paper-conference

Multimodal learning analytics: Society 5.0 project in Japan
Cite
Buda.art: A multimodal content-based analysis and retrieval system for Buddha statues
© 2019 Copyright held by the owner/author(s). We introduce BUDA.ART, a system designed to assist researchers in Art History, to explore …
Cite DOI
Context-aware embeddings for automatic art analysis
© 2019 Association for Computing Machinery. Automatic art analysis aims to classify and retrieve artistic representations from a …
Cite DOI
Contextualized context2vec
Lexical substitution ranks substitution candidates from the viewpoint of paraphrasability for a target word in a given sentence. There …
Cite DOI URL
Controllable text simplification with lexical constraint loss
We propose a method to control the level of a sentence in a text simplification task. Text simplification is a monolingual translation …
Cite DOI URL
Facial expression recognition with skip-connection to leverage low-level features
Deep convolutional neural networks (CNNs) have established their feet in the ground of computer vision and machine learning, used in …
Cite DOI URL
Historical and modern features for Buddha statue classification
© 2019 Copyright held by the owner/author(s). While Buddhism has spread along the Silk Roads, many pieces of art have been displaced. …
Cite DOI
Negative lexically constrained decoding for paraphrase generation
Paraphrase generation can be regarded as monolingual translation. Unlike bilingual machine translation, paraphrase generation rewrites …
Cite DOI URL
Rethinking the evaluation of video summaries
Video summarization is a technique to create a short skim of the original video while preserving the main stories/content. There exists …
Cite DOI arXiv
Video meets knowledge in visual question answering
In this work, we address knowledge-based visual question answering in videos. First, we introduce KnowIT VQA, a video dataset with …
Cite