Qiuqi Ruan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qiuqi Ruan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Gaoyun An
School of Computer Science and Technology, Beijing Jiaotong University, Beijing, China
6 shared publications - Jieru Jia
Institute of Information Science Beijing Jiaotong University Beijing China
2 shared publications - Yi Jin
Beijing Jiaotong University
2 shared publications - Congyan Lang
Beijing Jiaotong University, Beijing, China
1 shared publication - Jie Li
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
1 shared publication Ruonan Zhang
Beijing Jiaotong Univ, Inst Informat Sci, Beijing, Peoples R China
1 shared publication
Latest Publications
- 26 November 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (6) , 472
EIRA: an explicit-implicit representation alignment for multimodal relation extraction
- 26 November 2025
- Published by Springer Nature in Multimedia Systems
- Vol. 31 (6) , 472
EIRA: an explicit-implicit representation alignment for multimodal relation extraction
- 24 September 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
Attention redirection transformer with semantic oriented learning for unbiased scene graph generation
- 24 September 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
Attention redirection transformer with semantic oriented learning for unbiased scene graph generation
- 2 March 2023
- Published by Springer Nature
- p. 554-570
PromptLearner-CLIP: Contrastive Multi-Modal Action Representation Learning with Context Optimization
- 2 March 2023
- Published by Springer Nature
- p. 554-570
PromptLearner-CLIP: Contrastive Multi-Modal Action Representation Learning with Context Optimization
- Open Access
- 28 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 106303-106316
Multi-Feature Tensor Neighborhood Preserving Embedding for 3D Facial Expression Recognition
To investigate an effective representation model for 3D facial expression recognition, this paper proposes a multi-feature tensor neighborhood preserving embedding (MFTNPE) method, which seeks various attribute features from raw textured shape scan models of 3D facial expression to construct a multi-feature tensor model. With MFTNPE method, we can project the model into a tensor subspace, explore the interactions and correlations among multimodal data and then extract discriminative low-dimensional tensor features for 3D facial expression recognition. In the study, we first introduce a tensor model based on multi-feature integration for 3D facial expression recognition. Via exploring the textural and geometric features of 3D facial expression data, an original multi-feature tensor model is constructed by stacking various attribute maps orderly. Second, we utilize the tensor completion approach as the scheme of data preprocessing to correct the original multi-feature tensor model. Due to the presence of imperfect data in the projected attribute maps, the tensor completion can predict the missing data in tensor by the trace norm of multi-feature tensor model along each mode. Third, we redefine a weighted matrix for use in the orthogonal-based tensor neighborhood preserving embedding algorithm. In the weighted matrix, the class information is used to guarantee the correct neighborhood relationships for multi-feature tensor samples. This effectively avoids the disturbances and confusions between similar samples while preserving spatial structure and inter-class information. Finally, we conduct extensive experiments on two 3D facial expression recognition datasets. The experimental results show that the proposed method has much better efficiency and performance compared with the state-of-the-art methods.
- 28 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 106303-106316
Open AccessMulti-Feature Tensor Neighborhood Preserving Embedding for 3D Facial Expression Recognition
To investigate an effective representation model for 3D facial expression recognition, this paper proposes a multi-feature tensor neighborhood preserving embedding (MFTNPE) method, which seeks various attribute features from raw textured shape scan models of 3D facial expression to construct a multi-feature tensor model. With MFTNPE method, we can project the model into a tensor subspace, explore the interactions and correlations among multimodal data and then extract discriminative low-dimensional tensor features for 3D facial expression recognition. In the study, we first introduce a tensor model based on multi-feature integration for 3D facial expression recognition. Via exploring the textural and geometric features of 3D facial expression data, an original multi-feature tensor model is constructed by stacking various attribute maps orderly. Second, we utilize the tensor completion approach as the scheme of data preprocessing to correct the original multi-feature tensor model. Due to the presence of imperfect data in the projected attribute maps, the tensor completion can predict the missing data in tensor by the trace norm of multi-feature tensor model along each mode. Third, we redefine a weighted matrix for use in the orthogonal-based tensor neighborhood preserving embedding algorithm. In the weighted matrix, the class information is used to guarantee the correct neighborhood relationships for multi-feature tensor samples. This effectively avoids the disturbances and confusions between similar samples while preserving spatial structure and inter-class information. Finally, we conduct extensive experiments on two 3D facial expression recognition datasets. The experimental results show that the proposed method has much better efficiency and performance compared with the state-of-the-art methods.
- Open Access
Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
Contemporary person re-identification (\reid) methods usually require access to data from the deployment camera network during training in order to perform well. This is because contemporary \reid{} models trained on one dataset do not generalise to other camera networks due to the domain-shift between datasets. This requirement is often the bottleneck for deploying \reid{} systems in practical security or commercial applications, as it may be impossible to collect this data in advance or prohibitively costly to annotate it. This paper alleviates this issue by proposing a simple baseline for domain generalizable~(DG) person re-identification. That is, to learn a \reid{} model from a set of source domains that is suitable for application to unseen datasets out-of-the-box, without any model updating. Specifically, we observe that the domain discrepancy in \reid{} is due to style and content variance across datasets and demonstrate appropriate Instance and Feature Normalization alleviates much of the resulting domain-shift in Deep \reid{} models. Instance Normalization~(IN) in early layers filters out style statistic variations and Feature Normalization~(FN) in deep layers is able to further eliminate disparity in content statistics. Compared to contemporary alternatives, this approach is extremely simple to implement, while being faster to train and test, thus making it an extremely valuable baseline for implementing \reid{} in practice. With a few lines of code, it increases the rank 1 \reid{} accuracy by {11.8\%, 33.2\%, 12.8\% and 8.5\%} on the VIPeR, PRID, GRID, and i-LIDS benchmarks respectively. Source codes are available at \url{https://github.com/BJTUJia/person_reID_DualNorm}.
Open AccessFrustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
Contemporary person re-identification (\reid) methods usually require access to data from the deployment camera network during training in order to perform well. This is because contemporary \reid{} models trained on one dataset do not generalise to other camera networks due to the domain-shift between datasets. This requirement is often the bottleneck for deploying \reid{} systems in practical security or commercial applications, as it may be impossible to collect this data in advance or prohibitively costly to annotate it. This paper alleviates this issue by proposing a simple baseline for domain generalizable~(DG) person re-identification. That is, to learn a \reid{} model from a set of source domains that is suitable for application to unseen datasets out-of-the-box, without any model updating. Specifically, we observe that the domain discrepancy in \reid{} is due to style and content variance across datasets and demonstrate appropriate Instance and Feature Normalization alleviates much of the resulting domain-shift in Deep \reid{} models. Instance Normalization~(IN) in early layers filters out style statistic variations and Feature Normalization~(FN) in deep layers is able to further eliminate disparity in content statistics. Compared to contemporary alternatives, this approach is extremely simple to implement, while being faster to train and test, thus making it an extremely valuable baseline for implementing \reid{} in practice. With a few lines of code, it increases the rank 1 \reid{} accuracy by {11.8\%, 33.2\%, 12.8\% and 8.5\%} on the VIPeR, PRID, GRID, and i-LIDS benchmarks respectively. Source codes are available at \url{https://github.com/BJTUJia/person_reID_DualNorm}.
- Open Access
Multi-Level Recurrent Residual Networks for Action Recognition
Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the task related to sequence, we propose a novel Multi-Level Recurrent Residual Networks(MRRN) which incorporates three recognition streams. Each stream consists of a Residual Networks(ResNets) and a recurrent model. The proposed model captures spatiotemporal information by employing both alternative ResNets to learn spatial representations from static frames and stacked Simple Recurrent Units(SRUs) to model temporal dynamics. Three distinct-level streams learned low-, mid-, high-level representations independently are fused by computing a weighted average of their softmax scores to obtain the complementary representations of the video. Unlike previous models which boost performance at the cost of time complexity and space complexity, our models have a lower complexity by employing shortcut connection and are trained end-to-end with greater efficiency. MRRN displays significant performance improvements compared to CNN-RNN framework baselines and obtains comparable performance with the state-of-the-art, achieving 51.3% on HMDB-51 dataset and 81.9% on UCF-101 dataset although no additional data.
Open AccessMulti-Level Recurrent Residual Networks for Action Recognition
Most existing Convolutional Neural Networks(CNNs) used for action recognition are either difficult to optimize or underuse crucial temporal information. Inspired by the fact that the recurrent model consistently makes breakthroughs in the task related to sequence, we propose a novel Multi-Level Recurrent Residual Networks(MRRN) which incorporates three recognition streams. Each stream consists of a Residual Networks(ResNets) and a recurrent model. The proposed model captures spatiotemporal information by employing both alternative ResNets to learn spatial representations from static frames and stacked Simple Recurrent Units(SRUs) to model temporal dynamics. Three distinct-level streams learned low-, mid-, high-level representations independently are fused by computing a weighted average of their softmax scores to obtain the complementary representations of the video. Unlike previous models which boost performance at the cost of time complexity and space complexity, our models have a lower complexity by employing shortcut connection and are trained end-to-end with greater efficiency. MRRN displays significant performance improvements compared to CNN-RNN framework baselines and obtains comparable performance with the state-of-the-art, achieving 51.3% on HMDB-51 dataset and 81.9% on UCF-101 dataset although no additional data.
- 1 July 2017
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 160, 87-99
Multiple metric learning with query adaptive weights and multi-task re-weighting for person re-identification
- 1 July 2017
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 160, 87-99
Multiple metric learning with query adaptive weights and multi-task re-weighting for person re-identification
- 16 April 2016
- Published by Springer Nature in Multidimensional Systems and Signal Processing
- Vol. 28 (3) , 905-920
Multi-task clustering ELM for VIS-NIR cross-modal feature learning
- 16 April 2016
- Published by Springer Nature in Multidimensional Systems and Signal Processing
- Vol. 28 (3) , 905-920
Multi-task clustering ELM for VIS-NIR cross-modal feature learning
- 13 August 2015
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 20 (2) , 453-471
A sparse neighborhood preserving non-negative tensor factorization algorithm for facial expression recognition
- 13 August 2015
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 20 (2) , 453-471
A sparse neighborhood preserving non-negative tensor factorization algorithm for facial expression recognition