Picture for Felix Vogel

Felix Vogel

VideoGEM: Training-free Action Grounding in Videos

Add code
Mar 26, 2025
Viaarxiv icon

VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models

Add code
Sep 12, 2022
Figure 1 for VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models
Figure 2 for VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models
Figure 3 for VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models
Figure 4 for VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models
Viaarxiv icon