学界 | 一窥百度、京东、华为 AAAI 2019 收录论文

2019 年 2 月 9 日 AI研习社

AI 科技评论按，AAAI 人工智能学术界的顶级会议。作为第三十三届会议，AAAI 2019 又一次刷新了人工智能会议的记录，投稿数量达到 7,700 篇，录用率 16.2%。

近日，百度（百度研究院）、京东（京东数据科学研究院）、华为（华为诺亚方舟实验室）也分别整理公布了各自的 AAAI 2019 收录论文，并发表了简介文章。下面我们简单列出他们的收录论文，更详细的介绍可以点击附带链接阅读他们各自的介绍文章。

华为诺亚方舟实验室埃德蒙顿团队

ACE: An Actor Ensemble Algorithm for Continuous Controlwith Tree Search
https://arxiv.org/abs/1811.02696
QUOTA: The Quantile Option Architecturefor Reinforcement Learning
https://arxiv.org/abs/1811.02073

详细介绍请点击：

京东 AI

机器学习

AutoZOOM: Auto encoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks
https://pan.wps.cn/l/steqcro%20；
MPD-AL: An Efficient Membrane Potential Driven Aggregate-Label Learning Algorithm for Spiking Neurons
https://pan.wps.cn/l/s7ivylk%20；
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
https://pan.wps.cn/l/s87r4mq%20；
Attentive Tensor Product Learning
https://pan.wps.cn/l/s6pb4wb%20；

计算机视觉

Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
https://pan.wps.cn/l/srxdl7u%20；
Structured Two-stream Attention Network for Video Question Answering
https://pan.wps.cn/l/suy1wh4%20；
To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression
https://pan.wps.cn/l/s0ydo6b%20；
Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning
https://pan.wps.cn/l/s225cg7%20；

详细介绍请点击：

京东AI研究院 8 篇论文被AAAI 2019收录

百度

Modeling Coherence for Discourse Neural Machine Translation
Joint Representation Learning for Multi-Modal Transportation Recommendation
SpHMC: Spectral Hamiltonian Monte Carlo
StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents
Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos
Addressing the Under-translation Problem from the Entropy Perspective
Understanding Story Characters, Movie Actors and Their Versatility with Gaussian Representations
Joint Extraction of Entities and Overlapping Relations using Position-Attentive Sequence Labeling
Oversampling for Imbalanced Data via Optimal Transport
Multi-agent Discussion Mechanism for Natural Language Generation
Sign-Full Random Projections
Interactive Attention Transfer Network for Cross-domain Sentiment Classification
Exploiting the Contagious Effect for Employee Turnover Prediction
Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding