Zijian Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zijian Li has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Xun Jian
Comptuer Science, Hong Kong University of Science and Technology, Hong Kong, HK Hong Kong
4 shared publications - Lei Chen
HKUST, Hong Kong, Hong Kong
3 shared publications Lei Chen
Hong Kong University of Science and Technology
2 shared publications- Xiang Lian
Kent State University, Kent, OH, USA
2 shared publications - Yue Wang
Shenzhen Institute of Computing Sciences, Shenzhen, China
2 shared publications - Changxing Ding
South China University of Technology
1 shared publication
Latest Publications
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2347-2356
KBest: Efficient Vector Search on Kunpeng CPU
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 2347-2356
Open AccessKBest: Efficient Vector Search on Kunpeng CPU
- Open Access
Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection
Human-Object Interaction (HOI) detection is a core task for high-level image understanding. Recently, Detection Transformer (DETR)-based HOI detectors have become popular due to their superior performance and efficient structure. However, these approaches typically adopt fixed HOI queries for all testing images, which is vulnerable to the location change of objects in one specific image. Accordingly, in this paper, we propose to enhance DETR's robustness by mining hard-positive queries, which are forced to make correct predictions using partial visual cues. First, we explicitly compose hard-positive queries according to the ground-truth (GT) position of labeled human-object pairs for each training image. Specifically, we shift the GT bounding boxes of each labeled human-object pair so that the shifted boxes cover only a certain portion of the GT ones. We encode the coordinates of the shifted boxes for each labeled human-object pair into an HOI query. Second, we implicitly construct another set of hard-positive queries by masking the top scores in cross-attention maps of the decoder layers. The masked attention maps then only cover partial important cues for HOI predictions. Finally, an alternate strategy is proposed that efficiently combines both types of hard queries. In each iteration, both DETR's learnable queries and one selected type of hard-positive queries are adopted for loss computation. Experimental results show that our proposed approach can be widely applied to existing DETR-based HOI detectors. Moreover, we consistently achieve state-of-the-art performance on three benchmarks: HICO-DET, V-COCO, and HOI-A. Code is available at https://github.com/MuchHair/HQM.
Open AccessTowards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection
Human-Object Interaction (HOI) detection is a core task for high-level image understanding. Recently, Detection Transformer (DETR)-based HOI detectors have become popular due to their superior performance and efficient structure. However, these approaches typically adopt fixed HOI queries for all testing images, which is vulnerable to the location change of objects in one specific image. Accordingly, in this paper, we propose to enhance DETR's robustness by mining hard-positive queries, which are forced to make correct predictions using partial visual cues. First, we explicitly compose hard-positive queries according to the ground-truth (GT) position of labeled human-object pairs for each training image. Specifically, we shift the GT bounding boxes of each labeled human-object pair so that the shifted boxes cover only a certain portion of the GT ones. We encode the coordinates of the shifted boxes for each labeled human-object pair into an HOI query. Second, we implicitly construct another set of hard-positive queries by masking the top scores in cross-attention maps of the decoder layers. The masked attention maps then only cover partial important cues for HOI predictions. Finally, an alternate strategy is proposed that efficiently combines both types of hard queries. In each iteration, both DETR's learnable queries and one selected type of hard-positive queries are adopted for loss computation. Experimental results show that our proposed approach can be widely applied to existing DETR-based HOI detectors. Moreover, we consistently achieve state-of-the-art performance on three benchmarks: HICO-DET, V-COCO, and HOI-A. Code is available at https://github.com/MuchHair/HQM.
- 26 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Effective Similarity Search on Heterogeneous Networks: A Meta-path Free Approach
Heterogeneous information networks (HINs) are usually used to model information systems with multi-type objects and relations. In contrast, graphs that have a single type of nodes and edges, are often called homogeneous graphs. Measuring similarities among objects is an important task in data mining applications, such as web search, link prediction, and clustering. Currently, several similarity measures are defined for HINs. Most of these measures are based on meta-paths, which show sequences of node classes and edge types along the paths between two nodes. However, meta-paths, which are often designed by domain experts, are hard to enumerate and choose w.r.t. the quality of similarity scores. This makes using existing similarity measures in real applications difficult. To address this problem, we extend SimRank, a well-known similarity measure on homogeneous graphs, to HINs, by introducing the concept of the decay graph. The newly proposed similarity measure is called HowSim, which has the property of being meta-path free, and capturing the structural and semantic similarity simultaneously. The generality and effectiveness of HowSim, and the efficiency of our proposed algorithms for computing HowSim scores, are demonstrated by extensive experiments.
- 26 August 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Effective Similarity Search on Heterogeneous Networks: A Meta-path Free Approach
Heterogeneous information networks (HINs) are usually used to model information systems with multi-type objects and relations. In contrast, graphs that have a single type of nodes and edges, are often called homogeneous graphs. Measuring similarities among objects is an important task in data mining applications, such as web search, link prediction, and clustering. Currently, several similarity measures are defined for HINs. Most of these measures are based on meta-paths, which show sequences of node classes and edge types along the paths between two nodes. However, meta-paths, which are often designed by domain experts, are hard to enumerate and choose w.r.t. the quality of similarity scores. This makes using existing similarity measures in real applications difficult. To address this problem, we extend SimRank, a well-known similarity measure on homogeneous graphs, to HINs, by introducing the concept of the decay graph. The newly proposed similarity measure is called HowSim, which has the property of being meta-path free, and capturing the structural and semantic similarity simultaneously. The generality and effectiveness of HowSim, and the efficiency of our proposed algorithms for computing HowSim scores, are demonstrated by extensive experiments.
- 30 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Efficient Similarity Search for Sets over Graphs
Measuring similarities among different nodes is import in graph analysis tasks, such as link prediction, and recommendation. Among different similarity measurements, SimRank is one of the most popular and promising ones, and has received a lot of research attention. While most current studies focus on single-pair, single-source/top-k and all-pairs SimRank computation, few of them have studied finding similar pairs given a set of node pairs, which has attractive applications in personalized search and recommendation tasks. In this paper, we present Carmo, an efficient algorithm for retrieving the top-k similarities from an arbitrary set of pairs. In addition, we introduce two types of indexes to boost the efficiency of Carmo: one is hub-based, the other is tree-based. We shows the effectiveness and efficiency of our proposed methods by extensive experiments.
- 30 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. PP (10414347) , 1
Efficient Similarity Search for Sets over Graphs
Measuring similarities among different nodes is import in graph analysis tasks, such as link prediction, and recommendation. Among different similarity measurements, SimRank is one of the most popular and promising ones, and has received a lot of research attention. While most current studies focus on single-pair, single-source/top-k and all-pairs SimRank computation, few of them have studied finding similar pairs given a set of node pairs, which has attractive applications in personalized search and recommendation tasks. In this paper, we present Carmo, an efficient algorithm for retrieving the top-k similarities from an arbitrary set of pairs. In addition, we introduce two types of indexes to boost the efficiency of Carmo: one is hub-based, the other is tree-based. We shows the effectiveness and efficiency of our proposed methods by extensive experiments.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 268-279
G*-Tree: An Efficient Spatial Index on Road Networks
In this paper, we propose an efficient hierarchical index, G*-tree, to optimize spatial queries on road networks. Most existing graph indexes can only support one kind of query, and thus we need to build multiple indexes on a road network to handle various kinds of spatial queries, which is inefficient and unscalable for real-world applications. To address the problem, a recent study proposes G-tree to support multiple types of spatial queries on road networks within one framework. However, the assembly-based method on G-tree is not efficient enough to handle spatial queries when vertices, which are close in a road network, are distant in G-tree. To address the inefficiency problem of G-tree, in this paper, we propose a novel index structure on road networks, namely G*-tree, whose key idea is to build shortcuts between selected leaf nodes. Based on G*-tree, we propose three shortcut-based algorithms to answer distance queries, k-nearest neighbor queries and range queries, respectively, which are more efficient than the existing assembly-based algorithms on G-tree. Moreover, we propose a shortcut selection algorithm to optimize the performance of spatial queries on G*-tree. We conduct extensive experiments to compare our G*-tree and the state-of-the-art indexing methods on various large-scale road networks, where the results demonstrate that our G*-tree has better efficiency and scalability than the competitors to handle spatial queries.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 268-279
G*-Tree: An Efficient Spatial Index on Road Networks
In this paper, we propose an efficient hierarchical index, G*-tree, to optimize spatial queries on road networks. Most existing graph indexes can only support one kind of query, and thus we need to build multiple indexes on a road network to handle various kinds of spatial queries, which is inefficient and unscalable for real-world applications. To address the problem, a recent study proposes G-tree to support multiple types of spatial queries on road networks within one framework. However, the assembly-based method on G-tree is not efficient enough to handle spatial queries when vertices, which are close in a road network, are distant in G-tree. To address the inefficiency problem of G-tree, in this paper, we propose a novel index structure on road networks, namely G*-tree, whose key idea is to build shortcuts between selected leaf nodes. Based on G*-tree, we propose three shortcut-based algorithms to answer distance queries, k-nearest neighbor queries and range queries, respectively, which are more efficient than the existing assembly-based algorithms on G-tree. Moreover, we propose a shortcut selection algorithm to optimize the performance of spatial queries on G*-tree. We conduct extensive experiments to compare our G*-tree and the state-of-the-art indexing methods on various large-scale road networks, where the results demonstrate that our G*-tree has better efficiency and scalability than the competitors to handle spatial queries.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 533-544
An Efficient Probabilistic Approach for Graph Similarity Search
Graph similarity search is a common and fundamental operation in graph databases. One of the most popular graph similarity measures is the Graph Edit Distance (GED) mainly because of its broad applicability and high interpretability. Despite its prevalence, exact GED computation is proved to be NP-hard, which could result in unsatisfactory computational efficiency on large graphs. However, exactly accurate search results are usually unnecessary for real-world applications especially when the responsiveness is far more important than the accuracy. Thus, in this paper, we propose a novel probabilistic approach to efficiently estimate GED, which is further leveraged for the graph similarity search. Specifically, we first take branches as elementary structures in graphs, and introduce a novel graph similarity measure by comparing branches between graphs, i.e., Graph Branch Distance (GBD), which can be efficiently calculated in polynomial time. Then, we formulate the relationship between GED and GBD by considering branch variations as the result ascribed to graph edit operations, and model this process by probabilistic approaches. By applying our model, the GED between any two graphs can be efficiently estimated by their GBD, and these estimations are finally utilized in the graph similarity search. Extensive experiments show that our approach has better accuracy, efficiency and scalability than other comparable methods in the graph similarity search over real and synthetic data sets.
- 1 April 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 533-544
An Efficient Probabilistic Approach for Graph Similarity Search
Graph similarity search is a common and fundamental operation in graph databases. One of the most popular graph similarity measures is the Graph Edit Distance (GED) mainly because of its broad applicability and high interpretability. Despite its prevalence, exact GED computation is proved to be NP-hard, which could result in unsatisfactory computational efficiency on large graphs. However, exactly accurate search results are usually unnecessary for real-world applications especially when the responsiveness is far more important than the accuracy. Thus, in this paper, we propose a novel probabilistic approach to efficiently estimate GED, which is further leveraged for the graph similarity search. Specifically, we first take branches as elementary structures in graphs, and introduce a novel graph similarity measure by comparing branches between graphs, i.e., Graph Branch Distance (GBD), which can be efficiently calculated in polynomial time. Then, we formulate the relationship between GED and GBD by considering branch variations as the result ascribed to graph edit operations, and model this process by probabilistic approaches. By applying our model, the GED between any two graphs can be efficiently estimated by their GBD, and these estimations are finally utilized in the graph similarity search. Extensive experiments show that our approach has better accuracy, efficiency and scalability than other comparable methods in the graph similarity search over real and synthetic data sets.
- Open Access
An Efficient Probabilistic Approach for Graph Similarity Search
Graph similarity search is a common and fundamental operation in graph databases. One of the most popular graph similarity measures is the Graph Edit Distance (GED) mainly because of its broad applicability and high interpretability. Despite its prevalence, exact GED computation is proved to be NP-hard, which could result in unsatisfactory computational efficiency on large graphs. However, exactly accurate search results are usually unnecessary for real-world applications especially when the responsiveness is far more important than the accuracy. Thus, in this paper, we propose a novel probabilistic approach to efficiently estimate GED, which is further leveraged for the graph similarity search. Specifically, we first take branches as elementary structures in graphs, and introduce a novel graph similarity measure by comparing branches between graphs, i.e., Graph Branch Distance (GBD), which can be efficiently calculated in polynomial time. Then, we formulate the relationship between GED and GBD by considering branch variations as the result ascribed to graph edit operations, and model this process by probabilistic approaches. By applying our model, the GED between any two graphs can be efficiently estimated by their GBD, and these estimations are finally utilized in the graph similarity search. Extensive experiments show that our approach has better accuracy, efficiency and scalability than other comparable methods in the graph similarity search over real and synthetic data sets.
Open AccessAn Efficient Probabilistic Approach for Graph Similarity Search
Graph similarity search is a common and fundamental operation in graph databases. One of the most popular graph similarity measures is the Graph Edit Distance (GED) mainly because of its broad applicability and high interpretability. Despite its prevalence, exact GED computation is proved to be NP-hard, which could result in unsatisfactory computational efficiency on large graphs. However, exactly accurate search results are usually unnecessary for real-world applications especially when the responsiveness is far more important than the accuracy. Thus, in this paper, we propose a novel probabilistic approach to efficiently estimate GED, which is further leveraged for the graph similarity search. Specifically, we first take branches as elementary structures in graphs, and introduce a novel graph similarity measure by comparing branches between graphs, i.e., Graph Branch Distance (GBD), which can be efficiently calculated in polynomial time. Then, we formulate the relationship between GED and GBD by considering branch variations as the result ascribed to graph edit operations, and model this process by probabilistic approaches. By applying our model, the GED between any two graphs can be efficiently estimated by their GBD, and these estimations are finally utilized in the graph similarity search. Extensive experiments show that our approach has better accuracy, efficiency and scalability than other comparable methods in the graph similarity search over real and synthetic data sets.
- 1 July 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19457871,p. 1-6
Geo-informative discriminative image representation by semi-supervised hierarchical topic modeling
Nowadays, the prevalence of sharing tourist photos to online communities has created an increasing demand for mining discriminative architecture aspects from historic landmarks. Some previous researches have demonstrated that topic models could discover discriminative features represented by meaningful visual-topics. However, they seldom exploited the indicative function of geo-tags and the hierarchy in architecture characteristics. In order to utilize this information, we proposed a semi-supervised hierarchical topic modeling approach (namely, shTM). In our approach, every image could be represented by a probability distribution over selected geo-related visual-topics from a partly randomized topic tree. We evaluated our approach on a real-world dataset with over 26 thousand geo-informative photos from Flickr. Experiments show that shTM topics could reveal more discriminative aspects of a specific architecture than other well-known image features, such as HOG and SIFT, on the tasks of automatic photo categorization and geographical information retrieval.
- 1 July 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19457871,p. 1-6
Geo-informative discriminative image representation by semi-supervised hierarchical topic modeling
Nowadays, the prevalence of sharing tourist photos to online communities has created an increasing demand for mining discriminative architecture aspects from historic landmarks. Some previous researches have demonstrated that topic models could discover discriminative features represented by meaningful visual-topics. However, they seldom exploited the indicative function of geo-tags and the hierarchy in architecture characteristics. In order to utilize this information, we proposed a semi-supervised hierarchical topic modeling approach (namely, shTM). In our approach, every image could be represented by a probability distribution over selected geo-related visual-topics from a partly randomized topic tree. We evaluated our approach on a real-world dataset with over 26 thousand geo-informative photos from Flickr. Experiments show that shTM topics could reveal more discriminative aspects of a specific architecture than other well-known image features, such as HOG and SIFT, on the tasks of automatic photo categorization and geographical information retrieval.
- Open Access
- 5 August 2011
- Published by Association for Computing Machinery (ACM)
- p. 134-137
Image analysis with nonlinear adaptive dimension reduction
- 5 August 2011
- Published by Association for Computing Machinery (ACM)
- p. 134-137
Open AccessImage analysis with nonlinear adaptive dimension reduction