no code implementations • 17 May 2019 • Zhizhong Han, Xiyang Wang, Chi-Man Vong, Yu-Shen Liu, Matthias Zwicker, C. L. Philip Chen
Then, the content and spatial information of each pair of view nodes are encoded by a novel spatial pattern correlation, where the correlation is computed among latent semantic patterns.
no code implementations • ECCV 2020 • Chi-Chong Wong, Chi-Man Vong
Large-scale point cloud semantic understanding is an important problem in self-driving cars and autonomous robotics navigation.
no code implementations • 30 Apr 2021 • Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen
We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.
no code implementations • 17 Jul 2021 • Jiahua Luo, Chi-Man Wong, Chi-Man Vong
Sparse Bayesian Learning (SBL) constructs an extremely sparse probabilistic model with very competitive generalization.
no code implementations • ICCV 2021 • Chi-Chong Wong, Chi-Man Vong
Current deep learning and graph machine learning methods fail to tackle such challenges and thus provide inferior performance in fine-grained 3D analysis.
no code implementations • 6 Sep 2022 • Qi Lai, Jianhang Zhou, Yanfen Gan, Chi-Man Vong, DeShuang Huang
Existing MIML methods are useful in many applications but most of which suffer from relatively low accuracy and training efficiency due to several issues: i) the inter-label correlations(i. e., the probabilistic correlations between the multiple labels corresponding to an object) are neglected; ii) the inter-instance correlations (i. e., the probabilistic correlations of different instances in predicting the object label) cannot be learned directly (or jointly) with other types of correlations due to the missing instance labels; iii) diverse inter-correlations (e. g., inter-label correlations, inter-instance correlations) can only be learned in multiple stages.
no code implementations • 21 Apr 2023 • Houcheng Su, Jintao Huang, Daixian Liu, Rui Yan, Jiao Li, Chi-Man Vong
Multi-instance multi-label (MIML) learning is widely applicated in numerous domains, such as the image classification where one image contains multiple instances correlated with multiple logic labels simultaneously.
no code implementations • 18 Jan 2024 • Chen-Bin Feng, Qi Lai, Kangdao Liu, Houcheng Su, Chi-Man Vong
To avoid predicting wrong masks with SAM, we propose a prediction result selection (PRS) algorithm.