BezierFormer: A Unified Architecture for 2D and 3D Lane Detection

no code implementations • 25 Apr 2024 • Zhiwei Dong, Xi Zhu, Xiya Cao, Ran Ding, Wei Li, Caifa Zhou, Yongliang Wang, Qiangbo Liu

B\'{e}zierFormer formulate queries as B\'{e}zier control points and incorporate a novel B\'{e}zier curve attention mechanism.

Unravel Anomalies: An End-to-end Seasonal-Trend Decomposition Approach for Time Series Anomaly Detection

1 code implementation • 30 Sep 2023 • Zhenwei Zhang, Ruiqi Wang, Ran Ding, Yuantao Gu

Traditional Time-series Anomaly Detection (TAD) methods often struggle with the composite nature of complex time-series data and a diverse array of anomalies.

Anomaly Detection Time Series +1

Topic Modeling with Wasserstein Autoencoders

1 code implementation • ACL 2019 • Feng Nan, Ran Ding, Ramesh Nallapati, Bing Xiang

To measure the diversity of the produced topics, we propose a simple topic uniqueness metric.

Generative Adversarial Network Topic Models

WEAKLY SEMI-SUPERVISED NEURAL TOPIC MODELS

no code implementations • ICLR Workshop LLD 2019 • Ian Gemp, Ramesh Nallapati, Ran Ding, Feng Nan, Bing Xiang

We extend NTMs to the weakly semi-supervised setting by using informative priors in the training objective.

Topic Models

Coherence-Aware Neural Topic Modeling

2 code implementations • EMNLP 2018 • Ran Ding, Ramesh Nallapati, Bing Xiang

Topic models are evaluated based on their ability to describe documents well (i. e. low perplexity) and to produce topics that carry coherent semantic meaning.

Topic Models Variational Inference