AI Paper Atlas

Research map / Time series / Foundation models for time series

Deep Unsupervised Binary Coding Networks for Multivariate Time Series Retrieval

Dixian Zhu, Dongjin Song, Yuncong Chen, Cristian Lumezanu, Wei Cheng, Bo Zong, Jingchao Ni, Takehiko Mizoguchi, Tianbao Yang, Haifeng Chen

AAAI 2020 · Time series › Foundation models for time series · approach: Time series classification · 20 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add clustering loss (ablation)LSTM-ED · EEG Eye State 256 bitsMAP: 0.3870 -> 0.3979Improved
add clustering loss (ablation)LSTM-ED · IoT 128 bitsMAP: 0.4972 -> 0.4950No clear effect
add temporal encoding (ablation)DUBCNs(Clustering) · EEG Eye State 256 bitsMAP: 0.3979 -> 0.4103Improved
add temporal encoding (ablation)DUBCNs(Clustering) · EEG Eye State 128 bitsMAP: 0.3648 -> 0.3640No clear effect
add adversarial loss (ablation)DUBCNs(TE+Clustering) · IoT 64 bitsMAP: 0.4117 -> 0.4406Improved
add adversarial loss (ablation)DUBCNs(TE+Clustering) · EEG Eye State 256 bitsMAP: 0.4103 -> 0.4279Improved
add adversarial loss (ablation)DUBCNs(TE+Clustering) · Twitter 64 bitsMAP: 0.1077 -> 0.1080No clear effect
increase number of clusters k from 2 to 8 (ablation)DUBCNs · IoT 256 bitsMAP: 0.5178 -> 0.5646Improved
increase number of clusters k from 2 to 8 (ablation)DUBCNs · Twitter 256 bitsMAP: 0.1502 -> 0.1615Improved
DUBCNs full vs LSTM-EDLSTM-ED · IoT 64 bitsMAP: 0.3844 -> 0.4406Improved
DUBCNs full vs LSHLSH · IoT 256 bitsMAP: 0.5346 -> 0.5646Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy