Real-world Objects Research Articles

What do we see behind an occluder? Amodal completion of statistical properties in complex objects.

When a spiky object is occluded, we expect its spiky features tocontinue behind the occluder. Although many real-world objects contain complex features, it is unclear how more complex features are amodally completed and whether this process is automatic. To investigate this issue, we created pairs of displays with identical contour edges up to the point of occlusion, but with occluded portions exchanged. We then asked participants to search for oddball targets among distractors and asked whether relations between searches involving occluded displays would match better with relations between searches involving completions that are either globally consistent or inconsistent with the visible portions of these displays. Across two experiments involving simple and complex shapes, search times involving occluded displays matched better with those involving globally consistent compared with inconsistent displays. Analogous analyses on deep networks pretrained for object categorization revealed a similar pattern of results for simple but not complex shapes. Thus, deep networks seem to extrapolate simple occluded contours but not more complex contours. Taken together, our results show that amodal completion in humans is sophisticated and can be based on extrapolating global statistical properties.

A larger augmented-reality field of view improves interaction with nearby holographic objects.

Augmented-reality (AR) applications have shown potential for assisting and modulating gait in health-related fields, like AR cueing of foot-placement locations in people with Parkinson's disease. However, the size of the AR field of view (AR-FOV), which is smaller than one's own FOV, might affect interaction with nearby floor-based holographic objects. The study's primary objective was to evaluate the effect of AR-FOV size on the required head orientations for viewing and interacting with real-world and holographic floor-based objects during standstill and walking conditions. Secondary, we evaluated the effect of AR-FOV size on gait speed when interacting with real-world and holographic objects. Sixteen healthy middle-aged adults participated in two experiments wearing HoloLens 1 and 2 AR headsets that differ in AR-FOV size. To confirm participants' perceived differences in AR-FOV size, we examined the head orientations required for viewing nearby and far objects from a standstill position (Experiment 1). In Experiment 2, we examined the effect of AR-FOV size on head orientations and gait speeds for negotiating 2D and 3D objects during walking. Less downward head orientation was required for looking at nearby holographic objects with HoloLens 2 than with HoloLens 1, as expected given differences in perceived AR-FOV size (Experiment 1). In Experiment 2, a greater downward head orientation was observed for interacting with holographic objects compared to real-world objects, but again less so for HoloLens 2 than HoloLens 1 along the line of progression. Participants walked slightly but significantly slower when interacting with holographic objects compared to real-world objects, without any differences between the HoloLenses. To conclude, the increased size of the AR-FOV did not affect gait speed, but resulted in more real-world-like head orientations for seeing and picking up task-relevant information when interacting with floor-based holographic objects, improving the potential efficacy of AR cueing applications.

High-Visibility Edge-Highlighting Visualization of 3D Scanned Point Clouds Based on Dual 3D Edge Extraction

Recent advances in 3D scanning have enabled the digital recording of complex objects as large-scale point clouds, which require clear visualization to convey their 3D shapes effectively. Edge-highlighting visualization is used to improve the comprehensibility of complex 3D structures by enhancing the 3D edges and high-curvature regions of the scanned objects. However, traditional methods often struggle with real-world objects due to inadequate representation of soft edges (i.e., rounded edges) and excessive line clutter, impairing resolution and depth perception. To address these challenges, we propose a novel visualization method for 3D scanned point clouds based on dual 3D edge extraction and opacity–color gradation. Dual 3D edge extraction separately identifies sharp and soft edges, integrating both into the visualization. Opacity–color gradation enhances the clarity of fine structures within soft edges through variations in color and opacity, while also creating a halo effect that improves both resolution and depth perception of the visualized edges. Computation times required for dual 3D edge extraction are comparable to conventional binary statistical edge-extraction methods. Visualizations with opacity–color gradation are executable at interactive rendering speeds. The effectiveness of the proposed method is demonstrated using 3D scanned point cloud data from high-value cultural heritage objects.

Measures of angularity in digital images.

In light of the growing interest in studying the affective and aesthetic attributes of curvature, the present paper describes four digital image processing techniques that can be used to objectively discriminate between angular and curvilinear stimuli. MATLAB scripts for each of the techniques accompany the paper. Three studies are then reported that evaluate the efficacy of five metrics, derived from the four techniques, at quantifying the degree of angularity depicted in an image. Images of simple polygons (Study 1), artistic drawings of everyday objects (Study 2), and real-world objects, typefaces, and abstract patterns (Study 3) were analyzed. Logistic regression models were used to determine the relative importance of the metrics at distinguishing between angular and curvilinear items. With one exception, all of the metrics were capable of distinguishing between angular and curvilinear items at a level above chance, but some metrics were better at doing so than others, and their discriminative capacity was influenced by the characteristics of the image. The strengths and limitations of the metrics are discussed, as well as some practical recommendations.

Conceptual masking disrupts change-detection performance.

The present study investigated the effects of long-term knowledge on backward masking interference in visual working memory (VWM) by varying the similarity of mask stimuli along categorical dimensions. To-be-remembered items and masks were taken from categories controlled for perceptual distinctiveness and distinctiveness in kinds (e.g., there are many kinds of cars and few kinds of coffee mugs). Participants completed a change-detection task in which the memory array consisted of exemplars from either a similar or distinctive category, followed by a mask array of items from the same category (conceptually similar versus conceptually distinct categories), a different category, or no mask. The results over two experiments showed greater interference from conceptually similar masks as compared with the other conditions across stimulus onset asynchrony (SOA) conditions, suggesting masking with conceptually similar categories leads to more interference even when masks are shown well after the stimulus. These results have important implications for both the nature and time course of long-term conceptual knowledge influencing VWM, particularly when using complex real-world objects.

Teaching Reform of BIM Modeling and Realistic 3D Integration Application

BIM technology is based on three digit technology to achieve information integration and sharing throughout the entire life cycle of buildings, which can effectively improve design and construction efficiency. Realistic 3D technology is a technology that digitally presents real-world objects and scenes in high-precision, high-efficiency, and high fidelity 3D form, which can objectively and realistically reflect the real world and provide rich spatial analysis functions. This article integrates real-life 3D and BIM modeling technology and applies it to practical teaching of civil engineering majors in vocational colleges, explores its teaching practice methods, and proposes reform measures such as deepening course design, innovating teaching methods, deepening school enterprise cooperation, and improving assessment and evaluation systems. In order to enhance students' competitiveness in employment and continuously promote the teaching reform of BIM modeling courses.

Open-world object detection: A solution based on reselection mechanism and feature disentanglement

Traditional object detection algorithms operate within a closed set, where the training data may not cover all real-world objects. Therefore, the issue of open-world object detection has attracted significant attention. Open-world object detection faces two major challenges: “neglecting unknown objects” and “misclassifying unknown objects as known ones.” In our study, we address these challenges by utilizing the Region Proposal Network (RPN) outputs to identify potential unknown objects with high object scores that do not overlap with ground truth annotations. We introduce the reselection mechanism, which separates unknown objects from the background. Subsequently, we employ the simulated annealing algorithm to disentangle features of unknown and known classes, guiding the detector’s learning process. Our method has improved on multiple evaluation metrics such as U-mAP, U-recall, and UDP, greatly alleviating the challenges faced by open world object detection.

Exploring the relationship between fluid intelligence and visual working memory for simple features vs. real-world objects

Exploring the relationship between fluid intelligence and visual working memory for simple features vs. real-world objects

Visual long-term memory is not made more precise with medial-frontal direct-current stimulation

ABSTRACT Previous research suggests that applying anodal transcranial direct-current stimulation (tDCS) to the medial-frontal cortex can improve how quickly subjects learn to make simple discriminations (i.e., red from blue). Here, we tested the idea that this enhanced task learning is attributable to superior encoding of relevant information into visual long-term memory. Thirty subjects completed an anodal stimulation session and a sham session, with order counterbalanced across subjects, before performing recognition-memory tasks using pictures of real-world objects and visually presented words or nonwords. These tasks allowed us to detect potential memory differences across types of memoranda. Contrary to the hypothesis that the medial-frontal cortex helps control encoding fidelity, we found that anodal tDCS delivered over this brain region did not significantly improve subjects’ memory for visual stimuli, regardless of stimulus type. Our findings show no evidence that targeting medial-frontal cortex with tDCS changes the fidelity of our visual long-term memories.

Are selection history effects limited to implicit forms of memory? Evidence from intertrial repetition.

Selection history effects in visual attention are typically considered implicit memory effects. In three experiments, we investigated if a key selection history effect, intertrial priming, could be based on the incidental application of explicit memory. In the basic search task (Experiment 1), participants searched for real-world objects from different categories. We examined nonpredictive, intertrial repetition at two levels: (1) the repetition of target location from trial N-1 to trial N and (2) the repetition of target location and color within a category. Reliable repetition advantages were observed at both levels. In Experiments 2-4, we examined whether participants had explicit access to the target values driving the selection history effects here. In Experiments 2 and 3, participants could reliably report the properties of the immediately preceding search target. In Experiment 4, participants could reliably report the properties of the last target exemplar they had found in each of the 36 categories. These data indicate that guidance by selection history was based on the nonstrategic application of memory representations that could be explicitly retrieved and reported. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

SparkDWM: a scalable design of a Data Washing Machine using Apache Spark.

Data volume has been one of the fast-growing assets of most real-world applications. This increases the rate of human errors such as duplication of records, misspellings, and erroneous transpositions, among other data quality issues. Entity Resolution is an ETL process that aims to resolve data inconsistencies by ensuring entities are referring to the same real-world objects. One of the main challenges of most traditional Entity Resolution systems is ensuring their scalability to meet the rising data needs. This research aims to refactor a working proof-of-concept entity resolution system called the Data Washing Machine to be highly scalable using Apache Spark distributed data processing framework. We solve the single-threaded design problem of the legacy Data Washing Machine by using PySpark's Resilient Distributed Dataset and improve the Data Washing Machine design to use intrinsic metadata information from references. We prove that our systems achieve the same results as the legacy Data Washing Machine using 18 synthetically generated datasets. We also test the scalability of our system using a variety of real-world benchmark ER datasets from a few thousand to millions. Our experimental results show that our proposed system performs better than a MapReduce-based Data Washing Machine. We also compared our system with Famer and concluded that our system can find more clusters when given optimal starting parameters for clustering.

Internet of things enabled E-learning system for academic achievement among university students

The rise of the Internet of Things (IoT) represents a burgeoning frontier in educational innovation, particularly in the realm of e-learning. Despite its expanding capabilities, the integration of IoT technologies into e-learning within higher educational institutions (HEIs) faces numerous challenges and constraints. Limited research has delved into the implementation of IoT in e-learning, especially in developing nations. Consequently, this study seeks to explore the determinants influencing the adoption of IoT for e-learning in HEIs. The aim of the innovative ICT classroom is to assist students in acquiring new skills, adapting to new situations, and utilizing technology in a manner that leads to enhanced learning outcomes and extensive knowledge. Our suggested e-learning system, integrated with IoT technology, gauges student engagement and attentiveness throughout online lectures. The proposed technology integrates electroencephalography (EEG) with IoT. The IoT is a collection of technologies that allow embedded real-world objects to connect to the Internet and is widely used by humans to support a variety of activities. IoT should be taught using developmental learning approaches and included in higher education teaching projects. EEG devices are used to track the psychological movements of students taking online courses. Our findings demonstrate how the proposed method can be used to detect the user’s level of concentration and the required level of educational strategy. A collection of informational indexes for student attention. By using a BiLSTM network to predict undergraduate recall and temporary memory, we can accurately predict undergraduate preferred learning styles. The findings of the research demonstrate that IoT systems and devices play a pivotal role in enhancing access to education. They facilitate easier teaching and learning processes while democratizing education. When employed as educational tools, IoT devices contribute significantly to creating highly engaging learning experiences for students.

3D Scene Creation and Rendering via Rough Meshes: A Lighting Transfer Avenue.

This paper studies how to flexibly integrate reconstructed 3D models into practical 3D modeling pipelines such as 3D scene creation and rendering. Due to the technical difficulty, one can only obtain rough 3D models (R3DMs) for most real objects using existing 3D reconstruction techniques. As a result, physically-based rendering (PBR) would render low-quality images or videos for scenes that are constructed by R3DMs. One promising solution would be representing real-world objects as Neural Fields such as NeRFs, which are able to generate photo-realistic renderings of an object under desired viewpoints. However, a drawback is that the synthesized views through Neural Fields Rendering (NFR) cannot reflect the simulated lighting details on R3DMs in PBR pipelines, especially when object interactions in the 3D scene creation cause local shadows. To solve this dilemma, we propose a lighting transfer network (LighTNet) to bridge NFR and PBR, such that they can benefit from each other. LighTNet reasons about a simplified image composition model, remedies the uneven surface issue caused by R3DMs, and is empowered by several perceptual-motivated constraints and a new Lab angle loss which enhances the contrast between lighting strength and colors. Comparisons demonstrate that LighTNet is superior in synthesizing impressive lighting, and is promising in pushing NFR further in practical 3D modeling workflows.

One-Shot Learning from Prototype Stock Keeping Unit Images

This paper highlights the importance of one-shot learning from prototype Stock Keeping Unit (SKU) images for efficient product recognition in retail and inventory management. Traditional methods require large supervised datasets to train deep neural networks, which can be costly and impractical. One-shot learning techniques mitigate this issue by enabling classification from a single prototype image per product class, thus reducing data annotation efforts. We introduce the Variational Prototyping Encoder (VPE), a novel deep neural network for one-shot classification. Utilizing a support set of prototype SKU images, VPE learns to classify query images by capturing image similarity and prototypical concepts. Unlike metric learning-based approaches, VPE pre-learns image translation from real-world object images to prototype images as a meta-task, facilitating efficient one-shot classification with minimal supervision. Our research demonstrates that VPE effectively reduces the need for extensive datasets by utilizing a single image per class while accurately classifying query images into their respective categories, thus providing a practical solution for product classification tasks.

Visual object detection system based on augmented reality and steady-state visual evoked potential

This study investigates a brain-computer interface (BCI) system based on an augmented reality (AR) environment and steady-state visual evoked potentials (SSVEP). The system is designed to facilitate the selection of real-world objects through visual gaze in real-life scenarios. By integrating object detection technology and AR technology, the system augmented real objects with visual enhancements, providing users with visual stimuli that induced corresponding brain signals. SSVEP technology was then utilized to interpret these brain signals and identify the objects that users focused on. Additionally, an adaptive dynamic time-window-based filter bank canonical correlation analysis was employed to rapidly parse the subjects' brain signals. Experimental results indicated that the system could effectively recognize SSVEP signals, achieving an average accuracy rate of 90.6% in visual target identification. This system extends the application of SSVEP signals to real-life scenarios, demonstrating feasibility and efficacy in assisting individuals with mobility impairments and physical disabilities in object selection tasks.

Data processing in internet of things networks

One of the distinctive features of cloud applications in the Internet of Things (IoT) network is the real-time collection and processing of data about the objects of the physical environment. To solve this problem, with the help of sensors, data about the state of physical objects is collected to form the processing of data streams. The performance of such systems is critically dependent on the ability to securely and efficiently collect, transmit, and analyze data streams between environmental (real-world) objects and information systems. In such a case, it is relevant to study the data stream in Internet of Things networks and the operations that may occur on them. The issue of which platforms to process the operations to be carried out at the same time is the main subject of discussion.

RADAP: A Robust and Adaptive Defense Against Diverse Adversarial Patches on face recognition

Face recognition (FR) systems powered by deep learning have become widely used in various applications. However, they are vulnerable to adversarial attacks, especially those based on local adversarial patches that can be physically applied to real-world objects. In this paper, we propose RADAP, a robust and adaptive defense mechanism against diverse adversarial patches in both closed-set and open-set FR systems. RADAP employs innovative techniques, such as FCutout and F-patch, which use Fourier space sampling masks to improve the occlusion robustness of the FR model and the performance of the patch segmenter. Moreover, we introduce an edge-aware binary cross-entropy (EBCE) loss function to enhance the accuracy of patch detection. We also present the split and fill (SAF) strategy, which is designed to counter the vulnerability of the patch segmenter to complete white-box adaptive attacks. We conduct comprehensive experiments to validate the effectiveness of RADAP, which shows significant improvements in defense performance against various adversarial patches, while maintaining clean accuracy higher than that of the undefended Vanilla model.

Learning-based real-time imaging through dynamic scattering media

Imaging through dynamic scattering media is one of the most challenging yet fascinating problems in optics, with applications spanning from biological detection to remote sensing. In this study, we propose a comprehensive learning-based technique that facilitates real-time, non-invasive, incoherent imaging of real-world objects through dense and dynamic scattering media. We conduct extensive experiments, demonstrating the capability of our technique to see through turbid water and natural fog. The experimental results indicate that the proposed technique surpasses existing approaches in numerous aspects and holds significant potential for imaging applications across a broad spectrum of disciplines.

Multi-modal data clustering using deep learning: A systematic review

Multi-modal clustering represents a formidable challenge in the domain of unsupervised learning. The objective of multi-modal clustering is to categorize data collected from diverse modalities, such as audio, visual, and textual sources, into distinct clusters. These clustering techniques operate by extracting shared features across modalities in an unsupervised manner, where the identified common features exhibit high correlations within real-world objects. Recognizing the importance of perceiving the correlated nature of these features is vital for enhancing clustering accuracy in multi-modal settings. This survey explores Deep Learning (DL) techniques applied to multi-modal clustering, encompassing methodologies such as Convolutional Neural Networks (CNN), Autoencoders (AE), Recurrent Neural Networks (RNN), and Graph Convolutional Networks (GCN). Notably, this survey represents the first attempt to investigate DL techniques specifically for multi-modal clustering. The survey presents a novel taxonomy for DL-based multi-modal clustering, conducts a comparative analysis of various multi-modal clustering approaches, and deliberates on the datasets employed in the evaluation process. Additionally, the survey identifies research gaps within the realm of multi-modal clustering, offering insights into potential future avenues for research.

Wave-PCT: Wavelet point cloud transformer for point cloud quality assessment

Point cloud representation for real-world objects has seen a surge in interest recently, finding widespread applications in augmented reality, virtual reality, and autonomous driving. However, the process of acquiring, compressing, transmitting, and processing point cloud data often introduces unwanted distortions, highlighting the need for effective no-reference quality assessment methods for distorted point clouds. In this paper, we propose a Wavelet Point Cloud Transformer (Wave-PCT) method to assess the quality of point clouds without reference data. We start by performing patch sampling on a source point cloud, generating an extensive set of patches from the point cloud. These point cloud patches and their 2D projection images are processed using wavelets to produce multiscale local spectral features; moreover, we also extract global features of these patches using Pointnet++. Finally, a self-attention module is performed to fuse these local and global features, resulting in a distortion-sensitive quality score metric. We evaluate the Wave-PCT method on several point cloud quality assessment datasets using various metrics, and the experimental results indicate that the proposed framework exhibits outstanding and reliable performance when compared to various point cloud quality assessment methods.