Yi-Dong Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yi-Dong Shen has a total of 52 co-authors. Here are the top co-authors by number of shared publications:
- Chong Liu
Institute of Software State Key Laboratory of Computer Science Chinese Academy of Sciences China
3 shared publications - Danny De Schreye
Katholieke Universiteit Leuven
3 shared publications - Jia-Huai You
University of Alberta
3 shared publications - Li-Yan Yuan
Department of Computing Science University of Alberta Edmonton T6G 2H1 Alberta Canada
3 shared publications - Yi Yang
Zhejiang University, China
3 shared publications - Fan Wang
Alibaba Group
2 shared publications
Latest Publications
- 4 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36  (5) , 2096-2109
Partial Clustering Ensemble
Clustering ensemble often provides robust and stable results without accessing original features of data, and thus has been widely studied. The conventional clustering ensemble methods often take the full multiple base partitions as inputs and provide a consensus clustering result. However, in many real-world applications, full base partitions are hard to obtain because some data may be missing in some base partitions. To tackle this problem, in this paper, we propose a novel partial clustering ensemble method, which takes the partial multiple base partitions as inputs. In this method, we simultaneously fill the missing values in the base partitions and ensemble them by fully considering the consensus and diversity. Moreover, to address the unreliability issue in the partial data scenario, we seamlessly plug it into a self-paced learning framework. The extensive experiments on benchmark data sets demonstrate the effectiveness and efficiency of the proposed method when handling incomplete data.
- 4 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36  (5) , 2096-2109
Partial Clustering Ensemble
Clustering ensemble often provides robust and stable results without accessing original features of data, and thus has been widely studied. The conventional clustering ensemble methods often take the full multiple base partitions as inputs and provide a consensus clustering result. However, in many real-world applications, full base partitions are hard to obtain because some data may be missing in some base partitions. To tackle this problem, in this paper, we propose a novel partial clustering ensemble method, which takes the partial multiple base partitions as inputs. In this method, we simultaneously fill the missing values in the base partitions and ensemble them by fully considering the consensus and diversity. Moreover, to address the unreliability issue in the partial data scenario, we seamlessly plug it into a self-paced learning framework. The extensive experiments on benchmark data sets demonstrate the effectiveness and efficiency of the proposed method when handling incomplete data.
- 20 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32  (10577149) , 3622-3633
Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches. Code is publicly available: github.com/LCFractal/TGDT.
- 20 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 32  (10577149) , 3622-3633
Efficient Token-Guided Image-Text Retrieval With Consistent Multimodal Contrastive Training
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches. Code is publicly available: github.com/LCFractal/TGDT.
- Open Access
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches.
Open AccessEfficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches.
- Open Access
Vision-Language Navigation with Random Environmental Mixup
Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the small data scale and large navigation space, makes the VLN task challenging. Previous works have proposed various data augmentation methods to reduce data bias. However, these works do not explicitly reduce the data bias across different house scenes. Therefore, the agent would overfit to the seen scenes and achieve poor navigation performance in the unseen scenes. To tackle this problem, we propose the Random Environmental Mixup (REM) method, which generates cross-connected house scenes as augmented data via mixuping environment. Specifically, we first select key viewpoints according to the room connection graph for each scene. Then, we cross-connect the key views of different scenes to construct augmented scenes. Finally, we generate augmented instruction-path pairs in the cross-connected scenes. The experimental results on benchmark datasets demonstrate that our augmentation data via REM help the agent reduce its performance gap between the seen and unseen environment and improve the overall performance, making our model the best existing approach on the standard VLN benchmark. The code have released: https://github.com/LCFractal/VLNREM.
Open AccessVision-Language Navigation with Random Environmental Mixup
Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the small data scale and large navigation space, makes the VLN task challenging. Previous works have proposed various data augmentation methods to reduce data bias. However, these works do not explicitly reduce the data bias across different house scenes. Therefore, the agent would overfit to the seen scenes and achieve poor navigation performance in the unseen scenes. To tackle this problem, we propose the Random Environmental Mixup (REM) method, which generates cross-connected house scenes as augmented data via mixuping environment. Specifically, we first select key viewpoints according to the room connection graph for each scene. Then, we cross-connect the key views of different scenes to construct augmented scenes. Finally, we generate augmented instruction-path pairs in the cross-connected scenes. The experimental results on benchmark datasets demonstrate that our augmentation data via REM help the agent reduce its performance gap between the seen and unseen environment and improve the overall performance, making our model the best existing approach on the standard VLN benchmark. The code have released: https://github.com/LCFractal/VLNREM.
- Open Access
Dual-Path Convolutional Image-Text Embeddings with Instance Loss
Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image / text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss is hard for network learning, since it starts from the two heterogeneous features to build inter-modal relationship. To address this problem, we propose the instance loss which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image / text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this paper constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available.
Open AccessDual-Path Convolutional Image-Text Embeddings with Instance Loss
Matching images and sentences demands a fine understanding of both modalities. In this paper, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image / text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss is hard for network learning, since it starts from the two heterogeneous features to build inter-modal relationship. To address this problem, we propose the instance loss which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image / text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this paper constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available.
- Open Access
Constraint Monotonicity, Epistemic Splitting and Foundedness Could in General Be Too Strong in Answer Set Programming
Recently, the notions of subjective constraint monotonicity, epistemic splitting, and foundedness have been introduced for epistemic logic programs, with the aim to use them as main criteria respectively intuitions to compare different answer set semantics proposed in the literature on how they comply with these intuitions. In this note, we consider these three notions and demonstrate on some examples that they may be too strong in general and may exclude some desired answer sets respectively world views. In conclusion, these properties should not be regarded as mandatory properties that every answer set semantics must satisfy in general.
Open AccessConstraint Monotonicity, Epistemic Splitting and Foundedness Could in General Be Too Strong in Answer Set Programming
Recently, the notions of subjective constraint monotonicity, epistemic splitting, and foundedness have been introduced for epistemic logic programs, with the aim to use them as main criteria respectively intuitions to compare different answer set semantics proposed in the literature on how they comply with these intuitions. In this note, we consider these three notions and demonstrate on some examples that they may be too strong in general and may exclude some desired answer sets respectively world views. In conclusion, these properties should not be regarded as mandatory properties that every answer set semantics must satisfy in general.
- 20 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32  (4) , 1497-1511
Self-Paced Clustering Ensemble
The clustering ensemble has emerged as an important extension of the classical clustering problem. It provides an elegant framework to integrate multiple weak base clusterings to generate a strong consensus result. Most existing clustering ensemble methods usually exploit all data to learn a consensus clustering result, which does not sufficiently consider the adverse effects caused by some difficult instances. To handle this problem, we propose a novel self-paced clustering ensemble (SPCE) method, which gradually involves instances from easy to difficult ones into the ensemble learning. In our method, we integrate the evaluation of the difficulty of instances and ensemble learning into a unified framework, which can automatically estimate the difficulty of instances and ensemble the base clusterings. To optimize the corresponding objective function, we propose a joint learning algorithm to obtain the final consensus clustering result. Experimental results on benchmark data sets demonstrate the effectiveness of our method.
- 20 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32  (4) , 1497-1511
Self-Paced Clustering Ensemble
The clustering ensemble has emerged as an important extension of the classical clustering problem. It provides an elegant framework to integrate multiple weak base clusterings to generate a strong consensus result. Most existing clustering ensemble methods usually exploit all data to learn a consensus clustering result, which does not sufficiently consider the adverse effects caused by some difficult instances. To handle this problem, we propose a novel self-paced clustering ensemble (SPCE) method, which gradually involves instances from easy to difficult ones into the ensemble learning. In our method, we integrate the evaluation of the difficulty of instances and ensemble learning into a unified framework, which can automatically estimate the difficulty of instances and ensemble the base clusterings. To optimize the corresponding objective function, we propose a joint learning algorithm to obtain the final consensus clustering result. Experimental results on benchmark data sets demonstrate the effectiveness of our method.
- Open Access
Unity Style Transfer for Person Re-Identification
Style variation has been a major challenge for person re-identification, which aims to match the same pedestrians across different cameras. Existing works attempted to address this problem with camera-invariant descriptor subspace learning. However, there will be more image artifacts when the difference between the images taken by different cameras is larger. To solve this problem, we propose a UnityStyle adaption method, which can smooth the style disparities within the same camera and across different cameras. Specifically, we firstly create UnityGAN to learn the style changes between cameras, producing shape-stable style-unity images for each camera, which is called UnityStyle images. Meanwhile, we use UnityStyle images to eliminate style differences between different images, which makes a better match between query and gallery. Then, we apply the proposed method to Re-ID models, expecting to obtain more style-robust depth features for querying. We conduct extensive experiments on widely used benchmark datasets to evaluate the performance of the proposed framework, the results of which confirm the superiority of the proposed model.
Open AccessUnity Style Transfer for Person Re-Identification
Style variation has been a major challenge for person re-identification, which aims to match the same pedestrians across different cameras. Existing works attempted to address this problem with camera-invariant descriptor subspace learning. However, there will be more image artifacts when the difference between the images taken by different cameras is larger. To solve this problem, we propose a UnityStyle adaption method, which can smooth the style disparities within the same camera and across different cameras. Specifically, we firstly create UnityGAN to learn the style changes between cameras, producing shape-stable style-unity images for each camera, which is called UnityStyle images. Meanwhile, we use UnityStyle images to eliminate style differences between different images, which makes a better match between query and gallery. Then, we apply the proposed method to Re-ID models, expecting to obtain more style-robust depth features for querying. We conduct extensive experiments on widely used benchmark datasets to evaluate the performance of the proposed framework, the results of which confirm the superiority of the proposed model.
- 3 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 31  (5) , 1592-1601
Person Reidentification via Multi-Feature Fusion With Adaptive Graph Learning
The goal of person reidentification (Re-ID) is to identify a given pedestrian from a network of nonoverlapping surveillance cameras. Most existing works follow the supervised learning paradigm which requires pairwise labeled training data for each pair of cameras. However, this limits their scalability to real-world applications where abundant unlabeled data are available. To address this issue, we propose a multi-feature fusion with adaptive graph learning model for unsupervised Re-ID. Our model aims to negotiate comprehensive assessment on the consistent graph structure of pedestrians with the help of special information of feature descriptors. Specifically, we incorporate multi-feature dictionary learning and adaptive multi-feature graph learning into a unified learning model such that the learned dictionaries are discriminative and the subsequent graph structure learning is accurate. An alternating optimization algorithm with proved convergence is developed to solve the final optimization objective. Extensive experiments on four benchmark data sets demonstrate the superiority and effectiveness of the proposed method.
- 3 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 31  (5) , 1592-1601
Person Reidentification via Multi-Feature Fusion With Adaptive Graph Learning
The goal of person reidentification (Re-ID) is to identify a given pedestrian from a network of nonoverlapping surveillance cameras. Most existing works follow the supervised learning paradigm which requires pairwise labeled training data for each pair of cameras. However, this limits their scalability to real-world applications where abundant unlabeled data are available. To address this issue, we propose a multi-feature fusion with adaptive graph learning model for unsupervised Re-ID. Our model aims to negotiate comprehensive assessment on the consistent graph structure of pedestrians with the help of special information of feature descriptors. Specifically, we incorporate multi-feature dictionary learning and adaptive multi-feature graph learning into a unified learning model such that the learned dictionaries are discriminative and the subsequent graph structure learning is accurate. An alternating optimization algorithm with proved convergence is developed to solve the final optimization objective. Extensive experiments on four benchmark data sets demonstrate the superiority and effectiveness of the proposed method.
- 5 October 2018
- Published by Springer Nature
- p. 86-102
RCAA: Relational Context-Aware Agents for Person Search
- 5 October 2018
- Published by Springer Nature
- p. 86-102
RCAA: Relational Context-Aware Agents for Person Search