Thomas Hummel

hummelth's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 5 papers 10 months ago

EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

Paper • 2407.16658 • Published Jul 23, 2024

Video-adverb retrieval with compositional adverb-action embeddings

Paper • 2309.15086 • Published Sep 26, 2023

Semantic Image Synthesis with Semantically Coupled VQ-Model

Paper • 2209.02536 • Published Sep 6, 2022

Temporal and cross-modal attention for audio-visual zero-shot learning

Paper • 2207.09966 • Published Jul 20, 2022

Text-to-feature diffusion for audio-visual few-shot learning

Paper • 2309.03869 • Published Sep 7, 2023