AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models
Vision-Language Models struggle with domain adaptation in specialized spatio-temporal video grounding tasks, highlighting limitations in zero-shot generalization and in-context lea…
Hugging Face · Daily Papers
·Rintaro Otsubo, Ryo Fujii
·
·▲ 8 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Rintaro Otsubo, Ryo Fujii, Reina Ishikawa, Taiki Kanaya, Kanta Sawafuji, Hiroki Kajita
- 8 upvotes da comunidade
- Temas: Vision-Language Models, Spatio-Temporal Video Grounding, domain adaptation, In-Context Learning, zero-shot generalization
Resumo
Resumo original (em inglês), extraído do paper:
Vision-Language Models struggle with domain adaptation in specialized spatio-temporal video grounding tasks, highlighting limitations in zero-shot generalization and in-context learning capabilities.