Yiming Xu

education

1. 2021 - Now

   Vrije Universiteit Amsterdam & Universiteit van Amsterdam

   Master of Science in Computer Science - Big Data Engineering

1. 2020 - 2021

   Institut Polytechnique de Paris

   M1 - Data and Artificial Intelligence

1. 2015 - 2019

   Henan University

   Bachelor of Engineering in Computer Science

publications

1. ICCS

   Fine-Grained Label Learning via Siamese Network for Cross-modal Information Retrieval

   Yiming Xu, Jing Yu, Jingjing Guo, and 2 more authors

   2019

   Abs HTML PDF

   Cross-modal information retrieval aims to search for semantically relevant data from various modalities when given a query from one modality. For text-image retrieval, a common solution is to map texts and images into a common semantic space and measure their similarity directly. Both the positive and negative examples are used for common semantic space learning. Existing work treats the positive/negative text-image pairs as equally positive/negative. However, we observe that many positive examples resemble the negative ones in some degrees and vice versa. These “hard examples” are challenging for existing models. In this paper, we aim to assign fine-grained labels for the examples to capture the degrees of “hardness”, thus enhancing cross-modal correlation learning. Specifically, we propose a siamese network on both the positive and negative examples to obtain their semantic similarities. For each positive/negative example, we use the text description of the image in the example to calculate its similarity with the text in the example. Based on these similarities, we assign fine-grained labels to both the positives and negatives and introduce these labels to a pairwise similarity loss function. The loss function benefits from the labels to increase the influence of hard examples on the similarity learning while maximizing the similarity of relevant text-image pairs and minimizing the similarity of irrelevant pairs. We conduct extensive experiments on the English Wikipedia, Chinese Wikipedia, and TVGraz datasets. Compared with state-of-the-art models, our model achieves significant improvement on the retrieval performance by incorporating with fine-grained labels.

2. IMAGE

   Stable and compact face recognition via unlabeled data driven sparse representation-based classification

   Xiaohui Yang, Zheng Wang, Huan Wu, and 3 more authors

   Signal Processing: Image Communication 2022

   Abs HTML

   Sparse representation-based classification (SRC) has attracted much attention by casting the recognition problem as simple linear regression problem. SRC methods, however, still is limited to enough labeled samples per category, insufficient use of unlabeled samples, and instability of representation. For tackling these problems, an unlabeled data driven inverse projection pseudo-full-space representation-based classification model is proposed with low-rank sparse constraints. The proposed model aims to mine the hidden semantic information and intrinsic structure information of all available data, which is suitable for few labeled samples and proportion imbalance between labeled samples and unlabeled samples problems in frontal face recognition. The mixed Gauss–Seidel and Jacobian ADMM algorithm is introduced to solve the model. The convergence, representation capability and stability of the model are analyzed. Experiments on three public datasets show that the proposed LR-S-PFSRC model achieves stable results, especially for proportion imbalance of samples.