paper-conference

RUSE: Regressor using sentence embeddings for automatic machine translation evaluation
We introduce the RUSE metric for the WMT18 metrics shared task. Sentence embeddings can capture global information that cannot be …
引用 DOI URL
Visually grounded paraphrase extraction
引用
Novel view synthesis with light-weight view-dependent texture mapping for a stereoscopic HMD
The proliferation of off-the-shelf head-mounted displays (HMDs) let end-users enjoy virtual reality applications, some of which render …
引用 DOI
Hyperspectral imaging using flickerless active LED illumination
© 2017 SPIE. Hyperspectral imaging is used in various fields because it can obtain much more information than imaging by conventional …
引用 DOI
Fine-grained video retrieval for multi-clip video
引用
Incremental structural modeling on sparse visual SLAM
© 2017 MVA Organization All Rights Reserved. This paper presents an incremental structural modeling approach that improves the …
引用 DOI
Mixed features for face detection in thermal image
© 2017 SPIE. An infrared (IR) camera captures the temperature distribution of an object as an IR image. Because facial temperature is …
引用 DOI
Realtime novel view synthesis with eigen-texture regression
Realtime novel view synthesis, which generates a novel view of a real object or scene in realtime, enjoys a wide range of applications …
PDF 引用
ReMagicMirror: Action learning using human reenactment with the mirror metaphor
We propose ReMagicMirror, a system to help people learn actions (e.g., martial arts, dances). We first capture the motions of a teacher …
引用 DOI
Unsupervised Video Summarization using Deep Video Features
引用