共找到 20 条结果
In this paper, we address the challenges of automatic metadata annotation in the domain of Galleries, Libraries, Archives, and Museums (GLAMs) by introducing a novel dataset, EUFCC340K, collected from the Europeana portal. Comprising over 340,000 images, the EUFCC340K dataset is organized across multiple facets: Materials, Object Types, Disciplines, and Subjects, following a hierarchical structure based on the Art & Architecture Thesaurus (AAT). We developed several baseline models, incorporating multiple heads on a ConvNeXT backbone for multi-label image tagging on these facets, and fine-tuning a CLIP model with our image text pairs. Our experiments to evaluate model robustness and generalization capabilities in two different test scenarios demonstrate the utility of the dataset in improving multi-label classification tools that have the potential to alleviate cataloging tasks in the cultural heritage sector.
This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manually annotate a collection of scanned photographs. Detecting duplicate and near-duplicate photographs can reduce the time spent on manual annotation by archivists. This real use case differs from laboratory settings as the deployment dataset is available in advance, allowing the use of transductive learning. We propose a transductive learning approach that leverages state-of-the-art deep learning architectures such as convolutional neural networks (CNNs) and Vision Transformers (ViTs). Our approach involves pre-training a deep neural network on a large dataset and then fine-tuning the network on the unlabeled target collection with self-supervised learning. The results show that the proposed approach outperforms the baseline methods in the task of near-duplicate image detection in the UKBench and an in-house private dataset.
We pose and resolve a seeming paradox about spontaneous symmetry breaking in the quantum theory of infinite systems. For a symmetry to be spontaneously broken, it must not be implementable by a unitary operator. But Wigner's theorem guarantees that every symmetry is implemented by a unitary operator that preserves transition probabilities between pure states. We show how it is possible for a unitary operator of this sort to connect the folia of unitarily inequivalent representations. This result undermines interpretations of quantum theory that hold unitary equivalence to be necessary for physical equivalence.
"We are reassigning most affected employees across existing opportunities and programs
Crypto Clipper spreads over USB and communicates over Tor
The vulnerability, disclosed 12 months ago, affects multiple manufacturers
JWST has revealed dramatic differences between the dawn and dusk regions of the scorching exoplanet WASP-121 b。 Fierce winds appear to carry heat from the planet’s permanent dayside, making the evening side hotter and more expanded。 Scientists also found signs that water is being broken apart by extreme temperatures and that mysterious mineral clou
In February, a Trump official refused to review the vaccine
Researchers say these coral strongholds may help repopulate more degraded reefs
It's unclear whether the system is currently intact
Biggest AI firms will likely recoil at Bernie Sanders' AI wealth fund
Elsewhere, beyond-classical quantum hardware, plus classical computing fires back
A new catalyst design could significantly improve the conversion of CO2 into methanol, an important fuel and chemical feedstock。 Researchers separated key reaction steps across different catalyst sites, avoiding a long-standing trade-off between speed and efficiency。 The result was about three times more methanol production than standard commercial
Researchers gave top AI models a classic attention test used in psychology and found a major flaw。 While the models could correctly name colors in short lists, their performance deteriorated sharply as the task became longer and more complex。 Some leading systems fell from over 90% accuracy to nearly complete failure
"I consider this a success already, just from the fact that we're even going to try this
Deep beneath the ground in China, the massive JUNO neutrino observatory has delivered its first major scientific breakthrough, achieving one of the most precise measurements yet of how elusive neutrinos change as they travel。 Using just 59 days of data, researchers sharply improved measurements of key neutrino properties, boosting confidence that J
A new theory suggests the universe is constantly recording its own history in the fabric of spacetime。 If correct, this cosmic memory could help solve some of the biggest puzzles in physics, from black holes to dark matter and the universe’s ultimate fate
A French launch startup is scrapping the name of its rocket, apparently due to a trademark issue
Researchers have finally resolved a key problem in a 100-year-old theory of color, showing that the qualities we perceive in colors are intrinsic to the mathematics of color space itself。 The discovery sharpens our understanding of human vision and could lead to more precise color technologies and visualizations
Astronomers may be closing in on a long-standing cosmic mystery: why some of the universe’s biggest galaxies seem to have far fewer stars than expected。 Using NASA- and JAXA-supported XRISM observations of a galaxy called NGC 4151, researchers found strong evidence that supermassive black holes can unleash powerful winds that blow away the raw mate