification.

Most existing perception systems rely on sensory data acquired from cameras, which perform poorly in low light and adverse weather conditions. To resolve this limitation, we have witnessed advanced LiDAR sensors become popular in perception tasks in autonomous driving applications. Nevertheless, their usage in traffic monitoring systems is less ubiquitous. We identify two significant obstacles in cost-effectively and efficiently developing such a LiDAR-based traffic monitoring system: (i) public LiDAR datasets are insufficient for supporting perception tasks in infrastructure systems, and (ii) 3D annotations on LiDAR point clouds are time-consuming and expensive. To fill this gap, we present an efficient semi-automated annotation tool that automatically annotates LiDAR sequences with tracking algorithms while offering a fully annotated infrastructure LiDAR dataset—FLORIDA (Florida LiDAR-based Object Recognition and Intelligent Data Annotation)—which will be made publicly available. Our advanced annotation tool seamlessly integrates multi-object tracking (MOT), single-object tracking (SOT), and suitable trajectory post-processing techniques. Specifically, we introduce a human-in-the-loop schema in which annotators recursively fix and refine annotations imperfectly predicted by our tool and incrementally add them to the training dataset to obtain better SOT and MOT models. By repeating the process, we significantly increase the overall annotation speed by$3- 4$times and obtain better qualitative annotations than a state-of-the-art annotation tool. The human annotation experiments verify the effectiveness of our annotation tool. In addition, we provide detailed statistics and object detection evaluation results for our dataset in serving as a benchmark for perception tasks at traffic intersections.

We present a new approach to unsupervised shape correspondence learning between pairs of point clouds. We make the first attempt to adapt the classical locally linear embedding algorithm (LLE)-originally designed for nonlinear dimensionality reduction-for shape correspondence. The key idea is to find dense correspondences between shapes by first obtaining high-dimensional neighborhood-preserving embeddings of low-dimensional point clouds and subsequently aligning the source and target embeddings using locally linear transformations. We demonstrate that learning the embedding using a new LLE-inspired point cloud reconstruction objective results in accurate shape correspondences. More specifically, the approach comprises an end-to-end learnable framework of extracting high-dimensional neighborhood-preserving embeddings, estimating locally linear transformations in the embedding space, and reconstructing shapes via divergence measure-based alignment of probability density functions built over reconstructed and target shapes. Our approach enforces embeddings of shapes in correspondence to lie in the same universal/canonical embedding space, which eventually helps regularize the learning process and leads to a simple nearest neighbors approach between shape embeddings for finding reliable correspondences. Comprehensive experiments show that the new method makes noticeable improvements over state-of-the-art approaches on standard shape correspondence benchmark datasets covering both human and nonhuman shapes.

In this paper, we present a new self-supervised scene flow estimation approach for a pair of consecutive point clouds. The key idea of our approach is to represent discrete point clouds as continuous probability density functions using Gaussian mixture models. Scene flow estimation is therefore converted into the problem of recovering motion from the alignment of probability density functions, which we achieve using a closed-form expression of the classic Cauchy-Schwarz divergence. Unlike existing nearest-neighbor-based approaches that use hard pairwise correspondences, our proposed approach establishes soft and implicit point correspondences between point clouds and generates more robust and accurate scene flow in the presence of missing correspondences and outliers. Comprehensive experiments show that our method makes noticeable gains over the Chamfer Distance and the Earth Mover’s Distance in real-world environments and achieves state-of-the-art performance among self-supervised learning methods on FlyingThings3D and KITTI, even outperforming some supervised methods with ground truth annotations.

Existing malware detectors on safety-critical devices have difficulties in runtime detection due to the performance overhead. In this article, we introduce Propedeutica, a framework for efficient and effective real-time malware detection, leveraging the best of conventional machine learning (ML) and deep learning (DL) techniques. In Propedeutica, all software start executions are considered as benign and monitored by a conventional ML classifier for fast detection. If the software receives a borderline classification from the ML detector (e.g., the software is 50% likely to be benign and 50% likely to be malicious), the software will be transferred to a more accurate, yet performance demanding DL detector. To address spatial-temporal dynamics and software execution heterogeneity, we introduce a novel DL architecture (DeepMalware) for Propedeutica with multistream inputs. We evaluated Propedeutica with 9115 malware samples and 1338 benign software from various categories for the Windows OS. With a borderline interval of [30%, 70%], Propedeutica achieves an accuracy of 94.34% and a false-positive rate of 8.75%, with 41.45% of the samples moved for DeepMalwareanalysis. Even using only CPU, Propedeutica can detect malware within less than 0.1 s.

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either impractical due to long training times and large memory consumption or forego key inductive biases. In this work, we introduce EfficientMORL, an efficient framework for the unsupervised learning of object-centric representations. We show that optimization challenges caused by requiring both symmetry and disentanglement can in fact be addressed by high-cost iterative amortized inference by designing the framework to minimize its dependence on it. We take a two-stage approach to inference: first, a hierarchical variational autoencoder extracts symmetric and disentangled representations through bottom-up inference, and second, a lightweight network refines the representations with top-down feedback. The number of refinement steps taken during training is reduced following a curriculum, so that at test time with zero steps the model achieves 99.1% of the refined decomposition performance. We demonstrate strong object decomposition and disentanglement on the standard multi-object benchmark while achieving nearly an order of magnitude faster training and test time inference over the previous state-of-the-art model.

The egocentric video provides a unique view of event participants to show their attention, vision, and interaction with objects. In this paper, we introduce Ego-Deliver, a new large-scale egocentric video benchmark recorded by takeaway riders about their daily work. To the best of our knowledge, Ego-Deliver presents the first attempt in understanding activities from the takeaway delivery process while being one of the largest egocentric video action datasets to date. Our dataset provides a total of 5,360 videos with more than 139,000 multi-track annotations and 45 different attributes, which we believe is pivotal to future research in this area. We introduce the FS-Net architecture, a new anchor-free action detection approach handling extreme variations of action durations. We partition videos into fragments and build dynamic graphs over fragments, where multi-fragment context information is aggregated to boost fragment classification. A splicing and scoring module is applied to obtain final action proposals. Our experimental evaluation confirms that the proposed framework outperforms existing approaches on the proposed Ego-Deliver benchmark and is competitive on other popular benchmarks. In our current version, Ego-Deliver is used to make a comprehensive comparison between algorithms for activity detection. We also show its application to action recognition with promising results. The dataset, toolkits and baseline results will be made available at: https://egodeliver.github.io/EgoDeliver_Dataset/

In this paper, we present a novel and effective approach to truck and trailer classification, which integrates deep learning models and conventional image processing and computer vision techniques. The developed method groups trucks into subcategories by carefully examining the truck classes and identifying key geometric features for discriminating truck and trailer types. We also present three discriminating features that involve shape, texture, and semantic information to identify trailer types. Experimental results demonstrate that the developed hybrid approach can achieve high accuracy with limited training data, where the vanilla deep learning approaches show moderate performance due to over-fitting and poor generalization. Additionally, the models generated are human-understandable.

We propose SparsePipe, an efficient and asynchronous parallelism approach for handling 3D point clouds with multi-GPU training. SparsePipe is built to support 3D sparse data such as point clouds. It achieves this by adopting generalized convolutions with sparse tensor representation to build expressive high-dimensional convolutional neural networks. Compared to dense solutions, the new models can efficiently process irregular point clouds without densely sliding over the entire space, significantly reducing the memory requirements and allowing higher resolutions of the underlying 3D volumes for better performance. SparsePipe exploits intra-batch parallelism that partitions input data into multiple processors and further improves the training throughput with inter-batch pipelining to overlap communication and computing. Besides, it suitably partitions the model when the GPUs are heterogeneous such that the computing is load-balanced with reduced communication overhead. Using experimental results on an eight-GPU platform, we show that SparsePipe can parallelize effectively and obtain better performance on current point cloud benchmarks for both training and inference, compared to its dense solutions.

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks (DNNs) have been recently found vulnerable to well-designed input samples called adversarial examples. Adversarial perturbations are imperceptible to human but can easily fool DNNs in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying DNNs in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for DNNs, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples. In addition, three major challenges in adversarial examples and the potential solutions are discussed.

We present a novel single-shot text detector that directly outputs word-level bounding boxes in a natural image. We propose an attention mechanism which roughly identifies text regions via an automatically learned attentional map. This substantially suppresses background interference in the convolutional features, which is the key to producing accurate inference of words, particularly at extremely small sizes. This results in a single model that essentially works in a coarse-to-fine manner. It departs from recent FCN-based text detectors which cascade multiple FCN models to achieve an accurate prediction. Furthermore, we develop a hierarchical inception module which efficiently aggregates multi-scale inception features. This enhances local details, and also encodes strong context information, allowing the detector to work reliably on multi-scale and multi-orientation text with single-scale images. Our text detector achieves an F-measure of 77% on the ICDAR 2015 benchmark, advancing the state-of-the-art results in [18, 28]. Demo is available at: http://sstd.whuang.org/.

We develop a Deep-Text Recurrent Network (DTRN)that regards scene text reading as a sequence labelling problem. We leverage recent advances of deep convolutional neural networks to generate an ordered highlevel sequence from a whole word image, avoiding the difficult character segmentation problem. Then a deep recurrent model, building on long short-term memory (LSTM), is developed to robustly recognize the generated CNN sequences, departing from most existing approaches recognising each character independently. Our model has a number of appealing properties in comparison to existing scene text recognition methods: (i) It can recognise highly ambiguous words by leveraging meaningful context information, allowing it to work reliably without either pre- or post-processing; (ii) the deep CNN feature is robust to various image distortions; (iii) it retains the explicit order information in word image, which is essential to discriminate word strings; (iv) the model does not depend on pre-defined dictionary, and it can process unknown words and arbitrary strings. It achieves impressive results on several benchmarks, advancing the-state-of-the-art substantially.

In virtualized system, both redundancy and inspection-based maintenance has been used to maintain reliability. Analysis is often conducted on a single strategy, and the overall impact of a joint mechanism has not been analyzed in detail. So, a method is presented to analyze the reliability and performance of virtualized system with the joint mechanism. The reliability and performance indicators are based on the Markov chain constructed from the state transition diagram for the joint mechanism. Sensitivity analysis is conducted to analyze the impact of system configuration parameters change. Empirical studies show the process of evaluation model and sensitivity analysis. Changing the value of redundancy and inspection rate value, the system reliability and performance could be calculated through the analysis method. The increase of redundancy leads to the increase of reliability and performance rate. Whereas, the increase in inspection rate could only improve the performance to an extent. The influence of both parameters declines rapidly as the value increases.

This article presents an emulation and program context reconstruction tool for a real-time high-precision positioning embedded system. This tool records the context of the embedded software in the operation without affecting runtime behavior. The execution procedure is re-created on a host machine off-line through reconstruction. This approach successfully accelerates the debugging and fault diagnosis process of transient or intermittent errors during the run time.

As availability of web service has become a great concern in SOA, monitoring mechanism is often deployed to detect and recover failures for service composition. While monitoring mechanism could improve the availability to an extent, it may cost more resources and increase the response time perceived by end users. To decrease the overall usage of monitoring resources, this paper proposes to select some services bringing the highest availability improvement to the composition and allocate monitors on them while leaving others unmonitored. This paper first researched two common monitoring mechanisms in service composition and analyzed their different impact on the service composition QoS values. Then continuous-time Markov chain and discrete-time Markov chain were employed to build the availability model related to the monitoring rate or service pool size according to different kind of monitoring mechanisms. Based on these models, two algorithms were proposed, for two monitoring mechanisms respectively, to allocate monitors in the composition aiming at minimizing the overall number of monitors while making sure the composition availability could meet certain requirements. The monitor allocation algorithm could be used to get the overall number of monitors and those services to monitor in different scenarios. Empirical studies results showed that it was feasible to monitor only some services in the composition to meet certain availability requirement. Monitors allocation decreased the overall number of monitors in the service composition and also decreased the mean response time comparing with the scenario that all services were monitored.