ActivityNet Captions
Emerging6papers using it
111HF downloads
3HF likes
2017first seen
The ActivityNet Captions dataset connects videos to a series of temporally annotated sentence descriptions. Each sentence covers an unique segment of the video, describing multiple events that occur. These events may occur over very long or short periods of time and are not limited in any capacity, allowing them to co-
🤗 Hugging Face⚖ other
Papers using ActivityNet Captions (6)
- Live Video CaptioningAttend And Interact: Higher-order Object Interactions For Video UnderstandingGrounded Objects And Interactions For Video CaptioningSAVCHOI: Detecting Suspicious Activities Using Dense Video Captioning With Human Object InteractionsWeakly Supervised Dense Video Captioning via Jointly Usage of Knowledge
Distillation and Cross-modal MatchingConTra: (Con)text (Tra)nsformer for Cross-Modal Video Retrieval