ActivityNet
Emerging6papers using it
2021first seen
ActivityNet is a benchmark dataset that contains a diverse set of video clips annotated with temporal and action labels, used to evaluate video-language tasks.
Papers using ActivityNet (6)
- Bima: Towards Biases Mitigation For Text-video Retrieval Via Scene Element GuidanceDelving Deeper: Hierarchical Visual Perception for Robust Video-Text RetrievalCLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language
Representation AlignmentCross-Modal Adapter for Vision-Language RetrievalBidirectional Cross-Modal Knowledge Exploration for Video Recognition
with Pre-trained Vision-Language ModelsTACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment