ContCap: A comprehensive framework for continual image captioning

By GIANG NGUYEN, Tae Joon Jun, Trung Quang Tran, Daeyoung Kim. 2019

7 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Chris Dongjoo Kim
2. Xiang Ren
3. Xisen Jin
4. Jinseo Jeong
5. Gunhee Kim
6. Arka Sadhu
7. Junyi Du
8. Ramkant Nevatia

Citations in the corpus

• Imbalanced Continual Learning with Partitioning Reservoir Sampling (2020, background): “[64] tailor MSCOCO for continual learning of captioning.”
• Explaining How Deep Neural Networks Forget by Deep Visualization (2020, unknown): “While two naive approaches of freezing in [11] are also implemented, we devise critical freezing based on findings, which only freezes critical layers.”
• Visually Grounded Continual Learning of Compositional Phrases (2020, background): “Nguyen et al. (2019) investigate continual learning of image captioning, but make strong assumptions on the structure of the data stream, and do not evaluate compositionality.”
• Visually Grounded Continual Learning of Compositional Semantics (2020, background): “Nguyen et al. (2019) study continual learning of image captioning, but they do not analyze challenges of sequential predictions, and still make strong assumptions about the structure of the data stream.”