Hilde Kuehne

Full Professor@Eberhard-Karls-Universität Tübingen·德国·OpenReview

研究方向

multimodal learning · unsupervised action classification · weakly suppervised action classification · action classification · temporal action segmentation

Hilde Kuehne

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models

REVEAL: Advancing Relation-based Video Understanding for Video-Question-Answering

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation

VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes

TTRV: Test-Time Reinforcement Learning for Vision Language Models

TeMo: Temperature Modulation for Multimodal Contrastive Learning

AVRT: Audio-Visual Reasoning Transfer through Single-Modality Teachers

Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity