Search Results for author: Chenguang Li

Found 8 papers, 0 papers with code

A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representations

no code implementations2 Nov 2023 Hang Chen, Keqing Du, Chenguang Li, Xinyu Yang

The fusion of causal models with deep learning introducing increasingly intricate data sets, such as the causal associations within images or between textual components, has surfaced as a focal research area.

Time Series

A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigms

no code implementations14 Sep 2022 Hang Chen, Keqing Du, Xinyu Yang, Chenguang Li

Understanding causality helps to structure interventions to achieve specific goals and enables predictions under interventions.

Causal Discovery

Reconstruct from BEV: A 3D Lane Detection Approach based on Geometry Structure Prior

no code implementations21 Jun 2022 Chenguang Li, Jia Shi, Ya Wang, Guangliang Cheng

Inspired by previous methods, we first analyze the geometry heuristic between the 3D lane and its 2D representation on the ground and propose to impose explicit supervision based on the structure prior, which makes it achievable to build inter-lane and intra-lane relationships to facilitate the reconstruction of 3D lanes from local to global.

3D Lane Detection Data Augmentation

Multi-level Domain Adaptation for Lane Detection

no code implementations21 Jun 2022 Chenguang Li, Boheng Zhang, Jia Shi, Guangliang Cheng

We focus on bridging domain discrepancy in lane detection among different scenarios to greatly reduce extra annotation and re-training costs for autonomous driving.

Autonomous Driving Domain Adaptation +3

Reconstruct from Top View: A 3D Lane Detection Approach based on Geometry Structure Prior

no code implementations CVPR 2022 Chenguang Li, Jia Shi, Ya Wang, Guangliang Cheng

Inspired by previous methods, we first analyze the geometry heuristic between the 3D lane and its 2D representation on the ground and propose to impose explicit supervision based on the structure prior, which makes it achievable to build inter-lane and intra-lane relationships to facilitate the reconstruction of 3D lanes from local to global.

3D Lane Detection Data Augmentation

What Matters In Branch Specialization? Using a Toy Task to Make Predictions

no code implementations NeurIPS Workshop SVRHM 2021 Chenguang Li, Arturo Deza

What motivates the brain to allocate tasks to different regions and what distinguishes multiple-demand brain regions and the tasks they perform from ones in highly specialized areas?

Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation

no code implementations ACL 2019 Jiangjie Chen, Ao Wang, Haiyun Jiang, Suo Feng, Chenguang Li, Yanghua Xiao

A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity.

Knowledge Graphs

KDSL: a Knowledge-Driven Supervised Learning Framework for Word Sense Disambiguation

no code implementations28 Aug 2018 Shi Yin, Yi Zhou, Chenguang Li, Shangfei Wang, Jianmin Ji, Xiaoping Chen, Ruili Wang

We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning.

Word Sense Disambiguation

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