no code implementations • IEEE Access 2023 • Kian Yu Gan, Yu Tong Cheng, Hung-Khoon Tan, Hui-Fuang Ng, Maylor Karhang Leung, Joon Huang Chuah
We propose to employ a U-Net like structure to model both types of dependencies in a unified structure where the encoder learns global dependencies hierarchically on top of local ones; then the decoder propagates this global information back to the segment level for classification.
1 code implementation • 11 Feb 2022 • Jia Huei Tan, Ying Hua Tan, Chee Seng Chan, Joon Huang Chuah
Recent research that applies Transformer-based architectures to image captioning has resulted in state-of-the-art image captioning performance, capitalising on the success of Transformers on natural language tasks.
1 code implementation • 7 Oct 2021 • Jia Huei Tan, Chee Seng Chan, Joon Huang Chuah
With the advancement of deep models, research work on image captioning has led to a remarkable gain in raw performance over the last decade, along with increasing model complexity and computational cost.
1 code implementation • 28 Aug 2019 • Jia Huei Tan, Chee Seng Chan, Joon Huang Chuah
Recurrent Neural Network (RNN) has been widely used to tackle a wide variety of language generation problems and are capable of attaining state-of-the-art (SOTA) performance.
2 code implementations • 4 Mar 2019 • Jia Huei Tan, Chee Seng Chan, Joon Huang Chuah
This is because the size of word and output embedding matrices grow proportionally with the size of vocabulary, adversely affecting the compactness of these networks.