Multi-modal Dense Video Captioning(2020) Review

Introduction

---

Related Work

---

Model Framework

---

Experiments

---

Conclusion

---

References

---

Long-term dependency
https://pozalabs.github.io/transformer/
Evaluation code for dense-captioning events in videos
https://github.com/ranjaykrishna/densevid_eval
BLEU score
https://wikidocs.net/31695
METEOR score
https://en.wikipedia.org/wiki/METEOR
Inflated 3D Convolution Network
https://chacha95.github.io/2019-07-04-VideoUnderstanding3/
Label Smoothing
https://ratsgo.github.io/insight-notes/docs/interpretable/smoothing
Teacher Forcing
https://blog.naver.com/sooftware/221790750668
Transformer
https://huggingface.co/blog/encoder-decoder