开课单位--南京大学
1
HoORaYs: Highorder Optimization of Rating Distance for Recommender Systems[HoORaYs:推荐系统评级距离的高阶优化]
Yuan Yao(南京大学) Latent factor models have become a prevalent method in recommender systems, to predict users' preference on items based on the historical user fee...
热度:9
Yuan Yao(南京大学) Latent factor models have become a prevalent method in recommender systems, to predict users' preference on items based on the historical user fee...
热度:9
2
Complex Object Classification: A Multi‑Modal Multi‑Instance Multi‑Label Deep Network with Optimal Transport[复杂对象分类:具有最优传输的多模态多实例多标签深度网络]
Yang Yang(南京大学) Complex Object Classification: A Multi‑Modal Multi‑Instance Multi‑Label Deep Network with Optimal Transport
热度:39
Yang Yang(南京大学) Complex Object Classification: A Multi‑Modal Multi‑Instance Multi‑Label Deep Network with Optimal Transport
热度:39
3
Strong Baselines for Author Name Disambiguation with and without Neural Networks[使用和不使用神经网络的作者姓名消歧的强基线]
Zhen-Yu Zhang(南京大学) Strong Baselines for Author Name Disambiguation with and without Neural Networks
热度:29
Zhen-Yu Zhang(南京大学) Strong Baselines for Author Name Disambiguation with and without Neural Networks
热度:29
4
Data-Free Adversarial Perturbations for Practical Black-Box Attack[实际黑盒攻击的无数据对抗扰动]
Zhaoxin Huan(南京大学) Data-Free Adversarial Perturbations for Practical Black-Box Attack
热度:36
Zhaoxin Huan(南京大学) Data-Free Adversarial Perturbations for Practical Black-Box Attack
热度:36
5
Bottom-Up and Top-Down Graph Pooling[自下而上和自顶向下的图形池]
Jia-Qi Yang(南京大学) Bottom-Up and Top-Down Graph Pooling
热度:31
Jia-Qi Yang(南京大学) Bottom-Up and Top-Down Graph Pooling
热度:31
6
Accelerating Hyperparameter Optimization of Deep Neural Network via Progressive Multi-Fidelity Evaluation[通过渐进多保真度评估加速深度神经网络超参数优化]
Guanghui Zhu(南京大学) Accelerating Hyperparameter Optimization of Deep Neural Network via Progressive Multi-Fidelity Evaluation
热度:39
Guanghui Zhu(南京大学) Accelerating Hyperparameter Optimization of Deep Neural Network via Progressive Multi-Fidelity Evaluation
热度:39
7
Entity Summarization with User Feedback[具有用户反馈的实体摘要]
Qingxia Liu(南京大学) Entity Summarization with User Feedback
热度:24
Qingxia Liu(南京大学) Entity Summarization with User Feedback
热度:24
8
ESBM: An Entity Summarization BenchMark[ESBM:实体摘要基准]
Qingxia Liu(南京大学) ESBM: An Entity Summarization BenchMark
热度:58
Qingxia Liu(南京大学) ESBM: An Entity Summarization BenchMark
热度:58
9
DAPter: Preventing User Data Abuse in Deep Learning Inference Services[DAPter:在深度学习推理服务中防止用户数据滥用]
Hao Wu(南京大学) DAPter: Preventing User Data Abuse in Deep Learning Inference Services
热度:51
Hao Wu(南京大学) DAPter: Preventing User Data Abuse in Deep Learning Inference Services
热度:51
10
Facilitating Human Intervention in Coreference Resolution with Comparative Entity Summaries[通过比较实体摘要促进人类干预共指消解]
Gong Cheng(南京大学) A primary challenge to Web data integration is coreference resolution, namely identifying entity descriptions from different data sources that refer t...
热度:46
Gong Cheng(南京大学) A primary challenge to Web data integration is coreference resolution, namely identifying entity descriptions from different data sources that refer t...
热度:46