Imagen de Portada

From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Prasse, Katharina, Jung, Steffen, Bravo, Isaac, Walter, Stefanie, Knab, Patrick, Bartelt, Christian, Keuper, Margret
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DCBM: Data-Efficient Visual Concept Bottleneck Models
por: Prasse, Katharina, et al.
Publicado: (2024)

ClimateVID -- Social Media Videos Analysis and Challenges Involved
por: Xu, Shiqi, et al.
Publicado: (2026)

I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames
por: Prasse, Katharina, et al.
Publicado: (2024)

Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition
por: Prasse, Katharina, et al.
Publicado: (2023)

Deep Learning for Climate Action: Computer Vision Analysis of Visual Narratives on X
por: Prasse, Katharina, et al.
Publicado: (2025)

Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
por: Knab, Patrick, et al.
Publicado: (2024)

Fix your downsampling ASAP! Be natively more robust via Aliasing and Spectral Artifact free Pooling
por: Grabinski, Julia, et al.
Publicado: (2023)

TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
por: Medi, Tejaswini, et al.
Publicado: (2025)

Corner Cases: How Size and Position of Objects Challenge ImageNet-Trained Models
por: Fatima, Mishal, et al.
Publicado: (2025)

CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks
por: Agnihotri, Shashank, et al.
Publicado: (2023)

FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training
por: Medi, Tejaswini, et al.
Publicado: (2024)

Which LIME should I trust? Concepts, Challenges, and Solutions
por: Knab, Patrick, et al.
Publicado: (2025)

Interpreting Outliers in Time Series Data through Decoding Autoencoder
por: Knab, Patrick, et al.
Publicado: (2024)

Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging
por: Poggi, Nicolas, et al.
Publicado: (2025)

Deepfakes: we need to re-think the concept of "real" images
por: Keuper, Janis, et al.
Publicado: (2025)

Concepts in Motion: Temporal Concept Bottleneck Model for Interpretable Video Classification
por: Knab, Patrick, et al.
Publicado: (2025)

CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks
por: Leiter, Christoph, et al.
Publicado: (2025)

As large as it gets: Learning infinitely large Filters via Neural Implicit Functions in the Fourier Domain
por: Grabinski, Julia, et al.
Publicado: (2023)

Unfolding Local Growth Rate Estimates for (Almost) Perfect Adversarial Detection
por: Lorenz, Peter, et al.
Publicado: (2022)

Can We Talk Models Into Seeing the World Differently?
por: Gavrikov, Paul, et al.
Publicado: (2024)

Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
por: Müller, Patrick, et al.
Publicado: (2025)

Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
por: Walter, Jan Philip, et al.
Publicado: (2026)

CliME: Evaluating Multimodal Climate Discourse on Social Media and the Climate Alignment Quotient (CAQ)
por: Borah, Abhilekh, et al.
Publicado: (2025)

Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition
por: Xu, Jiawen, et al.
Publicado: (2024)

Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
por: Agnihotri, Shashank, et al.
Publicado: (2024)

How Do Training Methods Influence the Utilization of Vision Models?
por: Gavrikov, Paul, et al.
Publicado: (2024)

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?
por: Lorenz, Peter, et al.
Publicado: (2021)

Spatiotemporal Change-Points in Development Discourse: Insights from Social Media in Low-Resource Contexts
por: Jung, Woojin, et al.
Publicado: (2026)

Sprache und Fremdsprache
por: Prasse, Jutta
Publicado: (2020)

Detecting AutoAttack Perturbations in the Frequency Domain
por: Lorenz, Peter, et al.
Publicado: (2021)

MultiMax: Sparse and Multi-Modal Attention Learning
por: Zhou, Yuxuan, et al.
Publicado: (2024)

Towards Class-wise Robustness Analysis
por: Medi, Tejaswini, et al.
Publicado: (2024)

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks
por: Kleinmann, Marcel, et al.
Publicado: (2025)

Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation
por: Zhou, Yuxuan, et al.
Publicado: (2024)

Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context
por: Agnihotri, Shashank, et al.
Publicado: (2023)

Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentation
por: Xu, Jiawen, et al.
Publicado: (2025)

BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding
por: Knab, Patrick, et al.
Publicado: (2026)

Spaces of revolution: ethnic oppression and liberation in Myanmar
por: Elliott Prasse‐Freeman
Publicado: (2024)

Self-Elicitation of Requirements with Automated GUI Prototyping
por: Kolthoff, Kristian, et al.
Publicado: (2024)

Can Visual Language Models Replace OCR-Based Visual Question Answering Pipelines in Production? A Case Study in Retail
por: Lamm, Bianca, et al.
Publicado: (2024)