References
- Describing Videos by Exploiting Temporal Structure, 10.1109/ICCV.2015.512
- Incorporating Relation Paths in Neural Relation Extraction, 10.18653/v1/D17-1186
- https://blog.dataiku.com/how-deep-does-your-sentence-embedding-model-need-to-be
- https://adeshpande3.github.io/A-Beginner's-Guide-To-Understanding-Convolutional-Neural-Networks/
- Deep Temporal Linear Encoding Networks, 10.1109/CVPR.2017.168
- https://github.com/gojibjib/jibjib-model
- https://github.com/CSAILVision/places365
- Use What You Have: Video Retrieval Using Representations from Collaborative Experts, (http://arxiv.org/abs/1907.13487)
- Neural Models for Information Retrieval (https://arxiv.org/pdf/1705.01509.pdf)
- Learning a Video-Text Joint Embedding using Korean Tagged Movie Clips, ICTC 2020