Search Results (180)

Occluded person re-identification (Re-ID) aims to accurately match occluded pedestrian images against complete gallery images captured across multiple cameras, a task that is critical to public security and intelligent surveillance systems. Existing graph neural network (GNN)-based methods typically assign uniform aggregation weights to all nodes, failing to reflect the inherent reliability difference between visible and occluded body regions, which allows noise from low-confidence nodes to propagate freely and corrupt the final pedestrian representation. To address this, we propose the Self-Information-Driven Gated Graph Convolutional Network (SI-GCN). Keypoint detection confidence scores are transformed into logarithmic self-information measures as uncertainty priors for a learnable gating mechanism. The proposed SIG module enables visible nodes to dominate information diffusion while occluded nodes absorb more from neighbors, achieving efficient feature updating. A dynamic confidence calibration (DCC) strategy further synchronizes node reliability estimates with feature evolution across successive GCN layers. Extensive experiments on six public benchmarks covering occluded, partial, and holistic Re-ID scenarios demonstrate that SI-GCN achieves state-of-the-art performance, with Rank-1 accuracy and mAP improvements of 1.2% and 0.9%, respectively, over the strongest baseline on the Occluded-REID dataset, demonstrating its strong potential for deployment in real-world public security and urban surveillance applications where occlusion is pervasive. Full article

Declining birth rates are reshaping higher education across East Asia, accelerating the large-scale underutilization and, in some contexts, partial abandonment of university campus assets. Although adaptive reuse has been widely discussed, campus transformation is often framed primarily as a programmatic or policy problem, with limited attention to the inherited spatial logic embedded in campus morphology. This study revisits Le Corbusier’s concept of unlimited growth as a generative framework for campus transformation. Rather than treating it as a museum-specific historical typology, the research reinterprets unlimited growth as a scalable spatial logic defined by modular continuity, circulation hierarchy, and open-ended sequencing. To enhance reproducibility and operational clarity, the study formalizes a typo-morphological decoding protocol—modules, circulation, and growth sequence—and applies it through plan-, section-, and diagram-based analysis. Through comparative examination of three museum precedents—Sanskar Kendra Museum, the National Museum of Western Art (Tokyo), and the Chandigarh Museum and Art Gallery—the study extracts a set of transferable spatial mechanisms: modular increment, circulation-centered ordering, directional displacement, and fifth-façade ecological continuity. These mechanisms are then translated into an operational right-sizing model and tested through a design-operational demonstrator on a single anonymized Taiwanese campus experiencing demographic contraction. The findings indicate that unlimited growth functions not merely as a formal principle but as a spatial governance logic that supports phased consolidation, adaptive recomposition, and system-level coherence under long-term uncertainty. Importantly, this framework contributes to sustainability by reducing land consumption through spatial consolidation, minimizing unnecessary new construction, enabling adaptive reuse of existing campus assets, and improving long-term resource-use efficiency through phased right-sizing and ecological continuity. This study further advances a reproducible, mechanism-based methodological framework for institutional spatial transformation, providing a transferable approach for large-scale campus restructuring under conditions of long-term demographic and environmental uncertainty. Full article

Differentiating AI-generated, real, or imitated artworks is becoming a tedious and computationally challenging problem in digital art analysis. AI-generated art has become nearly indistinguishable from human-made works, posing a significant threat to copyrighted content. This content is appearing on online platforms, at exhibitions, and in commercial galleries, thereby escalating the risk of copyright infringement. This sudden increase in generative images raises concerns like authenticity, intellectual property, and the preservation of cultural heritage. Without an automated, comprehensible system to determine whether an artwork has been AI-generated, authentic (real), or imitated, artists are prone to the reduction of their unique works. Institutions also struggle to curate and safeguard authentic pieces. As the variety of generative models continues to grow, it becomes a cultural necessity to build a robust, efficient, and transparent framework for determining whether a piece of art or an artist is involved in potential copyright infringement. To address these challenges, we introduce ArtUnmasked, a practical and interpretable framework capable of (i) efficiently distinguishing AI-generated artworks from real ones using a lightweight Spectral Artifact Identification (SPAI), (ii) a TagMatch-based artist filtering module for stylistic attribution, and (iii) a DINOv3–CLIP similarity module with patch-level correspondence that leverages the one-shot generalization ability of modern vision transformers to determine whether an artwork is authentic or imitated. We also created a custom dataset of ∼24K imitated artworks to complement our evaluation and support future research. The complete implementation is available in our GitHub repository. Full article

Computer vision and machine learning have accelerated the automation of animal re-identification pipelines used in conservation programs worldwide. For species with distinctive markings, such as the spot patterns of giraffes, these automated methods are crucial for research and population monitoring purposes. However, many tools are designed for experts, and their implementation requires substantial technical expertise. Research teams often use specialist software and workflows that are not accessible to the general public. In a zoo setting, visitors lack a simple way to identify an individual animal, and unique features are easily missed by untrained visitors. This study presents a three-part solution: a web interface for zoo visitors to upload photos, a deep learning model for giraffe torso detection, and a fast re-identification method for matching observations to a gallery of known individuals using server-side processing. We compare several re-identification methods (RootSIFT, MiewID, and MegaDescriptor) using a consistent evaluation protocol and report both identification performance and system latency for this closed-set zoo setting. Taken together, this study presents a visitor-facing web system that integrates existing re-identification models into a modular, real-time pipeline for zoo deployment, lowering the barrier to visitor participation and making state-of-the-art re-identification methods more accessible to the general public. Full article

The palm swamp landscapes, particularly the Vereda wetlands and their associated swamp gallery forests (VED.SGF), comprise essential yet threatened ecosystems within the Brazilian Cerrado. In addition to supporting significant portions of biodiversity, they provide critical ecosystem services such as storing and filtering excess rainwater and serving as major carbon reservoirs in organic soils. These wetlands are directly linked to the drainage systems of the headwaters of the main Cerrado river basins, which together account for about two-thirds of Brazil’s hydrographic basins. Mapping and managing VED.SGF ecosystems through remote sensing present major challenges addressed in this first study. Their narrow, dendritic, and complex tabular spatial pattern, often elongated along watersheds on scales of hundreds of kilometers, suffering distortions due to human impact, and the limited amount of annotated data make segmentation particularly challenging. Existing deep learning (DL) methods, typically pre-trained on natural images, struggle to capture the spectral and spatial intricacies of these ecosystems. This study introduces a trained-from-scratch U-Net model supported by field-based experimental procedures to ensure high-quality wetland annotations. The resulting dataset covers approximately 7300 km² in western Bahia and provides domain-specific weights tailored to remote sensing applications. Using high-resolution (4.6 m) RGB mosaics, the model was trained, validated, and tested to establish a reproducible and scalable pipeline. The proposed method achieved robust results in an independent test area of 8040 km², with a mean IoU of 0.728, F1-score of 0.843, and Cohen’s Kappa of 0.837. These results demonstrate consistent performance and strong generalization to new areas, establishing a scientifically reliable baseline that situates the model competitively within the current state of the art. By releasing both the model weights and annotated dataset, this study provides valuable resources to advance future research on mapping and monitoring these unique and strategic wetland ecosystems. Full article

This article examines the critical role of archival exploration in decoding the painting practice of a modern Singaporean artist Liu Kang (1911–2004). Given Liu Kang’s undocumented artistic process and the absence of preserved paint tubes or technical notes, the research methodology combined a wide range of primary and secondary archival records with previous analytical investigations of his paintings. By examining works from the National Gallery Singapore and the Liu family collections created between 1927 and 1999, the research deduced the brands and types of materials he used. Hence, this article highlights the crucial and complementary role of diverse archival sources in technical art research. Consequently, primary archival sources, such as interviews with the artist, studio photographs and a TV documentary, provided evidence of his tools and methods. These were cross-referenced with secondary sources, including colourmen printed advertisements, trade directories and colourmen catalogues, which established the availability of art supplies in Shanghai, Paris, and Singapore throughout his career. Ultimately, these diverse archival sources enriched our understanding of Liu Kang’s painting practice. They connected the historical context of his artistic activities with the technical data, allowing the research to piece together narratives that might otherwise have remained obscured. Full article

Various heritage objects can be subjected to various types of biodegradation and biodeterioration. Mold fungi can destroy many types of art—be it monumental art or easel paintings. Tempera paintings on wood are at risk of biodeterioration, since the wide variety of organic and inorganic materials in art objects often provide an optimal habitat for biological colonization, causing aesthetic and structural damage. In this regard, timely identification and characterization of their microbiological destructive potential are critical. The fungi Syncephalastrum sp. STG-160 and Cladosporium sphaerospermum STG-161, isolated from bio-lesion sites of the 16th century icon “Descent into Hell” from State Tretyakov Gallery, Moscow, were identified and characterized morphologically and molecularly in our work. Syncephalastrum sp. was found in an unusual habitat that has not been previously described for this species. To determine the biodegradability of the identified fungi, their cells were inoculated onto mock layers—egg yolk ochre, cobalt green tempera pigments, and watercolor black. The results show that some pigments were more degradable than others. The addition of cobalt green completely inhibited STG-161 growth and significantly deceleratedSTG-160 mycelium development, most likely due to the presence of heavy metal ions in the pigment. Ochre, a frequently used pigment in restoration practice, is the most degradable material for Syncephalastrum sp. STG-160. Combining culture-dependent methods with SEM and fluorescence microscopy allowed us to identify an invisible individual spore of Syncephalastrum sp. STG-160 and a single hypha of Cladosporium sphaerospermum STG-161 directly on the icon’s surface in clean-contaminated zones, potentially allowing their development in cases of adverse temperature and humidity conditions. Therefore, in order to ensure rapid and effective conservation, it is crucial to assess and quantify the presence of biological systems causing damage to the heritage object itself as well as its individual art components. Full article

This study uniquely integrates physiological and subjective data to predict comfort. To optimize lighting conditions in art galleries, this study investigates the interactive effects of painting tones (cool, medium, warm) and illuminance levels (50, 150, 300 lx) on visual comfort. Using decorative paintings as experimental stimuli, 30 participants were exposed to nine distinct lighting scenarios. Subjective questionnaires and eye-tracking data were collected to establish five predictive models. An additional cohort of 10 participants served as an external validation set. Results indicate that the interaction between tone and illuminance exerts a significant influence on comfort. The optimal combinations identified were cool tone + 50 lx, warm tone + 150 lx, and medium tone + 300 lx. Among the models, XGBoost demonstrated superior predictive performance (R² = 0.928 in the test set; R² = 0.884 in external validation). SHAP analysis revealed that the coefficient of variation in pupil diameter was the most critical predictor, followed by fixation count and related features. Both global and individual feature contributions to comfort were elucidated, offering a robust scientific foundation for the precise regulation of lighting environments in art galleries. Full article

Sketch re-identification (Re-ID) aims to retrieve pedestrian photographs in the gallery dataset by a query sketch image drawn by professionals, which is crucial for criminal investigations and missing person searches in the field of public security. The main challenge of this task lies in bridging the significant modality gap between sketches and photos while extracting discriminative modality-invariant features. However, information asymmetry between sketches and RGB photographs, particularly the differences in color information, severely interferes with cross-modal matching processes. To address this challenge, we propose a novel network architecture that integrates multi-channel augmentation with hierarchically consistent disentanglement learning. Specifically, a multi-channel augmentation module is developed to mitigate the interference of color bias in cross-modal matching. Furthermore, a modality-disentangled prototype(MDP) module is introduced to decompose pedestrian representations at the feature level into modality-invariant structural prototypes and modality-specific appearance prototypes. Additionally, a cross-layer decoupling consistency constraint is designed to ensure the semantic coherence of disentangled prototypes across different network layers and to improve the stability of the whole decoupling process. Extensive experimental results on two public datasets demonstrate the superiority of our proposed approach over state-of-the-art methods. Full article

The first monographic exhibition dedicated to Vittore Carpaccio (ca. 1460–1525) in the US, and the first outside of Italy, was hosted at the National Gallery of Art in Washington, DC, from 20 Nov 2022 to 23 February 2023 (from where it went to Venice). Building on the research of art historians and experts on Venice and the larger Mediterranean region in the early modern period, this paper examines Carpaccio’s depiction of various “Turks” in some of the large narrative painting cycles (teleri) commissioned by the devotional confraternities (scuole) in Renaissance Venice. While Carpaccio’s and the larger Venetian familiarity with Islam, including Turks, has been studied, this paper compares various female figures in the St. Stephen cycle with those in his St. George cycle, situating them in the larger historical context of the commissioning scuole (Scuola di Santo Stefano and Scuola di San Giorgio degli Schiavoni, respectively). While attempting to uncover the significance, if not the identities, of a few individuals who stand out from the crowd, this paper urges caution when attempting to discern social history from a painting, much as we take literary texts (particularly those written well before our own times) with a grain of salt. Full article

This article analyzes responses of museums and art institutions in Israel to the events of October 7th. It stresses the public role of museums in times of crisis, and the ways that diverse curatorial choices reflect upon their institutions’ pursuits. It focuses on the case study of curatorial empathy, enacted at the Tel Aviv University Art Gallery, noting its aptness at times of crisis and trauma. The article claims that in a society that experiences both internal and external conflicts, the approach of empathy offers flexibility and openness that allow the museum to respond to public need on the one hand, and poses challenging questions on the other. Such questions are explored through the method of artistic-scientific dialogue. As contentions multiply, overlap, and contrast, the expansion of circles of identification becomes a key strategy in addressing this crisis. This essay argues that empathy is a more thoughtful and productive curatorial approach, because it emphasizes connection rather than only identity. From this perspective, the crisis that started on October 7th is not only that of war, loss, and grief, but also that of a threat to humanness under extreme angst. Full article

This study designed and empirically evaluated a method to enhance information accessibility for museum and art gallery visitors using a small Large Language Model (sLLM) based on the Retrieval-Augmented Generation (RAG) framework. Over 199,000 exhibition descriptions were collected and refined, and a question-answering dataset consisting of 102,000 pairs reflecting user personas was constructed to develop DocentGemma, a domain-optimized language model. This model was fine-tuned through Low-Rank Adaptation (LoRA) based on Google’s Gemma2-9B and integrated with FAISS and OpenSearch-based document retrieval systems within the LangChain framework. Performance evaluation was conducted using a dedicated Q&A benchmark for the docent domain, comparing the model against five commercial and open-source LLMs (including GPT-3.5 Turbo, LLaMA3.3-70B, and Gemma2-9B). DocentGemma achieved an accuracy of 85.55% and a perplexity of 3.78, demonstrating competitive performance in language generation and response accuracy within the domain-specific context. To enhance retrieval relevance, a Spatio-Contextual Retriever (SC-Retriever) was introduced, which combines semantic similarity and spatial proximity based on the user’s query and location. An ablation study confirmed that integrating both modalities improved retrieval quality, with the SC-Retriever achieving a recall@1 of 53.45% and a Mean Reciprocal Rank (MRR) of 68.12, representing a 17.5 20% gain in search accuracy compared to baseline models such as GTE and SpatialNN. System performance was further validated through field deployment at three major exhibition venues in Seoul (the Seoul History Museum, the Hwan-ki Museum, and the Hanseong Baekje Museum). A user test involving 110 participants indicated high response credibility and an average satisfaction score of 4.24. To ensure accessibility, the system supports various output formats, including multilingual speech and subtitles. This work illustrates a practical application of integrating LLM-based conversational capabilities into traditional docent services and suggests potential for further development toward location-aware interactive systems and AI-driven cultural content services. Full article

From the 17th century, European leisure travellers sought novel experiences, places and landscapes; they explored them within the context of contemporary, but temporally changing, social norms. Amongst travellers’ earliest motivations were reportage, curiosity and recuperation in managed landscapes. From the late 18th century, images in art galleries and then guidebooks directed leisure travellers into ‘wild’ places. Supporting and part-driving these developments were travel and antiquarian publications. That normalisation of ‘wild places’ exploration coincided with natural history’s popularisation. From the early 19th century, geosites were recognised, scientifically described, and popularised through a range of publications; this marked the beginning of geotourism. This can be contextualised within the rise in resort-based coastal tourism. These various themes are explored in relation to ‘Coastal Southern England’, an important tourism region from the early-18th century. By the Great War’s (1914–1918) close, its tourism patterns and nature, recognisable in present-day offerings, were established. Its development as a geotourism region can be conceptualised through the ‘travellers’ gaze’ and ‘adapted comfort zone’ models. Early geotourism literature and artistic representations, along with their creators’ biographies, could underpin modern geo-interpretation, of which some exemplars are given. General conclusions are drawn and future research suggested. Full article

The acoustics of St Paul’s Cathedral, London, have been discussed in previous studies as a space of historical, cultural, societal, and architectural interest in the capital city of the United Kingdom. This paper presents the results from recent acoustic measurements carried out within the space, making use of state-of-the-art measurement techniques and equipment. The results from these measurements provide a new perspective on the acoustic properties of different and distinct spaces within the cathedral, including coupling effects between the main areas, and the whispering gallery effect that can be heard around the walkway at the base of the dome. The discussion includes the analysis of room acoustic parameters included in the international standards and speech intelligibility parameters, and an indirect comparison between the techniques used here and those used in previous studies of this space. Full article

Vehicle re-identification (Re-ID) is a critical computer vision task that aims to match the same vehicle across spatially distributed cameras, especially in the context of remote sensing imagery. While prior research has primarily focused on Re-ID using remote sensing images captured from similar, typically elevated viewpoints, these settings do not fully reflect complex aerial-ground collaborative remote sensing scenarios. In this work, we introduce a novel and challenging task: aerial-ground cross-view vehicle Re-ID, which involves retrieving vehicles in ground-view image galleries using query images captured from aerial (top-down) perspectives. This task is increasingly relevant due to the integration of drone-based surveillance and ground-level monitoring in multi-source remote sensing systems, yet it poses substantial challenges due to significant appearance variations between aerial and ground views. To support this task, we present AGID (Aerial-Ground Vehicle Re-Identification), the first benchmark dataset specifically designed for aerial-ground cross-view vehicle Re-ID. AGID comprises 20,785 remote sensing images of 834 vehicle identities, collected using drones and fixed ground cameras. We further propose a novel method, Enhanced Self-Correlation Feature Computation (ESFC), which enhances spatial relationships between semantically similar regions and incorporates shape information to improve feature discrimination. Extensive experiments on the AGID dataset and three widely used vehicle Re-ID benchmarks validate the effectiveness of our method, which achieves a Rank-1 accuracy of 69.0% on AGID, surpassing state-of-the-art approaches by 2.1%. Full article