Current popular Large Vision-Language Models (LVLMs) are suffering from Hallucinations on Object Attributes (HoOA), leading to incorrect determination of fine-grained attributes in the input images. Leveraging significant advancements in 3D generation from a single image, this paper proposes a novel method to mitigate HoOA in LVLMs. This method utilizes multiview images sampled from generated 3D representations as visual prompts for LVLMs, thereby providing more visual information from other viewpoints. Furthermore, we observe the input order of multiple multiview images significantly affects the performance of LVLMs. Consequently, we have devised Multiview Image Augmented VLM (MIAVLM), incorporating a Multiview Attributes Perceiver (MAP) submodule capable of simultaneously eliminating the influence of input image order and aligning visual information from multiview images with Large Language Models (LLMs). Besides, we designed and employed negative instructions to mitigate LVLMs’ bias towards "Yes" responses. Comprehensive experiments demonstrate the effectiveness of our method.

The gradual maturation of mobile augmented reality (AR) and localization technologies is enabling the development of immersive AR-enabled indoor localization and navigation systems. Existing indoor localization technologies (e.g., WiFi, infrared, Bluetooth) and navigation services do not provide intuitive 3D AR experiences and can be expensive to deploy. This paper introduces WebARNav, a cross-platform indoor localization system that provides user-friendly AR navigation services with low overhead and remarkable accuracy. First, we propose a lightweight location fusion framework for indoor navigation on the mobile web, which leverages accurate edge-supported vision localization to guide and correct lightweight pedestrian dead reckoning localization. Second, we improve the accuracy of localization using an attention-based feature extraction method and a dual-stream retrieval and co-visibility re-ranking technique for initial localization. Third, we significantly improve accuracy and speed up retrieval as users move by generating a topological map for traveling localization. We conducted extensive experiments on various indoor datasets to demonstrate localization accuracy and navigation experience. The study shows that WebARNav achieves a localization frequency of over 30 Hz and reduces the average trajectory error by 76% and 95% for single- and multi-floor office scenes, respectively, compared to the PDR-only method. The proposed traveling localization method also reduces the localization latency by 15.2%, 55.1%, and 98.6% in the baseline datasets, with an accuracy improvement of over 4%.

The recommendation of suitable hashtags for mi-croposts encompassing multimodal content stands as a pivotal challenge for numerous Social Networking Service (SNS) applications such as Instagram, Weibo, etc. The accuracy of multimodal hashtag recommendation algorithms relies heavily on the comprehension of multimodal information, user historical information, and the reasoning ability based on such information. However, most previous works have not effectively utilized both historical and additional information simultaneously. Large Language Models (LLMs) learn a vast amount of implicit knowledge during the pre-training stage, which can serve as potential knowledge bases while also possessing strong reasoning abilities. Therefore, LLMs can provide additional information to help understand the micropost content and infer suitable hashtags with strong reasoning ability. However, introducing LLMs for multimodal hashtag recommendation faces three main challenges. Firstly, LLMs require an efficient modality alignment module to accept a multimodal input. Secondly, LLMs are highly sensitive to input order, while utilizing user historical information requires accepting multiple historical samples, necessitating the design of a robust historical information processing module to eliminate the influence of input order. Thirdly, fine-tuning LLMs entails substantial computational overheads, necessitating the reduction of additional trainable parameters. To address the first two challenges, this paper designs an efficient modality alignment module capable of processing multiple historical samples, simultaneously addressing the sensitivity of LLMs to input order changes. To tackle the third challenge, a hybrid prompt learning approach utilizing both soft and hard prompts is proposed to achieve parameter-efficient fine-tuning of LLMs. Finally, a LLM-augmented Multimodal Hashtag Recommendation algorithm (LLM-MHR) is implemented. Comprehensive experiments on the representative dataset MACON demonstrate that LLM-MHR has achieved SOTA performances with significant improvements.

Spacecraft telemetry data is crucial for assessing the health of a spacecraft, but it often contains missing or redundant information that affects data quality. To ensure accurate status assessments, it is necessary to research methods for reconstructing telemetry data. Since spacecraft are subject to many short-term disturbances, the number of missing points or redundancy in the data on a short time scale is highly random, so it is difficult to reconstruct the data using traditional deep learning models (such as recurrent neural networks). Therefore, this paper proposes a self-adaptive reconstruction method of spacecraft telemetry data based on a neural ordinary differential equation (NODE). First, this paper uses a time-continuous model based on NODE to better learn the long-term continuity of data. On this basis, self-adaptive reconstruction windows are constructed on the time scale for irregular sampling telemetry data (with only one missing condition in each window). Afterward, the NODE model is used to adaptively reconstruct the data. Finally, a real spacecraft telemetry dataset is used to verify the method proposed in this paper.

This letter presents a new method for localizing and identifying a target through walls with known wall parameters. A time-delay difference curve (TDDC) is utilized in this method for target localization and identification. The characteristic of the TDDC can be applied to estimate the incident angle and offset the influences in propagation path and propagation time delay brought from the wall. This letter analyzes the method and gives out the theoretical TDDC. Extensive simulations and experiments show the effectiveness of the proposed method.

This paper proposes a new algorithm to obtain the target shape imaging and track it synchronously using triangle localization method and the difference of time delay in the application of through wall imaging (TWI). The proposed algorithm based on a system model built in the near field can effectively estimate the velocity and track of moving target with the imaging result. Simulation results show that the effect of the wall can be removed visibly and the purpose of the imaging and tracking of moving target can be realized well.

In virtual instrument designs and applications, lots of functional parameters can be set through software methods. Currently, most parameter settings methods are lightly linked with the knowledge of instruments and basic principles related to specific applications. However, it is difficult for some end users to deal with those advanced operations. By adopting the particle swarm optimization (PSO) algorithm, the adaptive set and calibration of instrument parameters can be achieved by software with computational intelligence. Experiments and applications showed that the adaptive parameter calibration method based on the PSO can enhance the effectiveness of debugging and maintenance of virtual instrument and test system.