Výsledky vyhledávání

Report

GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions

Autor: Wu, Chenfei, Huang, Lun, Zhang, Qianxi, Li, Binyang, Ji, Lei, Yang, Fan, Sapiro, Guillermo, Duan, Nan

Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation. Existing works typically experiment on simple or small datasets, where the generalization ability

Externí odkaz: http://arxiv.org/abs/2104.14806

Zobrazit plný text záznamu

Report

NPE: An FPGA-based Overlay Processor for Natural Language Processing

Autor: Khan, Hamza, Khan, Asma, Khan, Zainab, Huang, Lun Bin, Wang, Kun, He, Lei

In recent years, transformer-based models have shown state-of-the-art results for Natural Language Processing (NLP). In particular, the introduction of the BERT language model brought with it breakthroughs in tasks such as question answering and natu

Externí odkaz: http://arxiv.org/abs/2104.06535

Zobrazit plný text záznamu

Report

Adaptively Aligned Image Captioning via Adaptive Attention Time

Autor: Huang, Lun, Wang, Wenmin, Xia, Yaxian, Chen, Jie

Recent neural models for image captioning usually employ an encoder-decoder framework with an attention mechanism. However, the attention mechanism in such a framework aligns one single (attended) image feature vector to one caption word, assuming on

Externí odkaz: http://arxiv.org/abs/1909.09060

Zobrazit plný text záznamu

Report

Attention on Attention for Image Captioning

Autor: Huang, Lun, Wang, Wenmin, Chen, Jie, Wei, Xiao-Yong

Attention mechanisms are widely used in current encoder/decoder frameworks of image captioning, where a weighted average on encoded vectors is generated at each time step to guide the caption decoding process. However, the decoder has little idea of

Externí odkaz: http://arxiv.org/abs/1908.06954

Zobrazit plný text záznamu

Report

ParNet: Position-aware Aggregated Relation Network for Image-Text matching

Autor: Xia, Yaxian, Huang, Lun, Wang, Wenmin, Wei, Xiaoyong

Exploring fine-grained relationship between entities(e.g. objects in image or words in sentence) has great contribution to understand multimedia content precisely. Previous attention mechanism employed in image-text matching either takes multiple sel

Externí odkaz: http://arxiv.org/abs/1906.06892

Zobrazit plný text záznamu