Viewpoint Changes Research Articles

A Systematic Literature Review of Virtual Reality Locomotion Taxonomies.

The change of the user's viewpoint in an immersive virtual environment, called locomotion, is one of the key components in a virtual reality interface. Effects of locomotion, such as simulator sickness or disorientation, depend on the specific design of the locomotion method and can influence the task performance as well as the overall acceptance of the virtual reality system. Thus, it is important that a locomotion method achieves the intended effects. The complexity of this task has increased with the growing number of locomotion methods and design choices in recent years. Locomotion taxonomies are classification schemes that group multiple locomotion methods and can aid in the design and selection of locomotion methods. Like locomotion methods themselves, there exist multiple locomotion taxonomies, each with a different focus and, consequently, a different possible outcome. However, there is little research that focuses on locomotion taxonomies. We performed a systematic literature review to provide an overview of possible locomotion taxonomies and analysis of possible decision criteria such as impact, common elements, and use cases for locomotion taxonomies. We aim to support future research on the design, choice, and evaluation of locomotion taxonomies and thereby support future research on virtual reality locomotion.

Rotation-equivariant correspondence matching based on a dual-activation mixer

Learning-based correspondence matching methods have become the mainstream techniques in many computer vision and robotics applications due to their robustness to large illumination and viewpoint changes. However, it is difficult for conventional convolutional neural networks (CNNs) to extract rotation-equivariant local features. Recent work has shown that CNNs combined with group-equivariant architectures are surprisingly effective at matching correspondences even when the images are rotated to a dramatic extent. However, the inherent shape (square) of convolution kernels causes the performance bottleneck of such rotation-equivariant CNNs. To address this issue, we propose an adaptive dual rotation-equivariant correspondence matching algorithm, which performs stably at all angles. We mathematically analyze the effectiveness of our proposed rotation-equivariant correspondence matching approach and its performance with respect to different convolution kernels. Extensive experiments on the Rotated-HPatches, SIM2E, and MegaDepth datasets demonstrate the effectiveness of our proposed algorithm.

The psychophysics of human three-dimensional active visuospatial problem-solving

Our understanding of how visual systems detect, analyze and interpret visual stimuli has advanced greatly. However, the visual systems of all animals do much more; they enable visual behaviours. How well the visual system performs while interacting with the visual environment and how vision is used in the real world is far from fully understood, especially in humans. It has been suggested that comparison is the most primitive of psychophysical tasks. Thus, as a probe into these active visual behaviours, we use a same-different task: Are two physical 3D objects visually the same? This task is a fundamental cognitive ability. We pose this question to human subjects who are free to move about and examine two real objects in a physical 3D space. The experimental design is such that all behaviours are directed to viewpoint change. Without any training, our participants achieved a mean accuracy of 93.82%. No learning effect was observed on accuracy after many trials, but some effect was seen for response time, number of fixations and extent of head movement. Our probe task, even though easily executed at high-performance levels, uncovered a surprising variety of complex strategies for viewpoint control, suggesting that solutions were developed dynamically and deployed in a seemingly directed hypothesize-and-test manner tailored to the specific task. Subjects need not acquire task-specific knowledge; instead, they formulate effective solutions right from the outset, and as they engage in a series of attempts, those solutions progressively refine, becoming more efficient without compromising accuracy.

Influence of Ni on corrosion and trench formation of low alloy steel in low H2S content sour corrosion environments

AbstractThe influence of Ni content on corrosion and trench formation of low alloy steel in a low H2S containing sour corrosion environment was investigated. The results show that Ni decreases the total amount of corrosion by forming a passive film containing Ni components, such as NiS and Ni3S2 on the steel surface as a result of long‐term corrosion and suppressing the anodic dissolution reaction, while increasing the trench depth. It was also identified that the Ni content had a more dominant effect on trench formation in steel regardless of the tested sour environments with 0.01 bar H2S gas (pH 4.0) and 0.001 M Na2S2O3 (pH 2.7) in this study. Based on the experimental findings, the mechanism of trenching propagation by Ni was discussed from the viewpoint of changes in surface film properties and associated difference of corrosion resistance between trench‐tip and bulk surface due to the variation in Ni content.

Critical Feminist Pedagogy in English Language Education: An Action Research Project on the Implementation of Feminist Views in a German Secondary School

AbstractBased on an action research project, this paper provides innovative teaching approaches for ELT to ensure gender equality through critical pedagogy. The qualitative study focuses on the reconstruction of students' perceptions through the analysis of group/peer talk allowing for the display of changing viewpoints after having dealt with feminist issues in class. Given the still limited representation of multiple individuals not only in society but also in secondary ELT coursebooks, critical educational practices have been concerned with the transformation of exclusionary schooling practices for the purpose of ensuring a just and equal future. Critical language education has been known to promote students' autonomy and sense of responsibility when it comes to the abolition of oppression and marginalization. Likewise, feminist approaches have the goal of fostering feminist principles and ethics of gender equality. The study, conducted in a German secondary school, reveals that the majority of learners welcome an exploration of feminist matters in the ELT classroom, because they recognize the significant connection between language learning and the exploration of societal issues. The implementation of critical and feminist ethics helped students become aware of prevailing gender inequalities; and their willingness for societal transformation highlights a visible increase in learner autonomy.

Multi-view graph convolution network for the recognition of human action with spatial and temporal occlusion problems

Human action recognition holds great significance in the field of social security. However, the challenges posed by occlusion and changes in viewpoint create specific obstacles in achieving accurate recognition. In this study, we propose a multi-view graph convolution fusion method to effectively address this issue. Specifically, considering the limited availability of public human action datasets that include occlusion, we introduce an adaptive multi-view spatial–temporal occlusion generation method. It allows us to generate occlusion skeleton data from multiple viewpoints, ensuring a close resemblance to real-life scenarios with minimal modifications to existing public datasets. Additionally, we present a plug-and-play multi-view information fusion module, briefed as MGL, which aims to solve the occlusion problem. The MGL combines the capabilities of Graph Convolutional network (GCN) and Long Short-Term Memory network (LSTM), in which GCN is employed to reconstruct human skeleton information using multi-view spatial occlusion data, and LSTM captures the long-term dependencies within the temporal sequences of the multi-view data. Moreover, an attention mask mechanism is introduced to highlight key joint features. Experiment results illustrate the excellent performance of our method on the NTU RGB+D 60 and NTU RGB+D 120 datasets.

Enhancing business students’ self-efficacy and learning outcomes: A multiple intelligences and technology approach

This research investigates the effect of multiple intelligences (MIs) teaching strategy with technology-enriched environments on business administration students’ self-efficacy, confidence, and learning outcomes. The study involved 276 participants from a university’s business administration department, undergoing an international business course. A range of technology-based activities incorporating MI strategies was employed, exploring key topics such as globalization, corporate social responsibility, and market segmentation. Hypothesis testing revealed that high expectations and changes in viewpoints positively impacted self-concept, ability, and motivation, contributing to improved learning outcomes. The integration of technology in teaching facilitated these transformations, demonstrating how digital tools like virtual reality, interactive platforms, and online tutorials can enhance learning experiences. However, the effect on learning gain varied when viewpoints changed, indicating a need for further research into the differential impact of technology on learning outcomes. Despite some limitations, the study offers compelling evidence supporting the integration of MIs teaching strategy with technology-enriched environments in business administration education. Future studies should further explore the role of emerging technologies in this context.

Explicit Points-of-Interest Driven Siamese Transformer for 3D LiDAR Place Recognition in Outdoor Challenging Environments

Place recognition (PR) plays a crucial role in simultaneous localization and mapping. Unfortunately, however, changes in viewpoints and conditions in large-scale environments impose tricky challenges for PR. To this end, this paper specifically proposes an explicit points-of-interest driven PR method, which consists of a road segmentation module based on grid-wise patch U-Transformer (GP_UT) and a PR module based on regions of interest Siamese Transformer NetVLAD (RI_STV). Especially for RI_STV, in the individual dimension, it is dedicated to exploring the local topological features of non-road regions of interest. In the spatial dimension, an improved Transformer is introduced to capture the global interactions between features of interest. In the cluster dimension, NetVLAD embedded with weighted pooling is created to perform weighted aggregation of feature clusters to generate discriminative and general descriptors. Evaluation on various datasets shows that our customized method is not only impressively competitive, but also strikes the best balance between accuracy and real-time performance.

Distilled representation using patch-based local-to-global similarity strategy for visual place recognition

Visual Place Recognition (VPR) is important for ensuring the accuracy and reliability of re-localization in a Visual Simultaneous Localization and Mapping (VSLAM) system, effectively reducing potential errors in mapping and navigation tasks. In VPR tasks, CNN-based VPR techniques encounter challenges in mitigating the impact of severe appearance changes caused by seasons and weather, as well as, viewpoint changes arising from robot motion deviations. To cope with this problem, a local-to-global similarity strategy is proposed in this paper. Specifically, an Auto-Encoder (AE) block is designed to distill appearance-invariant local features from AlexNet, where each local feature represents a specific image patch. Then, three local similarity measures, namely paired similarity, additional similarity, and adjacent similarity, are used to measure the similarity between paired images. Finally, weight encoders are introduced to combine the three local measures into a global one that achieves viewpoint-invariance. Extensive experiments show that our proposed method is robust to severe appearance and viewpoint changes while outperforming the current state-of-the-art methods on public visual place recognition datasets. Moreover, the proposed similarity strategy distinguishes the relationships between internal and external patches within images, effectively enhancing its recognition capability in real-world scenarios.

A feature enhanced RetinaNet-based for instance-level ship recognition

Instance-level ship recognition (ISR) has important applications in civil and military fields such as target acquisition, maritime surveillance, and ship situational awareness. Due to the special peculiarities of the marine environment and the rigidity of ships, the changes of viewpoint and scale lead to significant differences in the appearance of ships, which poses a challenge to ISR. Meanwhile, the lack of public datasets for ISR further increases the difficulty of recognition. Considerable work has been conducted on coarse- or fine-grained classification, and little research has been done on ISR. Therefore, a feature enhanced RetinaNet-based for ISR (FERISR) is proposed. First, an attention-aware pyramid network (APN) is designed to enhance the salience features of ship instances and integrate attention-guided features to maximize the use of multilayer information while reducing information redundancy. On this basis, a detail information enhancement module (DFEM) is proposed to refine the fused multi-scale feature maps to improve model performance in scale variations by further enhancing the ship features. At the same time, foggy environment at sea is simulated and the images of foggy and low-light scenario are tested to cope with the impacts caused by low visibility scenes. The ReidDataset is further divided into instance level to make a dataset for ISR(DISR), which is used to discuss the performance of FFRISR on ISR. The generalizability of FFRISR in different scenarios is also discussed. The experimental results demonstrate that FERISR can effectively improve recognition accuracy in viewpoint change, scale change and low visibility scenarios, as well as improve the detection speed. Finally, the effectiveness of APN and DFEM is further verified by ablation experiments.

Enhancing texture representation with deep tracing pattern encoding

Texture representation is a challenging problem due to the complex underlying physics of texture as well as the variations caused by changes in viewpoint. Recent progress in texture analysis has been made by the power of convolutional neural networks (CNNs) in feature learning. However, most current methods aggregate the features from the last convolutional layer of the CNN to obtain a global feature vector, which fails to leverage shallow low-level visual cues and cross-layer feature patterns, limiting their performance. In this paper, we propose to trace the features generated along the convolutional layers via a histogram of local 3D invariant binary patterns, called deep tracing patterns. This leads to a highly discriminative yet robust global feature representation module. Building such a module into a CNN backbone, we develop an effective approach for texture recognition. Extensive experiments on six benchmark datasets show that the proposed approach provides a discriminative and robust texture descriptor, with state-of-the-art performance achieved.

Global Multi-Scale Optimization and Prediction Head Attentional Siamese Network for Aerial Tracking

Siamese-based trackers have been widely used in object tracking. However, aerial remote tracking suffers from various challenges such as scale variation, viewpoint change, background clutter and occlusion, while most existing Siamese trackers are limited to single-scale and local features, making it difficult to achieve accurate aerial tracking. We propose the global multi-scale optimization and prediction head attentional Siamese network to solve this problem and improve aerial tracking performance. Firstly, a transformer-based multi-scale and global feature encoder (TMGFE) is proposed to obtain global multi-scale optimization of features. Then, the prediction head attentional module (PHAM) is proposed to add context information to the prediction head by adaptively adjusting the spatial position and channel contribution of the response map. Benefiting from these two components, the proposed tracker solves these challenges of aerial remote sensing tracking to some extent and improves tracking performance. Additionally, we conduct ablation experiments on aerial tracking benchmarks, including UAV123, UAV20L, UAV123@10fps and DTB70, to verify the effectiveness of the proposed network. The comparisons of our tracker with several state-of-the-art (SOTA) trackers are also conducted on four benchmarks to verify its superior performance. It runs at 40.8 fps on the GPU RTX3060ti.

Gait recognition with covariate separation based on adversarial learning

In response to the poor recognition accuracy caused by viewpoint changes and wearing changes in gait recognition problems, a viewpoint classifier and a wearing classifier are proposed to be connected after the feature extractor. The parameters of the feature extractor are updated using the gradient reversal mechanism so that its function is opposite to that of the two classifiers, thereby separating the viewpoint information, wearing information at the feature extraction level, and reducing the impact of these two most common factors on gait recognition. Comparative experiments on the CASIA-B dataset show that under BG and CL conditions, our model has improved by an average of 2.1% and 1.9% in cross-viewpoint accuracy compared to the baseline model. Our model is more robust under complex walking conditions.

중국과 한국의 영화 각색 사례에 나타난 텍스트 확장성과 의미론적 체계 연구

This paper is a study that started from the fact that in the production and formation of new content, not only the remediation of the original source, but also the relationship of mutual content influence between countries is constantly being considered. We will focus on cases where the novel was remade into a movie, then moved to a country, and then remade into a movie. Annie Baobei's novel 『Qiyue and Ansheng(七月与安生)』 was remade into the Chinese movie <Soulmate(七月與安生)> directed by Zeng Guoxiang(曾國 祥). In Korea, it is reborn as <Soulmate> directed by Min Yong-geun, and the characteristics of media transformation and adaptation revealed in this process are extracted. As novels are adapted into films, changes are accompanied by differences in narrative style and video media. In particular, it shows the characteristics of transformation and adaptation in the form of narrative loosely integrating not only the original short story but also several other short stories. This goes beyond the 'faithful adaptation' of the original work and materializes the generational critical mind of 'Beifiao', which is different from the original work, through the change of viewpoint and the expansion of narrative details. Meanwhile, the secondary creations made in this way are remade again in Korea, and in this third creation, more emphasis is placed on the characterization of the characters, breaking away from the 'faithful adaptation' of the existing films. In addition, while bringing the womance of female characters and generational critical mind, it is reset to fit the reality of Korea in the 2020s. In this process, it shows a critical look at the situation in which the problem of the gap between the rich and the poor and the value of vulgar success are particularly problematic for female characters. Through the adaptation work according to such media transformation, each creation shows a different point of view while sharing one original narrative. As the process of adapting the original work overlaps and expands through stages, the works acquire their own unique aesthetic system and thematic direction. This overturns the hierarchical relationship of original narratives in comparative studies and shows that adaptation can function as a free creative work without being conscious of anxiety about influence.

A narrow band of image dimensions is critical for face recognition

A key challenge in human and computer face recognition is to differentiate information that is diagnostic for identity from other sources of image variation. Here, we used a combined computational and behavioural approach to reveal critical image dimensions for face recognition. Behavioural data were collected using a sorting and matching task with unfamiliar faces and a recognition task with familiar faces. Principal components analysis was used to reveal the dimensions across which the shape and texture of faces in these tasks varied. We then asked which image dimensions were able to predict behavioural performance across these tasks. We found that the ability to predict behavioural responses in the unfamiliar face tasks increased when the early PCA dimensions (i.e. those accounting for most variance) of shape and texture were removed from the analysis. Image similarity also predicted the output of a computer model of face recognition, but again only when the early image dimensions were removed from the analysis. Finally, we found that recognition of familiar faces increased when the early image dimensions were removed, decreased when intermediate dimensions were removed, but then returned to baseline recognition when only later dimensions were removed. Together, these findings suggest that early image dimensions reflect ambient changes, such as changes in viewpoint or lighting, that do not contribute to face recognition. However, there is a narrow band of image dimensions for shape and texture that are critical for the recognition of identity in humans and computer models of face recognition.

Enhancing Robustness of Viewpoint Changes in 3D Skeleton-Based Human Action Recognition

Previous research on 3D skeleton-based human action recognition has frequently relied on a sequence-wise viewpoint normalization process, which adjusts the view directions of all segmented action sequences. This type of approach typically demonstrates robustness against variations in viewpoint found in short-term videos, a characteristic commonly encountered in public datasets. However, our preliminary investigation of complex action sequences, such as discussions or smoking, reveals its limitations in capturing the intricacies of such actions. To address these view-dependency issues, we propose a straightforward, yet effective, sequence-wise augmentation technique. This strategy enhances the robustness of action recognition models, particularly against changes in viewing direction that mainly occur within the horizontal plane (azimuth) by rotating human key points around either the z-axis or the spine vector, effectively creating variations in viewing directions. We scrutinize the robustness of this approach against real-world viewpoint variations through extensive empirical studies on multiple public datasets, including an additional set of custom action sequences. Despite the simplicity of our approach, our experimental results consistently yield improved action recognition accuracies. Compared to the sequence-wise viewpoint normalization method used with advanced deep learning models like Conv1D, LSTM, and Transformer, our approach showed a relative increase in accuracy of 34.42% for the z-axis and 10.86% for the spine vector.

STATE: Learning structure and texture representations for novel view synthesis

Novel viewpoint image synthesis is very challenging, especially from sparse views, due to large changes in viewpoint and occlusion. Existing image-based methods fail to generate reasonable results for invisible regions, while geometry-based methods have difficulties in synthesizing detailed textures. In this paper, we propose STATE, an end-to-end deep neural network, for sparse view synthesis by learning structure and texture representations. Structure is encoded as a hybrid feature field to predict reasonable structures for invisible regions while maintaining original structures for visible regions, and texture is encoded as a deformed feature map to preserve detailed textures. We propose a hierarchical fusion scheme with intra-branch and inter-branch aggregation, in which spatio-view attention allows multi-view fusion at the feature level to adaptively select important information by regressing pixel-wise or voxel-wise confidence maps. By decoding the aggregated features, STATE is able to generate realistic images with reasonable structures and detailed textures. Experimental results demonstrate that our method achieves qualitatively and quantitatively better results than state-of-the-art methods. Our method also enables texture and structure editing applications benefiting from implicit disentanglement of structure and texture. Our code is available at http://cic.tju.edu.cn/faculty/likun/projects/STATE.

A Change of Viewpoint in Translating Indonesian Novel Upacara into English

This research focuses on the translation of the Indonesian novel entitled Upacara into English. It deals with a change of viewpoint, including a change of perspective and a change of category of thought, which is categorized as a semantic shift under one of the translation procedures, namely modulation. The change occurs due to some factors, and one of them is the different cultural backgrounds between the author and the translator. Upacara is taken as the data source together with its translation Ceremony in English due to the fact that the novel involves the use of specific terms or expressions or words used in the preparation and the process of proceeding a ceremony in the life of Dayak tribes and these lead to the semantic shifts in the English target text. The cases of modulation found in the target text are significant. Using the descriptive qualitative method, the objectives of this research are to identify the types of modulation identified in the target text and the kinds of words which are being semantically shifted or modulated. The results show that the modulation found is not all of the types of free modulation, and the words which are modulated do not necessarily deal with the cultural words. There are some words or expressions which are semantically shifted out of all types of modulation. In the translation of the Indonesian novel Upacara into English Ceremony, the semantic shift under the modulation translation procedure covers both cultural and non-cultural words.

Neural Free‐Viewpoint Relighting for Glossy Indirect Illumination

AbstractPrecomputed Radiance Transfer (PRT) remains an attractive solution for real‐time rendering of complex light transport effects such as glossy global illumination. After precomputation, we can relight the scene with new environment maps while changing viewpoint in real‐time. However, practical PRT methods are usually limited to low‐frequency spherical harmonic lighting. All‐frequency techniques using wavelets are promising but have so far had little practical impact. The curse of dimensionality and much higher data requirements have typically limited them to relighting with fixed view or only direct lighting with triple product integrals. In this paper, we demonstrate a hybrid neural‐wavelet PRT solution to high‐frequency indirect illumination, including glossy reflection, for relighting with changing view. Specifically, we seek to represent the light transport function in the Haar wavelet basis. For global illumination, we learn the wavelet transport using a small multi‐layer perceptron (MLP) applied to a feature field as a function of spatial location and wavelet index, with reflected direction and material parameters being other MLP inputs. We optimize/learn the feature field (compactly represented by a tensor decomposition) and MLP parameters from multiple images of the scene under different lighting and viewing conditions. We demonstrate real‐time (512 x 512 at 24 FPS, 800 x 600 at 13 FPS) precomputed rendering of challenging scenes involving view‐dependent reflections and even caustics.

Skeleton-based action recognition with local dynamic spatial–temporal aggregation

Skeleton-based action recognition has attracted more and more attention due to its advantage in avoiding environmental noise including light transformations and viewpoint changing. Most current approaches consist of interleaving spatial-only modules and temporal-only modules, where messages are first spatially aggregated between human joints and then temporally delivered. Although efficient, such factorized design hinders direct information flow among joints in adjacent frames, thus failing to (1) effectively convey information in a larger neighborhood and (2) be inferior to capture short-term motion to distinguish similar action pairs. To handle these limitations, we propose spatial–temporal graph attention network (STGAT) to dynamically model local cross-spacetime information. Keeping the temporal-only modules unchanged, it inflates the spatial-only modules to perform spatial–temporal modeling from the local spatial–temporal neighborhood without a second transmission cost. Especially, different from previous spatial–temporal modeling methods, graph edges are adaptively computed to dynamically aggregate beneficial information to capture short-term movements, getting rid of predefined fixed connectivity. This ensures STGAT could dynamically attend to important joints in a local spatial–temporal neighborhood to capture critical short-term movements. While STGAT is theoretically effective in introducing local spatial–temporal information by comprising a large spatial–temporal neighborhood, we find its effectiveness is impeded by the inherent redundancy in local features. We propose three simple modules to reduce local feature redundancy to calibrate the feature modeling schema and further release the potential of STGAT, which (1) narrow the scope of self-attention operators, (2) dynamically weight joints along the temporal dimension, and (3) separate subtle motion from static features, respectively. As a result, STGAT achieves state-of-the-art performance on three large-scale datasets: NTU RGB＋D 60, NTU RGB＋D 120, and Kinetics Skeleton 400. Thanks to special care on local cross-spacetime information, STGAT generalizes better upon classifying hard similar actions than previous methods. Visualizations demonstrate that STGAT could intelligently attend to critical joints when dealing with different actions. Code is available at https://github.com/hulianyuyy/STGAT.