PM
Pascal Mettes
cs.CVcs.LGcs.AIDental Carieseess.IVArtificial intelligencecs.MMDental caries detectionneuroscienceRadiography, Dental
On Valency
published · living versionsW_r8wrpywh·v1 · currentpublished
Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models
with Puru Vaish, Meelad Dashti, Christoph Brune, Tatiana Tommasi +1
1 version
Preprints & journals
68 papers in the corpus · 2015–2026Compositionality with Primitives: A Unified View from Euclidean to Hyperbolic Vision-Language Models2610.29811v1 · Puru Vaish, Meelad Dashti, Christoph Brune et al.2026 · 0 citationsarXivon Valency
A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery2609.27139v1 · Ana Manzano Rodr'iguez, Pascal Mettes, Marlies P. Schijven et al.2026 · 0 citationsarXiv
Hierarchical Prompt Learning for Hyperbolic Vision-Language Models2609.24276v1 · Andro Erdelez, Pascal Mettes, Behzad Bozorgtabar2026 · 0 citationsarXiv
Human-AI Collaboration in Proximal Early Caries Lesion Detection: Potential Benefits for Novices and Potential Risks for Experts.42721109 · Gonzalez-Valenzuela, Ricardo E, Vu, Quoc T D, Mettes, Pascal et al.2026 · 0 citationsCaries research. 2026:1
Fourier Self-Supervision for Fine-Grained Generalized Category Discovery2608.08963v1 · Sarah Rastegar, Mina Ghadimi Atigh, Pascal Mettes et al.2026 · 0 citationsarXiv
Hyperbolic Concept Bottleneck Models2605.06440v2 · Daniel Uyterlinde, Swasti Shreya Mishra, Pascal Mettes2026 · 0 citationsarXiv
Fast and Geometrically Grounded Lorentz Neural Networks2601.21529v1 · Robert van der Klis, Ricardo Ch'avez Torres, Max van Spengler et al.2026 · 0 citationsarXiv
Accuracy of deep learning-based AI models for early caries lesion detection: the influence of annotation quality and reference choice.41339765 · Gonzalez-Valenzuela, Ricardo E, Mettes, Pascal, Loos, Bruno G et al.2025 · 4 citationsClinical oral investigations. 2025;29(12):598
Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring2511.20679v1 · Melika Ayoughi, Pascal Mettes, Paul Groth2025 · 0 citationsK-CAP2025 Conference
The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding10.1101/2025.10.27.684803v2 · Sartzetaki, C., Zonneveld, A. W., Oyarzo, P. et al.2025 · 2 citationsbioRxiv
Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding2508.20765v2 · Gowreesh Mago, Pascal Mettes, Stevan Rudinac2025 · 2 citationsInternational Journal of Computer Vision 134, 217 (2026)
Continual Hyperbolic Learning of Instances and Classes2506.10710v1 · Melika Ayoughi, Mina Ghadimi Atigh, Mohammad Mahdi Derakhshani et al.2025 · 0 citationsarXiv
Balanced Hyperbolic Embeddings Are Natural Out-of-Distribution Detectors2506.10146v1 · Tejaswi Kasarla, Max van Spengler, Pascal Mettes2025 · 1 citationarXiv
How PARTs assemble into wholes: Learning the relative composition of images2506.03682v2 · Melika Ayoughi, Samira Abnar, Chen Huang et al.2025 · 0 citationsarXiv
Microtomography to traditional dental radiograph: projecting 3-dimensional initial proximal caries lesion annotations for enhanced radiographic delineation.39901325 · Gonzalez-Valenzuela, Ricardo E, Vu, Quoc T D, Mettes, Pascal et al.2025 · 2 citationsDento maxillo facial radiology. 2025;54(4):320-328
Hyperbolic Safety-Aware Vision-Language Models2503.12127v1 · Tobia Poppi, Tejaswi Kasarla, Pascal Mettes et al.2025 · 6 citationsarXiv
Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space2502.17130v1 · Max van Spengler, Pascal Mettes2025 · 1 citationarXiv
Adversarial Attacks on Hyperbolic Networks2412.01495v1 · Max van Spengler, Jan Zah'alka, Pascal Mettes2024 · 3 citationsarXiv
Maximally Separated Active Learning2411.17444v1 · Tejaswi Kasarla, Abhishek Jha, Faye Tervoort et al.2024 · 0 citationsarXiv
BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation10.1101/2024.10.29.620889v2 · Garcia Cerdas, D., Sartzetaki, C., Petersen, M. et al.2024 · 3 citationsbioRxiv
Enhancement of early proximal caries annotations in radiographs: introducing the Diagnostic Insights for Radiographic Early-caries with micro-CT (ACTA-DIRECT) dataset.39478492 · Valenzuela, Ricardo E Gonzalez, Mettes, Pascal, Loos, Bruno G et al.2024 · 6 citationsBMC oral health. 2024;24(1):1325
Compositional Entailment Learning for Hyperbolic Vision-Language Models2410.06912v2 · Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno et al.2024 · 0 citationsarXiv
Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability2407.13392v1 · Judith Dijk, Gertjan Burghouts, Kapil D. Katyal et al.2024 · 0 citationsICRA Off-road Autonomy workshop 2024
Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd Navigation2407.13567v3 · Guido Maria D'Amely di Melendugno, Alessandro Flaborea, Pascal Mettes et al.2024 · 1 citationarXiv
Find the Cliffhanger: Multi-Modal Trailerness in Soap Operas2401.16076v1 · Carlo Bretti, Pascal Mettes, Hendrik Vincent Koops et al.2024 · 2 citationsarXiv
Latent Space Editing in Transformer-Based Flow Matching2312.10825v1 · Vincent Tao Hu, David W Zhang, Pascal Mettes et al.2023 · 14 citationsarXiv
Motion Flow Matching for Human Motion Synthesis and Editing2312.08895v1 · Vincent Tao Hu, Wenzhe Yin, Pingchuan Ma et al.2023 · 6 citationsarXiv
Union-over-Intersections: Object Detection beyond Winner-Takes-All2311.18512v2 · Aritra Bhowmik, Pascal Mettes, Martin R. Oswald et al.2023 · 0 citationsarXiv
Query by Activity Video in the Wild2311.13895v1 · Tao Hu, William Thong, Pascal Mettes et al.2023 · 0 citationsarXiv
Hyperbolic Random Forests2308.13279v2 · Lars Doorenbos, Pablo M'arquez-Neila, Raphael Sznitman et al.2023 · 3 citationsarXiv
Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation2306.10122v1 · Shuo Chen, Yingjun Du, Pascal Mettes et al.2023 · 7 citationsarXiv
HypLL: The Hyperbolic Learning Library2306.06154v3 · Max van Spengler, Philipp Wirth, Pascal Mettes2023 · 1 citationarXiv
Focus for Free in Density-Based Counting2306.05129v1 · Zenglin Shi, Pascal Mettes, Cees G.M. Snoek2023 · 16 citationsarXiv
Infinite Class Mixup2305.10293v2 · Thomas Mensink, Pascal Mettes2023 · 0 citationsarXiv
Hyperbolic Deep Learning in Computer Vision: A Survey2305.06611v1 · Pascal Mettes, Mina Ghadimi Atigh, Martin Keller-Ressel et al.2023 · 63 citationsarXiv
Poincaré ResNet2303.14027v3 · Max van Spengler, Erwin Berkhout, Pascal Mettes2023 · 24 citationsarXiv
Multi-Task Edge Prediction in Temporally-Dynamic Video Graphs2212.02875v1 · Osman Ulger, Julian Wiederer, Mohsen Ghafoorian et al.2022 · 0 citationsarXiv
Self-Contained Entity Discovery from Captioned Videos2208.06662v1 · Melika Ayoughi, Pascal Mettes, Paul Groth2022 · 1 citationarXiv
Maximum Class Separation as Inductive Bias in One Matrix2206.08704v2 · Tejaswi Kasarla, Gertjan J. Burghouts, Max van Spengler et al.2022 · 13 citationsarXiv
Less than Few: Self-Shot Video Instance Segmentation2204.08874v1 · Pengwan Yang, Yuki M. Asano, Pascal Mettes et al.2022 · 2 citationsarXiv
Hyperbolic Image Segmentation2203.05898v1 · Mina GhadimiAtigh, Julian Schoep, Erman Acar et al.2022 · 86 citationsarXiv
Universal Prototype Transport for Zero-Shot Action Recognition and Localization2203.03971v2 · Pascal Mettes2022 · 4 citationsInternational Journal of Computer Vision (2023)
Zero-Shot Action Recognition from Diverse Object-Scene Compositions2110.13479v1 · Carlo Bretti, Pascal Mettes2021 · 7 citationsarXiv
Diagnosing Errors in Video Relation Detectors2110.13110v1 · Shuo Chen, Pascal Mettes, Cees G.M. Snoek2021 · 3 citationsarXiv
Social Fabric: Tubelet Compositions for Video Relation Detection2108.08363v1 · Shuo Chen, Zenglin Shi, Pascal Mettes et al.2021 · 20 citationsarXiv
Frequency-Supervised MR-to-CT Image Synthesis2107.08962v1 · Zenglin Shi, Pascal Mettes, Guoyan Zheng et al.2021 · 13 citationsarXiv
On Measuring and Controlling the Spectral Bias of the Deep Image Prior2107.01125v3 · Zenglin Shi, Pascal Mettes, Subhransu Maji et al.2021 · 74 citationsarXiv
Hyperbolic Busemann Learning with Ideal Prototypes2106.14472v2 · Mina Ghadimi Atigh, Martin Keller-Ressel, Pascal Mettes2021 · 13 citationsarXiv
Object Priors for Classifying and Localizing Unseen Actions2104.04715v1 · Pascal Mettes, William Thong, Cees G. M. Snoek2021 · 18 citationsarXiv
Few-Shot Transformation of Common Actions into Time and Space2104.02439v1 · Pengwan Yang, Pascal Mettes, Cees G. M. Snoek2021 · 6 citationsarXiv
Career total: 114 works. 68 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.