Alert button
Picture for Hilde Kuehne

Hilde Kuehne

Alert button

Uncertainty Quantification via Stable Distribution Propagation

Feb 13, 2024
Felix Petersen, Aashwin Mishra, Hilde Kuehne, Christian Borgelt, Oliver Deussen, Mikhail Yurochkin

Viaarxiv icon

Grounding Everything: Emerging Localization Properties in Vision-Language Transformers

Dec 05, 2023
Walid Bousselham, Felix Petersen, Vittorio Ferrari, Hilde Kuehne

Viaarxiv icon

Learning Human Action Recognition Representations Without Real Humans

Nov 10, 2023
Howard Zhong, Samarth Mishra, Donghyun Kim, SouYoung Jin, Rameswar Panda, Hilde Kuehne, Leonid Karlinsky, Venkatesh Saligrama, Aude Oliva, Rogerio Feris

Viaarxiv icon

HowToCaption: Prompting LLMs to Transform Video Annotations at Scale

Oct 07, 2023
Nina Shvetsova, Anna Kukleva, Xudong Hong, Christian Rupprecht, Bernt Schiele, Hilde Kuehne

Figure 1 for HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
Figure 2 for HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
Figure 3 for HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
Figure 4 for HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
Viaarxiv icon

In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval

Sep 16, 2023
Nina Shvetsova, Anna Kukleva, Bernt Schiele, Hilde Kuehne

Figure 1 for In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval
Figure 2 for In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval
Figure 3 for In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval
Figure 4 for In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval
Viaarxiv icon

Preserving Modality Structure Improves Multi-Modal Learning

Aug 24, 2023
Swetha Sirnam, Mamshad Nayeem Rizve, Nina Shvetsova, Hilde Kuehne, Mubarak Shah

Figure 1 for Preserving Modality Structure Improves Multi-Modal Learning
Figure 2 for Preserving Modality Structure Improves Multi-Modal Learning
Figure 3 for Preserving Modality Structure Improves Multi-Modal Learning
Figure 4 for Preserving Modality Structure Improves Multi-Modal Learning
Viaarxiv icon

Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages

May 21, 2023
Andrew Rouditchenko, Sameer Khurana, Samuel Thomas, Rogerio Feris, Leonid Karlinsky, Hilde Kuehne, David Harwath, Brian Kingsbury, James Glass

Figure 1 for Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages
Figure 2 for Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages
Figure 3 for Comparison of Multilingual Self-Supervised and Weakly-Supervised Speech Pre-Training for Adaptation to Unseen Languages
Viaarxiv icon

ISAAC Newton: Input-based Approximate Curvature for Newton's Method

May 01, 2023
Felix Petersen, Tobias Sutter, Christian Borgelt, Dongsung Huh, Hilde Kuehne, Yuekai Sun, Oliver Deussen

Figure 1 for ISAAC Newton: Input-based Approximate Curvature for Newton's Method
Figure 2 for ISAAC Newton: Input-based Approximate Curvature for Newton's Method
Figure 3 for ISAAC Newton: Input-based Approximate Curvature for Newton's Method
Figure 4 for ISAAC Newton: Input-based Approximate Curvature for Newton's Method
Viaarxiv icon

Learning Situation Hyper-Graphs for Video Question Answering

Apr 18, 2023
Aisha Urooj Khan, Hilde Kuehne, Bo Wu, Kim Chheu, Walid Bousselham, Chuang Gan, Niels Lobo, Mubarak Shah

Figure 1 for Learning Situation Hyper-Graphs for Video Question Answering
Figure 2 for Learning Situation Hyper-Graphs for Video Question Answering
Figure 3 for Learning Situation Hyper-Graphs for Video Question Answering
Figure 4 for Learning Situation Hyper-Graphs for Video Question Answering
Viaarxiv icon

WEAR: A Multimodal Dataset for Wearable and Egocentric Video Activity Recognition

Apr 11, 2023
Marius Bock, Michael Moeller, Kristof Van Laerhoven, Hilde Kuehne

Figure 1 for WEAR: A Multimodal Dataset for Wearable and Egocentric Video Activity Recognition
Figure 2 for WEAR: A Multimodal Dataset for Wearable and Egocentric Video Activity Recognition
Figure 3 for WEAR: A Multimodal Dataset for Wearable and Egocentric Video Activity Recognition
Figure 4 for WEAR: A Multimodal Dataset for Wearable and Egocentric Video Activity Recognition
Viaarxiv icon