task · first seen 12 Oct 2026
open-vocabulary video recognition
Recognizing video action categories beyond a fixed training label set using vision-language model text embeddings.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Revisiting Natural Language Prompts from Large Language Models for Open-Vocabulary Video RecognitionPapers · 12 Oct 2026 · Haichen He, Weibin Liu, Weiwei Xing
Latest sources
- Revisiting Natural Language Prompts from Large Language Models for Open-Vocabulary Video RecognitionPapers · 12 Oct 2026 · Haichen He, Weibin Liu, Weiwei Xing