Minnan Luo

Minnan Luo

Auto-generated profile, based on publicly available information

Minnan Luo

Xi'an Jiaotong University, Xi'an, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
20 February 2017 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
MLMinnan Luo
Minnan Luo
XCXiaojun Chang
Xiaojun Chang
LNLiqiang Nie
Liqiang Nie
YYYi Yang
Yi Yang
AHAlexander G. Hauptmann
Alexander G. Hauptmann
QZQinghua Zheng
Qinghua Zheng
Video semantic recognition usually suffers from the curse of dimensionality and the absence of enough high-quality labeled instances, thus semisupervised feature selection gains increasing attentions for its efficiency and comprehensibility. Most of the previous methods assume that videos with close distance (neighbors) have similar labels and characterize the intrinsic local structure through a predetermined graph of both labeled and unlabeled data. However, besides the parameter tuning problem underlying the construction of the graph, the affinity measurement in the original feature space usually suffers from the curse of dimensionality. Additionally, the predetermined graph separates itself from the procedure of feature selection, which might lead to downgraded performance for video semantic recognition. In this paper, we exploit a novel semisupervised feature selection method from a new perspective. The primary assumption underlying our model is that the instances with similar labels should have a larger probability of being neighbors. Instead of using a predetermined similarity graph, we incorporate the exploration of the local structure into the procedure of joint feature selection so as to learn the optimal graph simultaneously. Moreover, an adaptive loss function is exploited to measure the label fitness, which significantly enhances model's robustness to videos with a small or substantial loss. We propose an efficient alternating optimization algorithm to solve the proposed challenging problem, together with analyses on its convergence and computational complexity in theory. Finally, extensive experimental results on benchmark datasets illustrate the effectiveness and superiority of the proposed approach on video semantic recognition related tasks.

27 January 2017 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
MLMinnan Luo
Minnan Luo
FNFeiping Nie
Feiping Nie
XCXiaojun Chang
Xiaojun Chang
YYYi Yang
Yi Yang
AHAlexander G. Hauptmann
Alexander G. Hauptmann
QZQinghua Zheng
Qinghua Zheng
Feature selection is one of the most important dimension reduction techniques for its efficiency and interpretation. Since practical data in large scale are usually collected without labels, and labeling these data are dramatically expensive and time-consuming, unsupervised feature selection has become a ubiquitous and challenging problem. Without label information, the fundamental problem of unsupervised feature selection lies in how to characterize the geometry structure of original feature space and produce a faithful feature subset, which preserves the intrinsic structure accurately. In this paper, we characterize the intrinsic local structure by an adaptive reconstruction graph and simultaneously consider its multiconnected-components (multicluster) structure by imposing a rank constraint on the corresponding Laplacian matrix. To achieve a desirable feature subset, we learn the optimal reconstruction graph and selective matrix simultaneously, instead of using a predetermined graph. We exploit an efficient alternative optimization algorithm to solve the proposed challenging problem, together with the theoretical analyses on its convergence and computational complexity. Finally, extensive experiments on clustering task are conducted over several benchmark data sets to verify the effectiveness and superiority of the proposed unsupervised feature selection algorithm.

4 January 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CYCaixia Yan
Caixia Yan
XCXiaojun Chang
Xiaojun Chang
MLMinnan Luo
Minnan Luo
HLHuan Liu
Huan Liu
XZXiaoqin Zhang
Xiaoqin Zhang
QZQinghua Zheng
Qinghua Zheng
Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories; 2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks.

17 June 2020 in Data Mining and Knowledge Discovery
Verified
Journal Article
Closed access
PDF file
JWJihong Wang
Jihong Wang
MLMinnan Luo
Minnan Luo
FSFnu Suya
Fnu Suya
JLJundong Li
Jundong Li
ZYZijiang Yang
Zijiang Yang
QZQinghua Zheng
Qinghua Zheng

16 June 2022 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LZLingling Zhang
Lingling Zhang
XCXiaojun Chang
Xiaojun Chang
Jun LiuJun Liu
Jun Liu
MLMinnan Luo
Minnan Luo
LZli zhihui
li zhihui
AHAlex Hauptmann
Alex Hauptmann
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training still need to be detected. We design an end-to-end deep transferable network TN-ZSTAD as the architecture for this solution. On the one hand, this network utilizes an activity graph transformer to predict a set of activity instances that appear in the video, rather than produces many activity proposals in advance. On the other hand, this network captures the common semantics of seen and unseen activities from their corresponding label embeddings, and it is optimized with an innovative loss function that considers the classification property on seen activities and the transfer property on unseen activities together. Experiments on the THUMOS’14, Charades, and ActivityNet datasets show promising performance in terms of detecting unseen activities.

1 January 2024
Verified
Conference Paper
Open access
PDF file
HWHerun Wan
Herun Wan
SFShangbin Feng
Shangbin Feng
ZTZhaoxuan Tan
Zhaoxuan Tan
HWHeng Wang
Heng Wang
YTYulia Tsvetkov
Yulia Tsvetkov
MLMinnan Luo
Minnan Luo
Herun Wan, Shangbin Feng, Zhaoxuan Tan, Heng Wang, Yulia Tsvetkov, Minnan Luo. Findings of the Association for Computational Linguistics ACL 2024. 2024.