Model fusion is becoming a crucial component in the context of model-as-a-service scenarios, enabling the delivery of high-quality model services to local users. However, this approach introduces privacy risks and imposes certain limitations on its applications. Ensuring secure model exchange and knowledge fusion among users becomes a significant challenge in this setting. To tackle this issue, we propose PrivFusion, a novel architecture that preserves privacy while facilitating model fusion under the constraints of local differential privacy. PrivFusion leverages a graph-based structure, enabling the fusion of models from multiple parties without necessitating retraining. By employing randomized mechanisms, PrivFusion ensures privacy guarantees throughout the fusion process. To enhance model privacy, our approach incorporates a hybrid local differentially private mechanism and decentralized federated graph matching, effectively protecting both activation values and weights. Additionally, we introduce a perturbation filter adapter to alleviate the impact of randomized noise, thereby preserving the utility of the fused model. Through extensive experiments conducted on diverse image datasets and real-world healthcare applications, we provide empirical evidence showcasing the effectiveness of PrivFusion in maintaining model performance while preserving privacy. Our contributions offer valuable insights and practical solutions for secure and collaborative data analysis within the domain of privacy-preserving model fusion.

Due to the incapability of one sensory measurement to provide enough information for condition monitoring of some complex engineered industrial mechanisms and also for overcoming the misleading noise of a single sensor, multiple sensors are installed to improve the condition monitoring of some industrial equipment. Therefore, an efficient data fusion strategy is demanded. In this research, we presented a Denoising Multi-Modal Autoencoder with a unique training strategy based on contrastive learning paradigm, both being utilized for the first time in the machine health monitoring realm. The presented approach, which leverages the merits of both supervised and unsupervised learning, not only achieves excellent performance in fusing multiple modalities (or views) of data into an enriched common representation but also takes data fusion to the next level wherein one of the views can be omitted during inference time with very slight performance reduction, or even without any reduction at all. The presented methodology enables multi-modal fault diagnosis systems to perform more robustly in case of sensor failure occurrence, and one can also intentionally omit one of the sensors (the more expensive one) in order to build a more cost-effective condition monitoring system without sacrificing performance for practical purposes. The effectiveness of the presented methodology is examined on a real-world private multi-modal dataset gathered under non-laboratory conditions from a complex engineered mechanism, an inline four-stroke spark-ignition engine, aiming for spark plug fault diagnosis. This dataset, which contains the accelerometer and acoustic signals as two modalities, has a very slight amount of fault, and achieving good performance on such a dataset promises that the presented method can perform well on other equipment as well.

Understanding the semantics of individual regions or patches within unconstrained images, such as in open-world object detection, represents a critical yet challenging task in computer vision. Building on the success of powerful image-level vision-language (ViL) foundation models like CLIP, recent efforts have sought to harness their capabilities by either training a contrastive model from scratch with an extensive collection of region-label pairs or aligning the outputs of a detection model with image-level representations of region proposals. Despite notable progress, these approaches are plagued by computationally intensive training requirements, susceptibility to data noise, and deficiency in contextual information. To address these limitations, we explore the synergistic potential of off-the-shelf foundation models, leveraging their respective strengths in localization and semantics. We introduce a novel, generic, and efficient region recognition architecture, named RegionSpot, designed to integrate position-aware localization knowledge from a localization foundation model (e.g., SAM) with semantic information extracted from a ViL model (e.g., CLIP). To fully exploit pretrained knowledge while minimizing training overhead, we keep both foundation models frozen, focusing optimization efforts solely on a lightweight attention-based knowledge integration module. Through extensive experiments in the context of open-world object recognition, our RegionSpot demonstrates significant performance improvements over prior alternatives, while also providing substantial computational savings. For instance, training our model with 3 million data in a single day using 8 V100 GPUs. Our model outperforms GLIP by 6.5 % in mean average precision (mAP), with an even larger margin by 14.8 % for more challenging and rare categories.

The entity alignment of science and technology patents aims to link the equivalent entities in the knowledge graph of different science and technology patent data sources. Most entity alignment methods only use graph neural network to obtain the embedding of graph structure or use attribute text description to obtain semantic representation, ignoring the process of multi-information fusion in science and technology patents. In order to make use of the graphic structure and auxiliary information such as the name, description and attribute of the patent entity, this paper proposes an entity alignment method based on the graph convolution network for science and technology patent information fusion. Through the graph convolution network and BERT model, the structure information and entity attribute information of the science and technology patent knowledge graph are embedded and represented to achieve multi-information fusion, thus improving the performance of entity alignment. Experiments on three benchmark data sets show that the proposed method Hit@K The evaluation indicators are better than the existing methods.

Precise relative navigation is a critical enabler for distributed satellites to achieve new mission objectives impossible for a monolithic spacecraft. Carrier phase differential GPS (CDGPS) with integer ambiguity resolution (IAR) is a promising means of achieving cm-level accuracy for high-precision Rendezvous, Proximity-Operations and Docking (RPOD), In-Space Servicing, Assembly and Manufacturing (ISAM) as well as satellite formation flying and swarming. However, IAR is sensitive to received GPS signal noise, especially under severe multi-path or high thermal noise. This paper proposes a sensor-fusion approach to achieve IAR under such conditions in two coupling stages. A loose coupling stage fuses through an Extended Kalman Filter the CDGPS measurements with on-board sensor measurements such as range from cross-links, and vision-based bearing angles. A second tight-coupling stage augments the cost function of the integer weighted least-squares minimization with a soft constraint function using noise-weighted observed-minus-computed residuals from these external sensor measurements. Integer acceptance tests are empirically modified to reflect added constraints. Partial IAR is applied to graduate integer fixing. These proposed techniques are packaged into flight-capable software, with ground truths simulated by the Stanford Space Rendezvous Laboratory's S3 library using state-of-the-art force modelling with relevant sources of errors, and validated in two scenarios: (1) a high multi-path scenario involving rendezvous and docking in low Earth orbit, and (2) a high thermal noise scenario relying only on GPS side-lobe signals during proximity operations in geostationary orbit. This study demonstrates successful IAR in both cases, using the proposed sensor-fusion approach, thus demonstrating potential for high-precision state estimation under adverse signal-to-noise conditions.

Multimodal deep sensor fusion has the potential to enable autonomous vehicles to visually understand their surrounding environments in all weather conditions. However, existing deep sensor fusion methods usually employ convoluted architectures with intermingled multimodal features, requiring large coregistered multimodal datasets for training. In this work, we present an efficient and modular RGB-X fusion network that can leverage and fuse pretrained single-modal models via scene-specific fusion modules, thereby enabling joint input-adaptive network architectures to be created using small, coregistered multimodal datasets. Our experiments demonstrate the superiority of our method compared to existing works on RGB-thermal and RGB-gated datasets, performing fusion using only a small amount of additional parameters. Our code is available at https://github.com/dsriaditya999/RGBXFusion.

We present a scalable combined localization infrastructure deployment and task planning algorithm for underwater assembly. Infrastructure is autonomously modified to suit the needs of manipulation tasks based on an uncertainty model on the infrastructure's positional accuracy. Our uncertainty model can be combined with the noise characteristics from multiple devices. For the task planning problem, we propose a layer-based clustering approach that completes the manipulation tasks one cluster at a time. We employ movable visual fiducial markers as infrastructure and an autonomous underwater vehicle (AUV) for manipulation tasks. The proposed task planning algorithm is computationally simple, and we implement it on AUV without any offline computation requirements. Combined hardware experiments and simulations over large datasets show that the proposed technique is scalable to large areas.

Object detection is a core component of perception systems, providing the ego vehicle with information about its surroundings to ensure safe route planning. While cameras and Lidar have significantly advanced perception systems, their performance can be limited in adverse weather conditions. In contrast, millimeter-wave technology enables radars to function effectively in such conditions. However, relying solely on radar for building a perception system doesn't fully capture the environment due to the data's sparse nature. To address this, sensor fusion strategies have been introduced. We propose a dual-branch framework to integrate radar and Lidar data for enhanced object detection. The primary branch focuses on extracting radar features, while the auxiliary branch extracts Lidar features. These are then combined using additive attention. Subsequently, the integrated features are processed through a novel Parallel Forked Structure (PFS) to manage scale variations. A region proposal head is then utilized for object detection. We evaluated the effectiveness of our proposed method on the Radiate dataset using COCO metrics. The results show that it surpasses state-of-the-art methods by $1.89\%$ and $2.61\%$ in favorable and adverse weather conditions, respectively. This underscores the value of radar-Lidar fusion in achieving precise object detection and localization, especially in challenging weather conditions.

Scalable and effective calibration is a fundamental requirement for Low Cost Air Quality Monitoring Systems and will enable accurate and pervasive monitoring in cities. Suffering from environmental interferences and fabrication variance, these devices need to encompass sensors specific and complex calibration processes for reaching a sufficient accuracy to be deployed as indicative measurement devices in Air Quality (AQ) monitoring networks. Concept and sensor drift often force calibration process to be frequently repeated. These issues lead to unbearable calibration costs which denies their massive deployment when accuracy is a concern. In this work, We propose a zero transfer samples, global calibration methodology as a technological enabler for IoT AQ multisensory devices which relies on low cost Particulate Matter (PM) sensors. This methodology is based on field recorded responses from a limited number of IoT AQ multisensors units and machine learning concepts and can be universally applied to all units of the same type. A multi season test campaign shown that, when applied to different sensors, this methodology performances match those of state of the art methodology which requires to derive different calibration parameters for each different unit. If confirmed, these results show that, when properly derived, a global calibration law can be exploited for a large number of networked devices with dramatic cost reduction eventually allowing massive deployment of accurate IoT AQ monitoring devices. Furthermore, this calibration model could be easily embedded on board of the device or implemented on the edge allowing immediate access to accurate readings for personal exposure monitor applications as well as reducing long range data transfer needs.

In recent years, Visual Question Answering (VQA) has gained significant attention for its diverse applications, including intelligent car assistance, aiding visually impaired individuals, and document image information retrieval using natural language queries. VQA requires effective integration of information from questions and images to generate accurate answers. Neural models for VQA have made remarkable progress on large-scale datasets, with a primary focus on resource-rich languages like English. To address this, we introduce the ViCLEVR dataset, a pioneering collection for evaluating various visual reasoning capabilities in Vietnamese while mitigating biases. The dataset comprises over 26,000 images and 30,000 question-answer pairs (QAs), each question annotated to specify the type of reasoning involved. Leveraging this dataset, we conduct a comprehensive analysis of contemporary visual reasoning systems, offering valuable insights into their strengths and limitations. Furthermore, we present PhoVIT, a comprehensive multimodal fusion that identifies objects in images based on questions. The architecture effectively employs transformers to enable simultaneous reasoning over textual and visual data, merging both modalities at an early model stage. The experimental findings demonstrate that our proposed model achieves state-of-the-art performance across four evaluation metrics. The accompanying code and dataset have been made publicly accessible at \url{https://github.com/kvt0012/ViCLEVR}. This provision seeks to stimulate advancements within the research community, fostering the development of more multimodal fusion algorithms, specifically tailored to address the nuances of low-resource languages, exemplified by Vietnamese.