Object Recognition Performance Research Articles

Perceptual Expertise and Attention: An Exploration using Deep Neural Networks.

Perceptual expertise and attention are two important factors that enable superior object recognition and task performance. While expertise enhances knowledge and provides a holistic understanding of the environment, attention allows us to selectively focus on task-related information and suppress distraction. It has been suggested that attention operates differently in experts and in novices, but much remains unknown. This study investigates the relationship between perceptual expertise and attention using convolutional neural networks (CNNs), which are shown to be good models of primate visual pathways. Two CNN models were trained to become experts in either face or scene recognition, and the effect of attention on performance was evaluated in tasks involving complex stimuli, such as superimposed images containing superimposed faces and scenes. The goal was to explore how feature-based attention (FBA) influences recognition within and outside the domain of expertise of the models. We found that each model performed better in its area of expertise-and that FBA further enhanced task performance, but only within the domain of expertise, increasing performance by up to 35% in scene recognition, and 15% in face recognition. However, attention had reduced or negative effects when applied outside the models' expertise domain. Neural unit-level analysis revealed that expertise led to stronger tuning towards category-specific features and sharper tuning curves, as reflected in greater representational dissimilarity between targets and distractors, which, in line with the biased competition model of attention, leads to enhanced performance by reducing competition. These findings highlight the critical role of neural tuning at single as well as network level neural in distinguishing the effects of attention in experts and in novices and demonstrate that CNNs can be used fruitfully as computational models for addressing neuroscience questions not practical with the empirical methods.

Two distinct enriched housings differentially ameliorate object and place recognition deficits in a rat model of schizophrenia

Schizophrenia is a psychiatric disorder characterized by cognitive dysfunctions. These dysfunctions significantly impact the daily lives of schizophrenic patients, yet effective interventions remain scarce. In this study, we explored the effects of two enriched housing types—cognitive and physical—on cognitive dysfunctions in a rat model of schizophrenia. Male neonatal Wistar-Imamichi rats were administered MK-801, a noncompetitive NMDAR antagonist, twice daily from postnatal day (PND) 7 to PND 20. Physical enrichment ameliorated memory deficits in both object and place recognition tests, while cognitive enrichment primarily improved object recognition performance. Our findings suggest that exercise therapy could be a potential approach to address cognitive dysfunctions in schizophrenia patients.

Synthetic lidar point cloud generation using deep generative models for improved driving scene object recognition

The imbalanced distribution of different object categories poses a challenge for training accurate object recognition models in driving scenes. Supervised machine learning models trained on imbalanced data are biased and easily overfit the majority classes, such as vehicles and pedestrians, which appear more frequently in driving scenes. We propose a novel data augmentation approach for object recognition in lidar point cloud of driving scenes, which leverages probabilistic generative models to produce synthetic point clouds for the minority classes and complement the original imbalanced dataset. We evaluate five generative models based on different statistical principles, including Gaussian mixture model, variational autoencoder, generative adversarial network, adversarial autoencoder and the diffusion model. Experiments with a real-world autonomous driving dataset show that the synthetic point clouds generated for the minority classes by the Latent Generative Adversarial Network result in significant improvement of object recognition performance for both minority and majority classes. The codes are available at https://github.com/AAAALEX-XIANG/Synthetic-Lidar-Generation.

On-Device Neural Network for Object Train and Recognition using Mobile

A neural network is a machine learning (ML) program or model that processes information and recognizes patterns, similar to the human brain. The neural network algorithm operates by training on data to learn and enhance its accuracy. If there is any mistake in the learning process, the machine will react unexpectedly and produce incorrect information. So, whenever a neural network model is developed, it is mandatory to evaluate its performance and ensure its output is accurate. Cameras, touchscreens, internet connectivity, and powerful CPUs have contributed to the popularity of smartphones. Mobile apps are software applications that run on smartphones. ML enhances mobile app functionality by offering features such as voice recognition, image analysis, natural language processing, personalization, and recommendations. Training ML models using mobile apps is challenging due to limited resources, data, and privacy concerns. Object recognition is a neural network-based technique that enables the identification and localization of objects in an image or video. This technique is used in driverless cars, disease identification, industrial inspection, robotics, and more. In this paper, the author introduces a new neural network-based algorithm that utilizes mobile devices for training and recognizing images. Although mobile devices have some technological limitations for training, well-established guidelines for systematically mapping verification and validation techniques have been used in the proposed neural network to ensure performance and correctness in on-device object training and recognition.

Attention-based scale sequence network for small object detection

Recently, with the remarkable development of deep learning technology, achievements are being updated in various computer vision fields. In particular, the object recognition field is receiving the most attention. Nevertheless, recognition performance for small objects is still challenging. Its performance is of utmost importance in realistic applications such as searching for missing persons through aerial photography. The core structure of the object recognition neural network is the feature pyramid network (FPN). You Only Look Once (YOLO) is the most widely used representative model following this structure. In this study, we proposed an attention-based scale sequence network (ASSN) that improves the scale sequence feature pyramid network (ssFPN), enhancing the performance of the FPN-based detector for small objects. ASSN is a lightweight attention module optimized for FPN-based detectors and has the versatility to be applied to any model with a corresponding structure. The proposed ASSN demonstrated performance improvements compared to the baselines (YOLOv7 and YOLOv8) in average precision (AP) of up to 0.6%. Additionally, the AP for small objects (APS) showed also improvements of up to 1.9%. Furthermore, ASSN exhibits higher performance than ssFPN while achieving lightweightness and optimization, thereby improving computational complexity and processing speed. ASSN is open-source based on YOLO version 7 and 8. This can be found in our public repository: https://github.com/smu-ivpl/ASSN.git

Mutual Voting for Ranking 3D Correspondences.

Consistent correspondences between point clouds are vital to 3D vision tasks such as registration and recognition. In this paper, we present a mutual voting method for ranking 3D correspondences. The key insight is to achieve reliable scoring results for correspondences by refining both voters and candidates in a mutual voting scheme. First, a graph is constructed for the initial correspondence set with the pairwise compatibility constraint. Second, nodal clustering coefficients are introduced to preliminarily remove a portion of outliers and speed up the following voting process. Third, we model nodes and edges in the graph as candidates and voters, respectively. Mutual voting is then performed in the graph to score correspondences. Finally, the correspondences are ranked based on the voting scores and top-ranked ones are identified as inliers. Feature matching, 3D point cloud registration, and 3D object recognition experiments on various datasets with different nuisances and modalities verify that MV is robust to heavy outliers under different challenging settings, and can significantly boost 3D point cloud registration and 3D object recognition performance.

RRAM based processing-in-memory for efficient intelligent vision tasks at the edge

The work presents a proof-of-concept methodology for at edge visual data storage and processing-in-memory (PIM) as visual data preprocessing inspired from the biological visual system pipeline. This work proposes a methodology to improve the contrast of low-light low-contrast image by carefully modulating the conductance of memristive kind oxide-based resistive memory (RRAM)device. We present the level of contrast enhancement using conductance modulation of different non-filamentary RRAMs with different material stacks and also analyze the impact of RRAM variability on the contrast enhancement. For intelligent vision tasks, we implement artificial neural network (ANN) to perform the image classification and shows the best-case improvement of ∼ 1500 epochs (∼ 74%) using RRAM based PIM. We also implement a large sized ANN “Efficient-Det Network” to perform object recognition on low-light low-contrast dataset ”Ex-Dark” to evaluate the proposed method using PIM layer. The result shows 8% higher mAP than network without a PIM layer. The present work is a step towards the development of efficient hybrid visual system for intelligent vision tasks at edge.

Time division multiplexing based multi-spectral semantic camera for LiDAR applications

The recent progress in the development of measurement systems for autonomous recognition had a substantial impact on emerging technology in numerous fields, especially robotics and automotive applications. In particular, time-of-flight (TOF) based light detection and ranging (LiDAR) systems enable to map the surrounding environmental information over long distances and with high accuracy. The combination of advanced LiDAR with an artificial intelligence platform allows enhanced object recognition and classification, which however still suffers from limitations of inaccuracy and misidentification. Recently, multi-spectral LiDAR systems have been employed to increase the object recognition performance by additionally providing material information in the short-wave infrared (SWIR) range where the reflection spectrum characteristics are typically very sensitive to material properties. However, previous multi-spectral LiDAR systems utilized band-pass filters or complex dispersive optical systems and even required multiple photodetectors, adding complexity and cost. In this work, we propose a time-division-multiplexing (TDM) based multi-spectral LiDAR system for semantic object inference by the simultaneous acquisition of spatial and spectral information. By utilizing the TDM method, we enable the simultaneous acquisition of spatial and spectral information as well as a TOF based distance map with minimized optical loss using only a single photodetector. Our LiDAR system utilizes nanosecond pulses of five different wavelengths in the SWIR range to acquire sufficient material information in addition to 3D spatial information. To demonstrate the recognition performance, we map the multi-spectral image from a human hand, a mannequin hand, a fabric gloved hand, a nitrile gloved hand, and a printed human hand onto an RGB-color encoded image, which clearly visualizes spectral differences as RGB color depending on the material while having a similar shape. Additionally, the classification performance of the multi-spectral image is demonstrated with a convolution neural network (CNN) model using the full multi-spectral data set. Our work presents a compact novel spectroscopic LiDAR system, which provides increased recognition performance and thus a great potential to improve safety and reliability in autonomous driving.

Experimental Study on Using Synthetic Images as a Portion of Training Dataset for Object Recognition in Construction Site

The application of Artificial Intelligence (AI) across various industries necessitates the acquisition of relevant environmental data and the implementation of AI recognition learning based on this data. However, the data available in real-world environments are limited and difficult to obtain. Construction sites represent dynamic and hazardous environments with a significant workforce, making data acquisition challenging and labor-intensive. To address these issues, this experimental study explored the potential of generating synthetic data to overcome the challenges of obtaining data from hazardous construction sites. Additionally, this research investigated the feasibility of hybrid dataset in securing construction-site data by creating synthetic data for scaffolding, which has a high incidence of falls but low object recognition rates due to its linear object characteristics. We generated a dataset by superimposing scaffolding objects, from which the backgrounds were removed, onto various construction site background images. Using this dataset, we produced a hybrid dataset to assess the feasibility of synthetic data for construction sites and to evaluate improvements in object recognition performance. By finding the optimal composition ratio with real data and conducting model training, the highest accuracy was achieved at an 8:2 ratio, with a construction object recognition accuracy of 0.886. Therefore, this study aims to reduce the risk and labor associated with direct data collection at construction sites through a hybrid dataset, achieving data generation at a low cost and high efficiency. By generating synthetic data to find the optimal ratio and constructing a hybrid dataset, this research demonstrates the potential to address the problems of data scarcity and data quality on construction sites. The improvement in recognition accuracy of the construction safety management system is anticipated, suggesting that the creation of synthetic data for constructing a hybrid dataset can reduce construction safety-accident issues.

Objective Video Quality Assessment Method for Object Recognition Tasks

In the field of video quality assessment for object recognition tasks, accurately predicting the impact of different quality factors on recognition algorithms remains a significant challenge. Our study introduces a novel evaluation framework designed to address this gap by focussing on machine vision rather than human perceptual quality metrics. We used advanced machine learning models and custom Video Quality Indicators to enhance the predictive accuracy of object recognition performance under various conditions. Our results indicate a model performance, achieving a mean square error (MSE) of 672.4 and a correlation coefficient of 0.77, which underscores the effectiveness of our approach in real-world scenarios. These findings highlight not only the robustness of our methodology but also its potential applicability in critical areas such as surveillance and telemedicine.

Adaptive Scale and Correlative Attention PointPillars: An Efficient Real-Time 3D Point Cloud Object Detection Algorithm

Recognizing 3D objects from point clouds is a crucial technology for autonomous vehicles. Nevertheless, LiDAR (Light Detection and Ranging) point clouds are generally sparse, and they provide limited contextual information, resulting in unsatisfactory recognition performance for distant or small objects. Consequently, this article proposes an object recognition algorithm named Adaptive Scale and Correlative Attention PointPillars (ASCA-PointPillars) to address this problem. Firstly, an innovative adaptive scale pillars (ASP) encoding method is proposed, which encodes point clouds using pillars of varying sizes. Secondly, ASCA-PointPillars introduces a feature enhancement mechanism called correlative point attention (CPA) to enhance the feature associations within each pillar. Additionally, a data augmentation algorithm called random sampling data augmentation (RS-Aug) is proposed to solve the class imbalance problem. The experimental results on the KITTI 3D object dataset demonstrate that the proposed ASCA-PointPillars algorithm significantly boosts the recognition performance and RS-Aug effectively enhances the training effects on an imbalanced dataset.

Constitutive knockout of interleukin-6 ameliorates memory deficits and entorhinal astrocytosis in the MRL/lpr mouse model of neuropsychiatric lupus.

Neuropsychiatric lupus (NPSLE) describes the cognitive, memory, and affective emotional burdens faced by many lupus patients. While NPSLE's pathogenesis has not been fully elucidated, clinical imaging studies and cerebrospinal fluid (CSF) findings, namely elevated interleukin-6 (IL-6) levels, point to ongoing neuroinflammation in affected patients. Not only linked to systemic autoimmunity, IL-6 can also activate neurotoxic glial cells the brain. A prior pre-clinical study demonstrated that IL-6 can acutely induce a loss of sucrose preference; the present study sought to assess the necessity of chronic IL-6 exposure in the NPSLE-like disease of MRL/lpr lupus mice. We quantified 1308 proteins in individual serum or pooled CSF samples from MRL/lpr and control MRL/mpj mice using protein microarrays. Serum IL-6 levels were plotted against characteristic NPSLE neurobehavioral deficits. Next, IL-6 knockout MRL/lpr (IL-6 KO; n = 15) and IL-6 wildtype MRL/lpr mice (IL-6 WT; n = 15) underwent behavioral testing, focusing on murine correlates of learning and memory deficits, depression, and anxiety. Using qPCR, we quantified the expression of inflammatory genes in the cortex and hippocampus of MRL/lpr IL-6 KO and WT mice. Immunofluorescent staining was performed to quantify numbers of microglia (Iba1 +) and astrocytes (GFAP +) in multiple cortical regions, the hippocampus, and the amygdala. MRL/lpr CSF analyses revealed increases in IL-17, MCP-1, TNF-α, and IL-6 (a priori p-value < 0.1). Serum levels of IL-6 correlated with learning and memory performance (R2 = 0.58; p = 0.03), but not motivated behavior, in MRL/lpr mice. Compared to MRL/lpr IL-6 WT, IL-6 KO mice exhibited improved novelty preference on object placement (45.4% vs 60.2%, p < 0.0001) and object recognition (48.9% vs 67.9%, p = 0.002) but equivalent performance in tests for anxiety-like disease and depression-like behavior. IL-6 KO mice displayed decreased cortical expression of aif1 (microglia; p = 0.049) and gfap (astrocytes; p = 0.044). Correspondingly, IL-6 KO mice exhibited decreased density of GFAP + cells compared to IL-6 WT in the entorhinal cortex (89 vs 148cells/mm2, p = 0.037), an area vital to memory. The inflammatory composition of MRL/lpr CSF resembles that of human NPSLE patients. Increased in the CNS, IL-6 is necessary to the development of learning and memory deficits in the MRL/lpr model of NPSLE. Furthermore, the stimulation of entorhinal astrocytosis appears to be a key mechanism by which IL-6 promotes these behavioral deficits.

Nigella Sativa Supplementations Attenuate Recognition Memory and Cellular Morphometric Impairments Induced by Toluene Administration in Mice

Toluene exposure has been associated with detrimental effects on the central nervous system. Discovering natural products that can offer neuroprotection following toluene exposure is an essential alternative. Nigella sativa (NS), a popular natural supplement, is a good candidate due to its antioxidant and neuroprotective properties. The study aimed to investigate the protective potentials of NS against toluene, on recognition memory performance in the Novel Object Recognition (NOR) test and cellular morphometric measurements of hippocampal CA1 pyramidal neurons. Adult male ICR mice (n=30) were randomly divided into five groups: Group 1 (G1) - corn oil (CO), G2 – Toluene (TOL), G3 - Toluene and NS seed suspension (TOL-NSS), G4 - Toluene and NS oil (TOL-NSO), G5 - Toluene and thymoquinone (TOL-TQ). NS supplementations were administered orally once daily for 14 consecutive days while 500 mg/kg b.w. toluene was administered intraperitoneally from day 8 until day 14. Behavioural NOR test was conducted. Subsequently, mice were intracardially perfused and harvested brains were histologically processed. The somatic size and shape of hippocampal CA1 pyramidal neurons were quantified according to specific morphometric parameters. Toluene reduced recognition memory performance of mice and somatic size of hippocampal CA1 pyramidal neurons. Contradictorily, TQ, NSO, and NSS improved mice recognition memory and somatic size of hippocampal CA1 pyramidal neurons. Somatic shape of hippocampal CA1 pyramidal was unaffected by the various treatments. Although non-significant differences were observed, the results indicate the tendency for toluene to cause impairment, while NS supplementations to improve mice recognition memory performance and brain hippocampal neuronal structure.

MDGA2 Constrains Glutamatergic Inputs Selectively onto CA1 Pyramidal Neurons to Optimize Neural Circuits for Plasticity, Memory, and Social Behavior.

Synapse organizers are essential for the development, transmission, and plasticity of synapses. Acting as rare synapse suppressors, the MAM domain containing glycosylphosphatidylinositol anchor (MDGA) proteins contributes to synapse organization by inhibiting the formation of the synaptogenic neuroligin-neurexin complex. A previous analysis of MDGA2 mice lacking a single copy of Mdga2 revealed upregulated glutamatergic synapses and behaviors consistent with autism. However, MDGA2 is expressed in diverse cell types and is localized to both excitatory and inhibitory synapses. Differentiating the network versus cell-specific effects of MDGA2 loss-of-function requires a cell-type and brain region-selective strategy. To address this, we generated mice harboring a conditional knockout of Mdga2 restricted to CA1 pyramidal neurons. Here we report that MDGA2 suppresses the density and function of excitatory synapses selectively on pyramidal neurons in the mature hippocampus. Conditional deletion of Mdga2 in CA1 pyramidal neurons of adult mice upregulated miniature and spontaneous excitatory postsynaptic potentials, vesicular glutamate transporter 1 intensity, and neuronal excitability. These effects were limited to glutamatergic synapses as no changes were detected in miniature and spontaneous inhibitory postsynaptic potential properties or vesicular GABA transporter intensity. Functionally, evoked basal synaptic transmission and AMPAR receptor currents were enhanced at glutamatergic inputs. At a behavioral level, memory appeared to be compromised in Mdga2 cKO mice as both novel object recognition and contextual fear conditioning performance were impaired, consistent with deficits in long-term potentiation in the CA3-CA1 pathway. Social affiliation, a behavioral analog of social deficits in autism, was similarly compromised. These results demonstrate that MDGA2 confines the properties of excitatory synapses to CA1 neurons in mature hippocampal circuits, thereby optimizing this network for plasticity, cognition, and social behaviors.

Object segmentation for image indexing in large database

It is a challenging task to devise an effective model for object segmentation considering numerous classes because different classes might have different features and different backgrounds. We propose a unique segmentation and classification model to detect and classify objects. We propose a extended version of the U-Net model for object segmentation whereas, for the classification task, we propose an effective fusion scheme by exploiting two popular CNN models including ResNet50 and MobileNet. We conduct experiments on the Caltech101 benchmark dataset which contains 8677 images grouped into 101 classes. Besides, to examine the performance of our proposed segmentation method on object detection, we devise a polygonal ground-truth dataset based on the Caltech101 benchmark dataset. The unique feature of polygon shape ground truth is that it creates a mask of the target image in which the probability of noise is very low where there is noise in the bounding box ground truth. Extensive experiments on the Caltech101 benchmark dataset demonstrate the efficacy of our proposed approaches compared to the other existing models with a segmentation accuracy of 95.94% and classification accuracy of 99.90%. We also achieve an average IoU score of 0.98 which validates the effective object recognition performance of our model.

Walking into a Modern Painting: The Impacts of Using Virtual Reality on Student Learning Performance and Experiences in Art Appreciation

This study reconstructed a modern painting into a fully-immersive Virtual Reality (VR) painting allowing users to walk into the painting’s 3D world and move around, and employed constructivism with a model of art appreciation to investigate the effects of applying VR techniques in appreciating the modern painting on student learning outcomes. Participants in the study included 60 undergraduates from a university in the midwestern United States. Quasi-experimental study designs and quantitative analysis methods were adopted to analyze students’ responses to the activities of modern painting appreciation through 2D and VR paintings. Results indicated that using the VR painting had significant negative impacts on students’ performance of object recognition in the painting and interpretations towards the painting, but no effects on the painting analysis and judgements. Students using the VR painting showed significantly higher interest and enjoyment than those using the 2D painting. Compared to those viewing the VR painting prior to the 2D painting appreciation, students who only viewed the 2D painting had significantly better learning performance. This study contributes to the lack of empirical VR research in art appreciation, offering insights into the application of using VR in appreciating modern paintings, and providing recommendations for future studies.

Regulation of Meat Duck Activeness through Photoperiod Based on Deep Learning.

The regulation of duck physiology and behavior through the photoperiod holds significant importance for enhancing poultry farming efficiency. To clarify the impact of the photoperiod on group-raised duck activeness and quantify duck activeness, this study proposes a method that employs a multi-object tracking model to calculate group-raised duck activeness. Then, duck farming experiments were designed with varying photoperiods as gradients to assess this impact. The constructed multi-object tracking model for group-raised ducks was based on YOLOv8. The C2f-Faster-EMA module, which combines C2f-Faster with the EMA attention mechanism, was used to improve the object recognition performance of YOLOv8. Furthermore, an analysis of the tracking performance of Bot-SORT, ByteTrack, and DeepSORT algorithms on small-sized duck targets was conducted. Building upon this foundation, the duck instances in the images were segmented to calculate the distance traveled by individual ducks, while the centroid of the duck mask was used in place of the mask regression box's center point. The single-frame average displacement of group-raised ducks was utilized as an intuitive indicator of their activeness. Farming experiments were conducted with varying photoperiods (24L:0D, 16L:8D, and 12L:12D), and the constructed model was used to calculate the activeness of group-raised ducks. The results demonstrated that the YOLOv8x-C2f-Faster-EMA model achieved an object recognition accuracy (mAP@50-95) of 97.9%. The improved YOLOv8 + Bot-SORT model achieved a multi-object tracking accuracy of 85.1%. When the photoperiod was set to 12L:12D, duck activeness was slightly lower than that of the commercial farming's 24L:0D lighting scheme, but duck performance was better. The methods and conclusions presented in this study can provide theoretical support for the welfare assessment of meat duck farming and photoperiod regulation strategies in farming.

Evaluation of Camera Recognition Performance under Blockage Using Virtual Test Drive Toolchain.

This study is the first to develop technology to evaluate the object recognition performance of camera sensors, which are increasingly important in autonomous vehicles owing to their relatively low price, and to verify the efficiency of camera recognition algorithms in obstruction situations. To this end, the concentration and color of the blockage and the type and color of the object were set as major factors, with their effects on camera recognition performance analyzed using a camera simulator based on a virtual test drive toolkit. The results show that the blockage concentration has the largest impact on object recognition, followed in order by the object type, blockage color, and object color. As for the blockage color, black exhibited better recognition performance than gray and yellow. In addition, changes in the blockage color affected the recognition of object types, resulting in different responses to each object. Through this study, we propose a blockage-based camera recognition performance evaluation method using simulation, and we establish an algorithm evaluation environment for various manufacturers through an interface with an actual camera. By suggesting the necessity and timing of future camera lens cleaning, we provide manufacturers with technical measures to improve the cleaning timing and camera safety.

Objective Vision

Abstract Convolutional neural networks (CNNs) are a key technology powering the automated technologies of seeing known as computer vision. CNNs have been especially successful in systems that perform object recognition from visual data. This article examines the persistence of a mid-twentieth-century ontology of the digital image in these contemporary technologies. While CNNs are multidimensional, their ontology flattens distinctions between background and foreground, between subjects and objects, and even the relations established among the categories of information used to organize and train these models. This ontology enables the introduction and amplification of bias and troubling correlations and the transfer or slippage of learned associations between humans and objects found in the training image archives. Inspecting and interpreting what CNNs learn and index through their complex architectures can be difficult if not impossible because of how they encode and obfuscate quite human ways of seeing the world and the image repertoires used to train these algorithms that are rife with residues of prior representations.

Multi-view convolutional vision transformer for 3D object recognition

With the rapid development of three-dimensional (3D) vision technology and the increasing application of 3D objects, there is an urgent need for 3D object recognition in the fields of computer vision, virtual reality, and artificial intelligence robots. The view-based method projects 3D objects into two-dimensional (2D) images from different viewpoints and applies convolutional neural networks (CNN) to model the projected views. Although these methods have achieved excellent recognition performance, there is not sufficient information interaction between the features of different views in these methods. Inspired by the recent success achieved by vision transformer (ViT) in image recognition, we propose a hybrid network by taking advantage of CNN to extract multi-scale local information of each view, and of transformer to capture the relevance of multi-scale information between different views. To verify the effectiveness of our multi-view convolutional vision transformer (MVCVT), we conduct experiments on two public benchmarks, ModelNet40 and ModelNet10, and compare with those of some state-of-the-art methods. The final results show that MVCVT has competitive performance in 3D object recognition.