Search Results for author: Song Yang

Found 7 papers, 3 papers with code

GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series

no code implementations27 Oct 2021 Sikai Zhang, Hong Zheng, Hongyi Su, Bo Yan, Jiamou Liu, Song Yang

The main novelty of the model is the integration of time series of four different time granularities: the original time series, together with hourly, daily, and weekly time series.

Graph Attention Time Series

Tribrid: Stance Classification with Neural Inconsistency Detection

1 code implementation EMNLP 2021 Song Yang, Jacopo Urbani

In the second case, we show that using the confidence scores to remove doubtful predictions allows our method to achieve human-like performance over the retained information, which is still a sizable part of the original input.

Classification Fact Checking +1

Space Meets Time: Local Spacetime Neural Network For Traffic Flow Forecasting

no code implementations11 Sep 2021 Song Yang, Jiamou Liu, Kaiqi Zhao

We argue that such correlations are universal and play a pivotal role in traffic flow.

Traffic Prediction

Multimodal Learning For Classroom Activity Detection

no code implementations22 Oct 2019 Hang Li, Yu Kang, Wenbiao Ding, Song Yang, Songfan Yang, Gale Yan Huang, Zitao Liu

The experimental results demonstrate the benefits of our approach on learning attention based neural network from classroom data with different modalities, and show our approach is able to outperform state-of-the-art baselines in terms of various evaluation metrics.

Action Detection Activity Detection

Classification of full exceptional collections of line bundles on three blow-ups of $\mathbb{P}^{3}$

1 code implementation15 Oct 2018 Wanmin Liu, Song Yang, Xun Yu

A fullness conjecture of Kuznetsov says that if a smooth projective variety $X$ admits a full exceptional collection of line bundles of length $l$, then any exceptional collection of line bundles of length $l$ is full.

Algebraic Geometry 14F05, 14J45, 18E30

S-index: Towards Better Metrics for Quantifying Research Impact

no code implementations13 Jul 2015 Shah Neil, Song Yang

The ongoing growth in the volume of scientific literature available today precludes researchers from efficiently discerning the relevant from irrelevant content.

Cannot find the paper you are looking for? You can Submit a new open access paper.