Xin Xin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Xin Xin has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Ping Guo
Beijing Normal University
4 shared publications - Yao Yao
School of Computer Science Beijing Institute of Technology 100081 Beijing China
3 shared publications Bo Li
Platform and Content Group, Tencent
2 shared publicationsLili Li
Platform and Content Group, Tencent
2 shared publications- Sijia Zhao
School of Computer Science and Technology, Beijing Institute of Technology
2 shared publications Xi Chen
Platform and Content Group, Tencent
2 shared publications
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (12) , 12981-12989
Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking
Visual Entity Linking (VEL) is a crucial task for achieving fine-grained visual understanding, matching objects within images (visual mentions) to entities in a knowledge base. Previous VEL tasks rely on textual inputs, but writing queries for complex scenes can be challenging. Visual inputs like clicks or bounding boxes offer a more convenient alternative. Therefore, we propose a new task, Pixel-Level Visual Entity Linking (PL-VEL), which uses pixel masks from visual inputs to refer to objects, supplementing reference methods for VEL. To facilitate research on this task, we have constructed the MaskOVEN-Wiki dataset through an entirely automatic reverse region-entity annotation framework. This dataset contains over 5 million annotations aligning pixel-level regions with entity-level labels, which will advance visual understanding towards fine-grained. Moreover, as pixel masks correspond to semantic regions in an image, we enhance previous patch-interacted attention with region-interacted attention by a visual semantic tokenization approach. Manual evaluation results indicate that the reverse annotation framework achieved a 94.8% annotation success rate. Experimental results show that models trained on this dataset improved accuracy by 18 points compared to zero-shot models. Additionally, the semantic tokenization method achieved a 5-point accuracy improvement over the trained baseline.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (12) , 12981-12989
Open AccessReverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking
Visual Entity Linking (VEL) is a crucial task for achieving fine-grained visual understanding, matching objects within images (visual mentions) to entities in a knowledge base. Previous VEL tasks rely on textual inputs, but writing queries for complex scenes can be challenging. Visual inputs like clicks or bounding boxes offer a more convenient alternative. Therefore, we propose a new task, Pixel-Level Visual Entity Linking (PL-VEL), which uses pixel masks from visual inputs to refer to objects, supplementing reference methods for VEL. To facilitate research on this task, we have constructed the MaskOVEN-Wiki dataset through an entirely automatic reverse region-entity annotation framework. This dataset contains over 5 million annotations aligning pixel-level regions with entity-level labels, which will advance visual understanding towards fine-grained. Moreover, as pixel masks correspond to semantic regions in an image, we enhance previous patch-interacted attention with region-interacted attention by a visual semantic tokenization approach. Manual evaluation results indicate that the reverse annotation framework achieved a 94.8% annotation success rate. Experimental results show that models trained on this dataset improved accuracy by 18 points compared to zero-shot models. Additionally, the semantic tokenization method achieved a 5-point accuracy improvement over the trained baseline.
- 9 March 2025
- Published by Springer Nature
- p. 124-133
Alias Extraction Enhanced by Automatically Generated Long-Tail Instances
- 9 March 2025
- Published by Springer Nature
- p. 124-133
Alias Extraction Enhanced by Automatically Generated Long-Tail Instances
- Open Access
Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking
Visual Entity Linking (VEL) is a crucial task for achieving fine-grained visual understanding, matching objects within images (visual mentions) to entities in a knowledge base. Previous VEL tasks rely on textual inputs, but writing queries for complex scenes can be challenging. Visual inputs like clicks or bounding boxes offer a more convenient alternative. Therefore, we propose a new task, Pixel-Level Visual Entity Linking (PL-VEL), which uses pixel masks from visual inputs to refer to objects, supplementing reference methods for VEL. To facilitate research on this task, we have constructed the MaskOVEN-Wiki dataset through an entirely automatic reverse region-entity annotation framework. This dataset contains over 5 million annotations aligning pixel-level regions with entity-level labels, which will advance visual understanding towards fine-grained. Moreover, as pixel masks correspond to semantic regions in an image, we enhance previous patch-interacted attention with region-interacted attention by a visual semantic tokenization approach. Manual evaluation results indicate that the reverse annotation framework achieved a 94.8% annotation success rate. Experimental results show that models trained on this dataset improved accuracy by 18 points compared to zero-shot models. Additionally, the semantic tokenization method achieved a 5-point accuracy improvement over the trained baseline.
Open AccessReverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking
Visual Entity Linking (VEL) is a crucial task for achieving fine-grained visual understanding, matching objects within images (visual mentions) to entities in a knowledge base. Previous VEL tasks rely on textual inputs, but writing queries for complex scenes can be challenging. Visual inputs like clicks or bounding boxes offer a more convenient alternative. Therefore, we propose a new task, Pixel-Level Visual Entity Linking (PL-VEL), which uses pixel masks from visual inputs to refer to objects, supplementing reference methods for VEL. To facilitate research on this task, we have constructed the MaskOVEN-Wiki dataset through an entirely automatic reverse region-entity annotation framework. This dataset contains over 5 million annotations aligning pixel-level regions with entity-level labels, which will advance visual understanding towards fine-grained. Moreover, as pixel masks correspond to semantic regions in an image, we enhance previous patch-interacted attention with region-interacted attention by a visual semantic tokenization approach. Manual evaluation results indicate that the reverse annotation framework achieved a 94.8% annotation success rate. Experimental results show that models trained on this dataset improved accuracy by 18 points compared to zero-shot models. Additionally, the semantic tokenization method achieved a 5-point accuracy improvement over the trained baseline.
- Open Access
Pulsar Candidate Identification with Artificial Intelligence Techniques
Discovering pulsars is a significant and meaningful research topic in the field of radio astronomy. With the advent of astronomical instruments such as he Five-hundred-meter Aperture Spherical Telescope (FAST) in China, data volumes and data rates are exponentially growing. This fact necessitates a focus on artificial intelligence (AI) technologies that can perform the automatic pulsar candidate identification to mine large astronomical data sets. Automatic pulsar candidate identification can be considered as a task of determining potential candidates for further investigation and eliminating noises of radio frequency interferences or other non-pulsar signals. It is very hard to raise the performance of DCNN-based pulsar identification because the limited training samples restrict network structure to be designed deep enough for learning good features as well as the crucial class imbalance problem due to very limited number of real pulsar samples. To address these problems, we proposed a framework which combines deep convolution generative adversarial network (DCGAN) with support vector machine (SVM) to deal with imbalance class problem and to improve pulsar identification accuracy. DCGAN is used as sample generation and feature learning model, and SVM is adopted as the classifier for predicting candidate's labels in the inference stage. The proposed framework is a novel technique which not only can solve imbalance class problem but also can learn discriminative feature representations of pulsar candidates instead of computing hand-crafted features in preprocessing steps too, which makes it more accurate for automatic pulsar candidate selection. Experiments on two pulsar datasets verify the effectiveness and efficiency of our proposed method.
Open AccessPulsar Candidate Identification with Artificial Intelligence Techniques
Discovering pulsars is a significant and meaningful research topic in the field of radio astronomy. With the advent of astronomical instruments such as he Five-hundred-meter Aperture Spherical Telescope (FAST) in China, data volumes and data rates are exponentially growing. This fact necessitates a focus on artificial intelligence (AI) technologies that can perform the automatic pulsar candidate identification to mine large astronomical data sets. Automatic pulsar candidate identification can be considered as a task of determining potential candidates for further investigation and eliminating noises of radio frequency interferences or other non-pulsar signals. It is very hard to raise the performance of DCNN-based pulsar identification because the limited training samples restrict network structure to be designed deep enough for learning good features as well as the crucial class imbalance problem due to very limited number of real pulsar samples. To address these problems, we proposed a framework which combines deep convolution generative adversarial network (DCGAN) with support vector machine (SVM) to deal with imbalance class problem and to improve pulsar identification accuracy. DCGAN is used as sample generation and feature learning model, and SVM is adopted as the classifier for predicting candidate's labels in the inference stage. The proposed framework is a novel technique which not only can solve imbalance class problem but also can learn discriminative feature representations of pulsar candidates instead of computing hand-crafted features in preprocessing steps too, which makes it more accurate for automatic pulsar candidate selection. Experiments on two pulsar datasets verify the effectiveness and efficiency of our proposed method.
- 9 December 2015
- Published by Springer Nature
- p. 506-514
Neural Networks with Marginalized Corrupted Hidden Layer
- 9 December 2015
- Published by Springer Nature
- p. 506-514
Neural Networks with Marginalized Corrupted Hidden Layer
- 8 July 2015
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 30 (4) , 917-932
When Factorization Meets Heterogeneous Latent Topics: An Interpretable Cross-Site Recommendation Framework
- 8 July 2015
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 30 (4) , 917-932
When Factorization Meets Heterogeneous Latent Topics: An Interpretable Cross-Site Recommendation Framework
- Open Access
- 20 May 2015
- Published by Springer Nature in Cognitive Computation
- Vol. 7 (5) , 633
Erratum to: Image Fusion by Hierarchical Joint Sparse Representation
- 20 May 2015
- Published by Springer Nature in Cognitive Computation
- Vol. 7 (5) , 633
Open AccessErratum to: Image Fusion by Hierarchical Joint Sparse Representation
- 26 November 2014
- Published by Springer Nature
- p. 357-368
Learning to Display in Sponsored Search
- 20 November 2013
- Published by Springer Nature in Cognitive Computation
- Vol. 6 (3) , 281-292
Image Fusion by Hierarchical Joint Sparse Representation
- 20 November 2013
- Published by Springer Nature in Cognitive Computation
- Vol. 6 (3) , 281-292
Image Fusion by Hierarchical Joint Sparse Representation