Viewpoint Changes Research Articles

Advancing Sustainable Human Security in a Digital Era through Inclusivity and Accountability

Abstract The purpose of this article is to look at how a humanized global governance framework based on human rights, ethics, and harnessing humanities may ensure that artificial intelligence (AI) is utilized for promoting sustainable human security for all and safeguarding human rights. The digital era adds to substantial changes in understanding key viewpoints in international humanitarian law and related humanitarian practice in this environment. Notably, this article reflects the ideological, legal, social, political, and economic development of the concept of ‘human security’ over the years. Constitutions will inevitably undergo revisions and modifications to adapt to such developments. The article also focuses on how AI might help achieve the United Nations Sustainable Development Goals (SDG s) and other humanitarian goals.

시 이미지에 대한 영화적 이해 : 정지용의 「카ᅋᅦ·ᅋᅳ란스」와 김광균의 「夜車」 를 대상으로

This study attempted to examine the development of poetry images and their structure by utilizing the unique characteristics of the cinema genre. This shows a different approach from the attitude of discussing modernist poetry by limiting it to the level of painting. If a painting is structured as a single overall screen, a cinema has the characteristic of assembling fragmentary screens to structure the whole. Therefore, the attitude of understanding poetry images cinematically requires appropriate use and analysis of free viewpoint changes that allow the screen to be divided into several parts and editing methods necessary to effectively assemble the results that appear through this. In addition, the appropriate use and arrangement of sound effects are also elements that should be examined. This cinematic understanding of poetry images not only helps in understanding the intimate structuring method of poetry images, but also confirms that it can be a good means for examining the continuation and deepening of the emotions that the poem is trying to convey.

Cross-View Multi-Scale Re-Identification Network in the Perspective of Ground Rotorcraft Unmanned Aerial Vehicle

Traditional Re-Identification (Re-ID) schemes often rely on multiple cameras from the same perspective to search for targets. However, the collaboration between fixed cameras and unmanned aerial vehicles (UAVs) is gradually becoming a new trend in the surveillance field. Facing the significant perspective differences between fixed cameras and UAV cameras, the task of Re-ID is facing unprecedented challenges. In the setting of a single perspective, although significant advancements have been made in person Re-ID models, their performance markedly deteriorates when confronted with drastic viewpoint changes, such as transitions from aerial to ground-level perspectives. This degradation in performance is primarily attributed to the stark variations between viewpoints and the significant differences in subject posture and background across various perspectives. Existing methods focusing on learning local features have proven to be suboptimal in cross-perspective Re-ID tasks. The reason lies in the perspective distortion caused by the top-down viewpoint of drones, and the richer and more detailed texture information observed from a ground-level perspective, which leads to notable discrepancies in local features. To address this issue, the present study introduces a Multi-scale Across View Model (MAVM) that extracts features at various scales to generate a richer and more robust feature representation. Furthermore, we incorporate a Cross-View Alignment Module (AVAM) that fine-tunes the attention weights, optimizing the model’s response to critical areas such as the silhouette, attire textures, and other key features. This enhancement ensures high recognition accuracy even when subjects change posture and lighting conditions. Extensive experiments conducted on the public dataset AG-ReID have demonstrated the superiority of our proposed method, which significantly outperforms existing state-of-the-art techniques.

Person re-identification transformer with patch attention and pruning

Person re-identification (Re-ID), which is widely used in surveillance and tracking systems, aims to search individuals as they move between different camera views by maintaining identity across various camera views. In the realm of person re-identification (Re-ID), recent advancements have introduced convolutional neural networks (CNNs) and vision transformers (ViTs) as promising solutions. While CNN-based methods excel in local feature extraction, ViTs have emerged as effective alternatives to CNN-based person Re-ID, offering the ability to capture long-range dependencies through multi-head self-attention without relying on convolution and downsampling. However, it still faces challenges such as changes in illumination, viewpoint, pose, low resolutions, and partial occlusions. To address the limitations of widely used person Re-ID datasets and improve the generalization, we present a novel person Re-ID method that enhances global and local information interactions using self-attention modules within a ViT network. It leverages dynamic pruning to extract and prioritize essential image patches effectively. The designed patch selection and pruning for person Re-ID model resulted in a robust feature extractor even in scenarios with partial occlusion, background clutter, and illumination variations. Empirical validation demonstrates its superior performance compared to previous approaches and its adaptability across various domains.

360-degree Human Video Generation with 4D Diffusion Transformer

We present a novel approach for generating 360-degree high-quality, spatiotemporally coherent human videos from a single image. Our framework combines the strengths of diffusion transformers for capturing global correlations across viewpoints and time, and CNNs for accurate condition injection. The core is a hierarchical 4D transformer architecture that factorizes self-attention across views, time steps, and spatial dimensions, enabling efficient modeling of the 4D space. Precise conditioning is achieved by injecting human identity, camera parameters, and temporal signals into the respective transformers. To train this model, we collect a multi-dimensional dataset spanning images, videos, multi-view data, and limited 4D footage, along with a tailored multi-dimensional training strategy. Our approach overcomes the limitations of previous methods based on generative adversarial networks or vanilla diffusion models, which struggle with complex motions, viewpoint changes, and generalization. Through extensive experiments, we demonstrate our method's ability to synthesize 360-degree realistic, coherent human motion videos, paving the way for advanced multimedia applications in areas such as virtual reality and animation.

IDENTITY CONFUSION IN DOROTHY WEST’S THE LIVING IS EASY

Literature is a media for conveying the authors’ ideas and feelings to the payers, or it is a mean of relief for them to bare their souls. In this context, literature involves an enormous place in human life. In this regard, African American literature has an important place in American literature and culture. It is also one of the strongest pillars of the literature produced by black writers in the United States of America. African American literature goes and continues in the course of history as oral literature from generation to generation. Since African Americans’ place changes gradually in the USA- due to racism in particular- their viewpoint of literature changes, too. African American history predates the foundation of the United States of America as an independent country, so their literature has deep roots, consisting of rich oral culture in poetry, including gospel music, blues, rap, and spirituals along with written poetry, and slave narrations. Although African Americans come from slave ancestors, they have been able to leave a deep effect on the literature of the United States when they are brought to the continent of America. African American literature is mainly based on autobiographical spiritual narratives, and before the American Civil War African Americans’ literature consists of memoirs of people who escape from slavery. So, African American literature has witnessed the problem of racial discrimination in its existential aspect. But in the progress of time, black writers go deep into verbal literature and perform their own experiences. Dorothy West, in her novel Living is Easy criticizes the blacks who mimes the whites. When we scrutinize, it is possible to penetrate that the writer wants to reflect her own experiences via narration and criticizes her own past. Writing is a kind of purgation for West since she writes about herself. In this study, we aim to point out the impulses that foster Dorothy West’s narration from a Freudian point of view.

Garment Animation NeRF with Color Editing

AbstractGenerating high‐fidelity garment animations through traditional workflows, from modeling to rendering, is both tedious and expensive. These workflows often require repetitive steps in response to updates in character motion, rendering viewpoint changes, or appearance edits. Although recent neural rendering offers an efficient solution for computationally intensive processes, it struggles with rendering complex garment animations containing fine wrinkle details and realistic garment‐and‐body occlusions, while maintaining structural consistency across frames and dense view rendering. In this paper, we propose a novel approach to directly synthesize garment animations from body motion sequences without the need for an explicit garment proxy. Our approach infers garment dynamic features from body motion, providing a preliminary overview of garment structure. Simultaneously, we capture detailed features from synthesized reference images of the garment's front and back, generated by a pre‐trained image model. These features are then used to construct a neural radiance field that renders the garment animation video. Additionally, our technique enables garment recoloring by decomposing its visual elements. We demonstrate the generalizability of our method across unseen body motions and camera views, ensuring detailed structural consistency. Furthermore, we showcase its applicability to color editing on both real and synthetic garment data. Compared to existing neural rendering techniques, our method exhibits qualitative and quantitative improvements in garment dynamics and wrinkle detail modeling. Code is available at https://github.com/wrk226/GarmentAnimationNeRF.

A Novel Method for Extracting DBH and Crown Base Height in Forests Using Small Motion Clips

The diameter at breast height (DBH) and crown base height (CBH) are important indicators in forest surveys. To enhance the accuracy and convenience of DBH and CBH extraction for standing trees, a method based on understory small motion clips (a series of images captured with slight viewpoint changes) has been proposed. Histogram equalization and quadtree uniformization algorithms are employed to extract image features, improving the consistency of feature extraction. Additionally, the accuracy of depth map construction and point cloud reconstruction is improved by minimizing the variance cost function. Six 20 m × 20 m square sample plots were selected to verify the effectiveness of the method. Depth maps and point clouds of the sample plots were reconstructed from small motion clips, and the DBH and CBH of standing trees were extracted using a pinhole imaging model. The results indicated that the root mean square error (RMSE) for DBH extraction ranged from 0.60 cm to 1.18 cm, with relative errors ranging from 1.81% to 5.42%. Similarly, the RMSE for CBH extraction ranged from 0.08 m to 0.21 m, with relative errors ranging from 1.97% to 5.58%. These results meet the accuracy standards required for forest surveys. The proposed method enhances the efficiency of extracting tree structural parameters in close-range photogrammetry (CRP) for forestry. A rapid and accurate method for DBH and CBH extraction is provided by this method, laying the foundation for subsequent forest resource management and monitoring.

Image Registration Algorithm for Stamping Process Monitoring Based on Improved Unsupervised Homography Estimation

Homography estimation is a crucial task in aligning template images with target images in stamping monitoring systems. To enhance the robustness and accuracy of homography estimation against random vibrations and lighting variations in stamping environments, this paper proposes an improved unsupervised homography estimation model. The model takes as input the channel-stacked template and target images and outputs the estimated homography matrix. First, a specialized deformable convolution module and Group Normalization (GN) layer are introduced to expand the receptive field and enhance the model’s ability to learn rotational invariance when processing large, high-resolution images. Next, a multi-scale, multi-stage unsupervised homography estimation network structure is constructed to improve the accuracy of homography estimation by refining the estimation through multiple stages, thereby enhancing the model’s resistance to scale variations. Finally, stamping monitoring image data is incorporated into the training through data fusion, with data augmentation techniques applied to randomly introduce various levels of perturbation, brightness, contrast, and filtering to improve the model’s robustness to complex changes in the stamping environment, making it more suitable for monitoring applications in this specific industrial context. Compared to traditional methods, this approach provides better homography matrix estimation when handling images with low texture, significant lighting variations, or large viewpoint changes. Compared to other deep-learning-based homography estimation methods, it reduces estimation errors and performs better on stamping monitoring images, while also offering broader applicability.

LiDAR‐based place recognition for mobile robots in ground/water surface multiple scenes

AbstractLiDAR‐based 3D place recognition is an essential component of simultaneous localization and mapping systems in multi‐scene robotic applications. However, extracting discriminative and generalizable global descriptors of point clouds is still an open issue due to the insufficient use of the information contained in the LiDAR scans in existing approaches. In this paper, we propose a novel spatial‐temporal point cloud encoding network for multiple scenes, dubbed STM‐Net, to fully fuse the multi‐view spatial information and temporal information of LiDAR point clouds. Specifically, we first develop a spatial feature encoding module consisting of the single‐view transformer and multi‐view transformer. The module learns the correlation both within a single view and between two views by utilizing the multi‐layer range images generated by spherical projection and multi‐layer bird's eye view images generated by top‐down projection. Then in the temporal feature encoding module, we exploit the temporal transformer to mine the temporal information in the sequential point clouds, and a NetVLAD layer is applied to aggregate features and generate sub‐descriptors. Furthermore, we use a GeM pooling layer to fuse more information along the time dimension for the final global descriptors. Extensive experiments conducted on unmanned ground/surface vehicles with different LiDAR configurations indicate that our method (1) achieves superior place recognition performance than state‐of‐the‐art algorithms, (2) generalizes well to diverse sceneries, (3) is robust to viewpoint changes, (4) can operate in real‐time, demonstrating the effectiveness and satisfactory capability of the proposed approach and highlighting its promising applications in multi‐scene place recognition tasks.

Spatial-Temporal Contextual Aggregation Siamese Network for UAV Tracking

In recent years, many studies have used Siamese networks (SNs) for UAV tracking. However, there are two problems with SNs for UAV tracking. Firstly, the information sources of the SNs are the invariable template patch and the current search frame. The static template information lacks the perception of dynamic feature information flow, and the shallow feature extraction and linear sequential mapping severely limit the mining of feature expressiveness. This makes it difficult for many existing SNs to cope with the challenges of UAV tracking, such as scale variation and viewpoint change caused by the change in height and angle of the UAV, and the challenges of background clutter and occlusion caused by complex aviation backgrounds. Secondly, the SNs trackers for UAV tracking still struggle with extracting lightweight and effective features. A tracker with a heavy-weighted backbone is not welcome due to the limited computing power of the UAV platform. Therefore, we propose a lightweight spatial-temporal contextual Siamese tracking system for UAV tracking (SiamST). The proposed SiamST improves the UAV tracking performance by augmenting the horizontal spatial information and introducing vertical temporal information to the Siamese network. Specifically, a high-order multiscale spatial module is designed to extract multiscale remote high-order spatial information, and a temporal template transformer introduces temporal contextual information for dynamic template updating. The evaluation and contrast results of the proposed SiamST with many state-of-the-art trackers on three UAV benchmarks show that the proposed SiamST is efficient and lightweight.

Conformal Image Viewpoint Invariant

In this paper, we introduce an invariant by image viewpoint changes by applying an important theorem in conformal geometry stating that every surface of the Minkowski space R3,1 leads to an invariant by conformal transformations. For this, we identify the domain of an image to the disjoint union of horospheres ∐αHα of R3,1 by means of the powerful tools of the conformal Clifford algebras. We explain that every viewpoint change is given by a planar similarity and a perspective distortion encoded by the latitude angle of the camera. We model the perspective distortion by the point at infinity of the conformal model of the Euclidean plane described by D. Hestenesand we clarify the spinor representations of the similarities of the Euclidean plane. This leads us to represent the viewpoint changes by conformal transformations of ∐αHα for the Minkowski metric of the ambient space.

A Review of Deep Learning Based Video Action Recognition Techniques

Video action recognition is an important research direction in the field of computer vision and pattern recognition, with extensive applications in intelligent video surveillance, human-computer interaction, and sports analysis. The development of data storage and computing hardware over the past decade has driven a shift from traditional feature extraction and machine learning algorithms to deep learning-based approaches. This paper reviews the current state of development, problems, and future research directions of video action recognition techniques. Traditional methods are gradually being replaced by deep learning methods such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long-short-term memory networks (LSTMs). These methods automatically extract features and handle time-dependency, significantly improving the accuracy and robustness of action recognition. In particular, models based on the attention mechanism further enhance action recognition performance by dynamically adjusting the focus of attention, a current hot spot in research. Despite many advances, video action recognition still faces several challenges, including high computational resource requirements, complex model training, dataset bias issues, and variations in real-world application scenarios such as viewpoint changes, lighting changes, and occlusion. Future research can explore multi-modal fusion, lightweight models, self-supervised learning, and cross-domain transfer learning to improve the accuracy, robustness, and generalization of action recognition. The review provided aims to offer researchers a comprehensive perspective on the current state of development and future research directions of video action recognition technology.

LSGDDN-LCD: An appearance-based loop closure detection using local superpixel grid descriptors and incremental dynamic nodes

Loop Closure Detection (LCD) is an essential component of visual Simultaneous Localization and Mapping (SLAM) systems. It enables the recognition of previously visited scenes to eliminate pose and map estimate drifts arising from long-term exploration. However, current appearance-based LCD methods face significant challenges, including high computational costs, viewpoint changes, and dynamic objects in scenes. This paper introduced an online appearance based LCD using Local Superpixel Grids Descriptor (LSGD) and Dynamic Nodes (DN), i.e., LSGDDN-LCD, to find similarities between scenes via handcrafted features extracted from the LSGD. Additionally, we proposed the adaptive mechanism to group similar scenes called DynamicNodes, which incrementally adjusted the database in an online manner, allowing for efficient and online retrieval of previously viewed images without need of the pre-training. Experimental results confirmed that the LSGDDN-LCD significantly improved LCD precision–recall and efficiency, and outperformed several state-of-the-art (SOTA) approaches on public and our own datasets, indicating its great potential as a generic LCD framework. Our implementation of the LSGDDN-LCD approach and the datasets were open-sourced on GitHub (https://github.com/BaoshengZhang0/LSGDDN-LCD.git).

SDNet: Spatial adversarial perturbation local descriptor learned with the dynamic probabilistic weighting loss

Local descriptor is an important upstream component in computer vision tasks. Despite considerable advances with deep learning-based descriptors, recent descriptors are not robust enough to handle widespread viewpoint changes in image matching tasks such as localization and 3D reconstruction. In this study, SDNet, a robust descriptor utilizing spatial adversarial perturbations, trained with a novel dynamic probabilistic weighting loss to enhance performance under such challenges. First, to increase the robustness and generalization ability of the network across spatially transformed instances, a innovative module for generating hard negative samples via spatial adversarial perturbations is designed. By maximizing adversarial loss, this module generates more complex patches, significantly enhancing the geometric robustness of the descriptor. Importantly, this module integrates seamlessly with existing patch-based descriptors without necessitating extra training data. Second, to mitigate the imbalance in the matching relationship between generated positive and negative pairs, the label weighted triplet loss is proposed, which markedly improves descriptor performance. Third, a comprehensive theoretical analysis of preceding studies is carried out from a gradient perspective, and a probabilistic dynamic weighting approach that adaptively emphasizes weighting functions with higher likelihoods is proposed to improve training performance of the descriptor. Extensive experiments are carried out on mainstream datasets. These comprehensive experiments demonstrate the effectiveness of SDNet, and the proposed method achieves significant improvements on the UBC, HPatches and ETH datasets, outperforming current state-of-the-art methods. The code is available at https://github.com/webd111/sdnet.

SMART: Syntax-Calibrated Multi-Aspect Relation Transformer for Change Captioning.

Change captioning aims to describe the semantic change between two similar images. In this process, as the most typical distractor, viewpoint change leads to the pseudo changes about appearance and position of objects, thereby overwhelming the real change. Besides, since the visual signal of change appears in a local region with weak feature, it is difficult for the model to directly translate the learned change features into the sentence. In this paper, we propose a syntax-calibrated multi-aspect relation transformer to learn effective change features under different scenes, and build reliable cross-modal alignment between the change features and linguistic words during caption generation. Specifically, a multi-aspect relation learning network is designed to 1) explore the fine-grained changes under irrelevant distractors (e.g., viewpoint change) by embedding the relations of semantics and relative position into the features of each image; 2) learn two view-invariant image representations by strengthening their global contrastive alignment relation, so as to help capture a stable difference representation; 3) provide the model with the prior knowledge about whether and where the semantic change happened by measuring the relation between the representations of captured difference and the image pair. Through the above manner, the model can learn effective change features for caption generation. Further, we introduce the syntax knowledge of Part-of-Speech (POS) and devise a POS-based visual switch to calibrate the transformer decoder. The POS-based visual switch dynamically utilizes visual information during different word generation based on the POS of words. This enables the decoder to build reliable cross-modal alignment, so as to generate a high-level linguistic sentence about change. Extensive experiments show that the proposed method achieves the state-of-the-art performance on the three public datasets.

A Semantic Spatial Structure-Based Loop Detection Algorithm for Visual Environmental Sensing

Loop closure detection is an important component of the Simultaneous Localization and Mapping (SLAM) algorithm, which is utilized in environmental sensing. It helps to reduce drift errors during long-term operation, improving the accuracy and robustness of localization. Such improvements are sorely needed, as conventional visual-based loop detection algorithms are greatly affected by significant changes in viewpoint and lighting conditions. In this paper, we present a semantic spatial structure-based loop detection algorithm. In place of feature points, robust semantic features are used to cope with the variation in the viewpoint. In consideration of the semantic features, which are region-based, we provide a corresponding matching algorithm. Constraints on semantic information and spatial structure are used to determine the existence of loop-back. A multi-stage pipeline framework is proposed to systematically leverage semantic information at different levels, enabling efficient filtering of potential loop closure candidates. To validate the effectiveness of our algorithm, we conducted experiments using the uHumans2 dataset. Our results demonstrate that, even when there are significant changes in viewpoint, the algorithm exhibits superior robustness compared to that of traditional loop detection methods.

Multi-dimensional impact of COVID-19 on active mobility in urban China: a scoping review of empirical knowledge.

Active mobility, such as cycling and walking, is assuming a growing significance in the daily lives of urban residents in China due to its positive impact on health and the environment. The impact of the COVID-19 epidemic has elicited significant changes in behaviors, perceptions, and intellectual viewpoints in this domain, potentially altering residents' physical activities in the long-term. This scoping review seeks to delve into the multi-dimensional influence of the epidemic on active mobility in urban China. A thorough investigation of English and Chinese studies up to January 2024 was conducted, drawing from articles in Web of Science and the Chinese National Knowledge Infrastructure. Only empirical studies providing knowledge into this subject were selected in the review, which comprised 20 studies in total. This review indicates that the influence of COVID-19 on active urban mobility in China has exhibited contradictory outcomes in terms of behavior. Besides, the experiences during the epidemic have significantly shaped citizens' attitudes and understanding of active mobility. The repercussions of the epidemic and the ensuing restrictions exacerbate the existing challenges faced by women, particularly those who are married, the older adult, and individuals with low incomes. The results exhibit both resemblances and idiosyncrasies when juxtaposed with prior research conducted in different nations. This analysis also offers valuable insights for improving active mobility across individual, organizational, and socio-political realms. The current state of empirical understanding in this field underscores the need for further research endeavors employing diverse methodological approaches and increased emphasis on the transformations anticipated in the post-epidemic era.

Unsupervised Object-Centric Learning From Multiple Unspecified Viewpoints.

Visual scenes are extremely diverse, not only because there are infinite possible combinations of objects and backgrounds but also because the observations of the same scene may vary greatly with the change of viewpoints. When observing a multi-object visual scene from multiple viewpoints, humans can perceive the scene compositionally from each viewpoint while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold. This ability is essential for humans to identify the same object while moving and to learn from vision efficiently. It is intriguing to design models that have a similar ability. In this article, we consider a novel problem of learning compositional scene representations from multiple unspecified (i.e., unknown and unrelated) viewpoints without using any supervision and propose a deep generative model which separates latent representations into a viewpoint-independent part and a viewpoint-dependent part to solve this problem. During the inference, latent representations are randomly initialized and iteratively updated by integrating the information in different viewpoints with neural networks. Experiments on several specifically designed synthetic datasets have shown that the proposed method can effectively learn from multiple unspecified viewpoints.

CamGNN: Cascade Graph Neural Network for Camera Re-Localization

In response to the inaccurate positioning of traditional camera relocation methods in scenes with large-scale or severe viewpoint changes, this study proposes a camera relocation method based on a cascaded graph neural network to achieve accurate scene relocation. Firstly, the NetVLAD retrieval method, which has advantages in image feature representation and similarity calculation, is used to retrieve the most similar images to a given query image. Then, the feature pyramid is employed to extract features at different scales of these images, and the features at the same scale are treated as nodes of the graph neural network to construct a single-layer graph neural network structure. Secondly, a top–down connection is used to cascade the single-layer graph structures, where the information of nodes in the previous graph is fused into a message node to improve the accuracy of camera pose estimation. To better capture the topological relationships and spatial geometric constraints between images, an attention mechanism is introduced in the single-layer graph structure, which helps to effectively propagate information to the next graph during the cascading process, thereby enhancing the robustness of camera relocation. Experimental results on the public dataset 7-Scenes demonstrate that the proposed method can effectively improve the accuracy of camera absolute pose localization, with average translation and rotation errors of 0.19 m and 6.9°, respectively. Compared to other deep learning-based methods, the proposed method achieves more than 10% improvement in both average translation and rotation accuracy, demonstrating highly competitive localization precision.