Bo Ren

Bo Ren

Auto-generated profile, based on publicly available information

Bo Ren

Tencent Youtu Lab

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 February 2023
Verified
Book Chapter
Closed access
PDF file
XSXiujun Shu
Xiujun Shu
WWWei Wen
Wei Wen
HWHaoqian Wu
Haoqian Wu
KCKeyu Chen
Keyu Chen
YSYiran Song
Yiran Song
XWXiao Wang
Xiao Wang

26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
SHSunan He
Sunan He
TGTaian Guo
Taian Guo
TDTao Dai
Tao Dai
RQRuizhi Qiao
Ruizhi Qiao
XSXiujun Shu
Xiujun Shu
Shu-Tao XiaShu-Tao Xia
Shu-Tao Xia
Real-world recognition system often encounters the challenge of unseen labels. To identify such unseen labels, multi-label zero-shot learning (ML-ZSL) focuses on transferring knowledge by a pre-trained textual label embedding (e.g., GloVe). However, such methods only exploit single-modal knowledge from a language model, while ignoring the rich semantic information inherent in image-text pairs. Instead, recently developed open-vocabulary (OV) based methods succeed in exploiting such information of image-text pairs in object detection, and achieve impressive performance. Inspired by the success of OV-based methods, we propose a novel open-vocabulary framework, named multi-modal knowledge transfer (MKT), for multi-label classification. Specifically, our method exploits multi-modal knowledge of image-text pairs based on a vision and language pre-training (VLP) model. To facilitate transferring the image-text matching ability of VLP model, knowledge distillation is employed to guarantee the consistency of image and label embeddings, along with prompt tuning to further update the label embeddings. To further enable the recognition of multiple objects, a simple but effective two-stream module is developed to capture both local and global features. Extensive experimental results show that our method significantly outperforms state-of-the-art methods on public benchmark datasets.

19 August 2023
Verified
Book Chapter
Closed access
PDF file
JKJianfeng Kuang
Jianfeng Kuang
WHWei Hua
Wei Hua
DLDingkang Liang
Dingkang Liang
MYMingkun Yang
Mingkun Yang
DJDeqiang Jiang
Deqiang Jiang
XBXiang Bai
Xiang Bai

24 March 2020 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
JWJingjing Wu
Jingjing Wu
HLHao Liu
Hao Liu
JJJianguo Jiang
Jianguo Jiang
MQMeibin Qi
Meibin Qi
BRBo Ren
Bo Ren
YWYashen Wang
Yashen Wang
Person attribute recognition aims to identify the attribute labels from the pedestrian images. Extracting contextual relation from the images and attributes, including the spatial-semantic relations, the spatial context and the semantic correlation, is beneficial to enhance the discrimination of the features for recognizing the attributes. Thus, this work proposes a sequence contextual relation learning (SCRL) method to capture these relations. It first embeds the images and attributes into sequences in two branches. Then SCRL flexibly learns the contextual relation from the sequences with the parallel attention model structure, which integrates the inter-attention and intra-attention models. The inter-attention module is utilized to extract the spatial-semantic relations, while the intra-attention is designed to gain the spatial context and the semantic correlation. Both attention modules are comprised of several parallel attention units and each unit can obtain the pairwise relations in one subspace. Therefore, they obtain the relations in multiple subspaces, which can improve the comprehensiveness of the relation learning. Additionally, for the sake of better extraction of spatial-semantic relations, this paper employs connectionist temporal classification (CTC) loss which is capable of driving the network to enforce monotonic alignment between the image and attribute. It can also accelerate the convergence of the network by the algorithm in it. Extensive experiments on five public datasets, i.e., Market-1501 attribute, Duke attribute, PETA, RAP and PA-100K datasets, demonstrate the effectiveness of the proposed method.

20 October 2022
Verified
Book Chapter
Closed access
PDF file
BKBo Ke
Bo Ke
YZYunquan Zhu
Yunquan Zhu
MLMengtian Li
Mengtian Li
XSXiujun Shu
Xiujun Shu
RQRuizhi Qiao
Ruizhi Qiao
BRBo Ren
Bo Ren

4 December 2023
Verified
Conference Paper
Open access
XZXirong Zhuang
Xirong Zhuang
LZLan Zhang
Lan Zhang
CTChen Tang
Chen Tang
HLHuiqi Liu
Huiqi Liu
BWBin Wang
Bin Wang
BRBo Ren
Bo Ren
Well-trained deep learning (DL) models are widely used in various fields and recognized as valuable intellectual property. However, most existing efforts to fully exploit their value either require users to upload input data to provide machine learning services, which raises serious privacy concerns, or deploy DL models on the user side, resulting in a loss of control over the models. While a few active model authorization methods protect the model from unauthorized users, they cannot prevent the model from being redistributed or abused by authorized users. To address the urgent need to efficiently protect both model confidentiality and input data privacy, and achieve uninterrupted model controllability, we propose a contract-based model authorization framework called DeepContract. This framework enables model owners to deploy their models on the user side for local inference without revealing original model weights. Moreover, it allows them to grant and revoke the right to use their models at any time. Specifically, we propose a generic model encryption method that significantly outperforms the state-of-the-art method in both efficiency and security. Leveraging the integrity verification in the Trusted Execution Environment, contract-based and verifiable enclave codes generated by DeepContract can perform controlled inference using the encrypted model distributed on the user side. Our extensive evaluations show that DeepContract can achieve efficient and secure controllable model authorization for the pre-signed contract.