activity
20192021
most citedInterpretable Compositional Convolutional Neural Networks

6 citations · 10 across the 3 of their papers we have counts for

collaborators

7 papers

cs.IR20212 cited

Multi-behavior Graph Contextual Aware Network for Session-based Recommendation

Qi Shen, Lingfei Wu, Yitong Pang +4

Predicting the next interaction of a short-term sequence is a challenging task in session-based recommendation (SBR).Multi-behavior session recommendation considers session sequenc…

cs.IR20212 cited

Graph Learning Augmented Heterogeneous Graph Neural Network for Social Recommendation

Yiming Zhang, Lingfei Wu, Qi Shen +5

Social recommendation based on social network has achieved great success in improving the performance of recommendation system. Since social network (user-user relations) and user-…

cs.CV20216 cited

Interpretable Compositional Convolutional Neural Networks

Wen Shen, Zhihua Wei, Shikun Huang +4

The reasonable definition of semantic interpretability presents the core challenge in explainable AI. This paper proposes a method to modify a traditional convolutional neural netw…

cs.SD2020

Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020

Shufan Shen, Ran Miao, Yi Wang +1

In this report, we discribe the submission of Tongji University undergraduate team to the CLOSE track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020 at Interspeech 202…

eess.AS2020

Tongji University Team for the VoxCeleb Speaker Recognition Challenge 2020

Rui Wang, Zhihua Wei, Yibin Zhan +1

In this report, we describe the submission of Tongji University team to the CLOSE track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020 at Interspeech 2020. We investig…

cs.CV2019

Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing

Wen Shen, Zhihua Wei, Shikun Huang +4

In this paper, we diagnose deep neural networks for 3D point cloud processing to explore utilities of different intermediate-layer network architectures. We propose a number of hyp…