Semantic-Aware Pretraining for Dense Video Captioning
Not on the map. Why?
Abstract (arXiv)
This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video captioning, which empowers the learned features to recognize high-level semantic concepts. Diverse video features of different modalities are fed into an event captioning module to generate accurate and meaningful sentences. Our final ensemble model achieves a 10.00 METEOR score on the test set.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 10 of its 10 references that are in the map. First posted on arXiv 13 Apr 2022.
Builds on
10 of 10 references.
References · 10
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
- 2018SlowFast Networks for Video Recognitioncited by 1,862
- 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
- 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
- 2016Self-critical Sequence Training for Image Captioningcited by 544
- 2020Asymmetric Loss For Multi-Label Classificationcited by 379
- 2020TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Taskscited by 77
- 2016CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016cited by 53
- 2020Dense-Captioning Events in Videos: SYSU Submission to ActivityNet Challenge 2020cited by 9
Built on by
Citing papers per year: 2023: 2.
2 papers.