Rui Liu
Rui Liu has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Fang Liu
City University of Hong Kong
2 shared publications - Huankang Guan
Huawei Research
2 shared publications - Jinpeng Chen
Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China
2 shared publications - Xudong Lu
Chinese University of Hong Kong
2 shared publications - Yang Bo
Huawei Research
2 shared publications - Bin Zou
The University of Hong Kong, Hong Kong, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-14
PhotoMaster: Learning Holistic Capture-Time Decisions for Guided Photography Reshooting
Capturing compelling photographs requires sequential capture-time decisions. However, existing guidance methods operate at the image level rather than modeling the decision process that diagnoses photographic dimensions (e.g., camera position, lighting) and resolves them into executable reshooting actions, offering limited actionable support for novices. We present PhotoMaster, a decision-driven multimodal framework for capture-time photography guidance. To model the decision-making process, we propose the Photography Decision Taxonomy (PDT) that defines photographic dimensions for diagnosing novice-captured photos and maps them to executable actions. To make this intuitive, PhotoMaster pairs these executable actions with a rendered visual target that previews the expected outcome. To learn this decision space, we introduce a two-fold data engine: Forward Decision Transfer distills professional photographers' decisions from masterworks to casual shots, while Decision Inversion applies inverse capture decisions via camera-controllable world models, collectively yielding over 230K PDT-annotated triplets. Evaluations demonstrate PhotoMaster's capability to produce expert-aligned diagnoses and highly preferred visual references, while a real-world user study confirms that novices achieve significantly better captures using our framework.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-14
Open AccessPhotoMaster: Learning Holistic Capture-Time Decisions for Guided Photography Reshooting
Capturing compelling photographs requires sequential capture-time decisions. However, existing guidance methods operate at the image level rather than modeling the decision process that diagnoses photographic dimensions (e.g., camera position, lighting) and resolves them into executable reshooting actions, offering limited actionable support for novices. We present PhotoMaster, a decision-driven multimodal framework for capture-time photography guidance. To model the decision-making process, we propose the Photography Decision Taxonomy (PDT) that defines photographic dimensions for diagnosing novice-captured photos and maps them to executable actions. To make this intuitive, PhotoMaster pairs these executable actions with a rendered visual target that previews the expected outcome. To learn this decision space, we introduce a two-fold data engine: Forward Decision Transfer distills professional photographers' decisions from masterworks to casual shots, while Decision Inversion applies inverse capture decisions via camera-controllable world models, collectively yielding over 230K PDT-annotated triplets. Evaluations demonstrate PhotoMaster's capability to produce expert-aligned diagnoses and highly preferred visual references, while a real-world user study confirms that novices achieve significantly better captures using our framework.
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6321-6330
Disentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 6321-6330
Open AccessDisentangling Instruction Influence in Diffusion Transformers for Parallel Multi-Instruction-Guided Image Editing
- 4 October 2026
- Published by Springer Nature
- p. 75-93
X-Stream: Exploring MLLMs as Multiplexers for Multi-stream Understanding
- 4 October 2026
- Published by Springer Nature
- p. 75-93
X-Stream: Exploring MLLMs as Multiplexers for Multi-stream Understanding
- 14 September 2026
- Published by Springer Nature
- p. 57-74
GuideMe: Multi-domain Task Guidance and Intervention in Streaming Video
- 14 September 2026
- Published by Springer Nature
- p. 57-74
GuideMe: Multi-domain Task Guidance and Intervention in Streaming Video
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 711-7113
Identity-Based Multi-replicas Data Public Audit Scheme
When users outsource the data to the remote cloud servers, they lose physical control of data while gaining storage convenience and cannot ensure the integrity of cloud data. Therefore, a series of auditing schemes were proposed to solve the problem of cloud data integrity verification. However, the existing public auditing scheme mainly focuses on a single replica, and the dynamic update of data requires a large computational overhead. Aiming at these problems, a new identity-based multi-replicas public auditing scheme is proposed by using homomorphic authentication labels and multi-branch path tree. The analysis results show that the scheme can effectively audit the integrity of cloud data. Compared with similar schemes, it has higher computational efficiency
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 711-7113
Identity-Based Multi-replicas Data Public Audit Scheme
When users outsource the data to the remote cloud servers, they lose physical control of data while gaining storage convenience and cannot ensure the integrity of cloud data. Therefore, a series of auditing schemes were proposed to solve the problem of cloud data integrity verification. However, the existing public auditing scheme mainly focuses on a single replica, and the dynamic update of data requires a large computational overhead. Aiming at these problems, a new identity-based multi-replicas public auditing scheme is proposed by using homomorphic authentication labels and multi-branch path tree. The analysis results show that the scheme can effectively audit the integrity of cloud data. Compared with similar schemes, it has higher computational efficiency
- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7984-7993
Conditional Adversarial Generative Flow for Controllable Image Synthesis
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions. This is because the potential distribution of image conditions is hard to measure precisely from its latent variable $z$. In this paper, based on modeling a joint probabilistic density of an image and its conditions, we propose a novel flow-based generative model named conditional adversarial generative flow (CAGlow). Instead of disentangling attributes from latent space, we blaze a new trail for learning an encoder to estimate the mapping from condition space to latent space in an adversarial manner. Given a specific condition $c$, CAGlow can encode it to a sampled $z$, and then enable robust conditional image synthesis in complex situations like combining person identity with multiple attributes. The proposed CAGlow can be implemented in both supervised and unsupervised manners, thus can synthesize images with conditional information like categories, attributes, and even some unknown properties. Extensive experiments show that CAGlow ensures the independence of different conditions and outperforms regular Glow to a significant extent.- 1 June 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7984-7993
Conditional Adversarial Generative Flow for Controllable Image Synthesis
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions. This is because the potential distribution of image conditions is hard to measure precisely from its latent variable $z$. In this paper, based on modeling a joint probabilistic density of an image and its conditions, we propose a novel flow-based generative model named conditional adversarial generative flow (CAGlow). Instead of disentangling attributes from latent space, we blaze a new trail for learning an encoder to estimate the mapping from condition space to latent space in an adversarial manner. Given a specific condition $c$, CAGlow can encode it to a sampled $z$, and then enable robust conditional image synthesis in complex situations like combining person identity with multiple attributes. The proposed CAGlow can be implemented in both supervised and unsupervised manners, thus can synthesize images with conditional information like categories, attributes, and even some unknown properties. Extensive experiments show that CAGlow ensures the independence of different conditions and outperforms regular Glow to a significant extent.- 1 July 2018
- Published by International Joint Conferences on Artificial Intelligence
- p. 3449-3455
Discrete Factorization Machines for Fast Feature-based Recommendation
User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 107, results in expensive storage and computational cost. This prohibits fast recommendation especially on mobile applications where the computational resource is very limited. In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation. DFM binarizes the real-valued model parameters (e.g., float32) of every feature embedding into binary codes (e.g., boolean), and thus supports efficient storage and fast user-item score computation. To avoid the severe quantization loss of the binarization, we propose a convergent updating rule that resolves the challenging discrete optimization of DFM. Through extensive experiments on two real-world datasets, we show that 1) DFM consistently outperforms state-of-the-art binarized recommendation models, and 2) DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss.
- 1 July 2018
- Published by International Joint Conferences on Artificial Intelligence
- p. 3449-3455
Discrete Factorization Machines for Fast Feature-based Recommendation
User and item features of side information are crucial for accurate recommendation. However, the large number of feature dimensions, e.g., usually larger than 107, results in expensive storage and computational cost. This prohibits fast recommendation especially on mobile applications where the computational resource is very limited. In this paper, we develop a generic feature-based recommendation model, called Discrete Factorization Machine (DFM), for fast and accurate recommendation. DFM binarizes the real-valued model parameters (e.g., float32) of every feature embedding into binary codes (e.g., boolean), and thus supports efficient storage and fast user-item score computation. To avoid the severe quantization loss of the binarization, we propose a convergent updating rule that resolves the challenging discrete optimization of DFM. Through extensive experiments on two real-world datasets, we show that 1) DFM consistently outperforms state-of-the-art binarized recommendation models, and 2) DFM shows very competitive performance compared to its real-valued version (FM), demonstrating the minimized quantization loss.
- Open Access
- 4 August 2017
- Published by Association for Computing Machinery (ACM)
- p. 325-334
Discrete Content-aware Matrix Factorization
Precisely recommending relevant items from massive candidates to a large number of users is an indispensable yet computationally expensive task in many online platforms (e.g., Amazon.com and Netflix.com). A promising way is to project users and items into a Hamming space and then recommend items via Hamming distance. However, previous studies didn't address the cold-start challenges and couldn't make the best use of preference data like implicit feedback. To fill this gap, we propose a Discrete Content-aware Matrix Factorization (DCMF) model, 1) to derive compact yet informative binary codes at the presence of user/item content information; 2) to support the classification task based on a local upper bound of logit loss; 3) to introduce an interaction regularization for dealing with the sparsity issue. We further develop an efficient discrete optimization algorithm for parameter learning. Based on extensive experiments on three real-world datasets, we show that DCFM outperforms the state-of-the-arts on both regression and classification tasks.
- 4 August 2017
- Published by Association for Computing Machinery (ACM)
- p. 325-334
Open AccessDiscrete Content-aware Matrix Factorization
Precisely recommending relevant items from massive candidates to a large number of users is an indispensable yet computationally expensive task in many online platforms (e.g., Amazon.com and Netflix.com). A promising way is to project users and items into a Hamming space and then recommend items via Hamming distance. However, previous studies didn't address the cold-start challenges and couldn't make the best use of preference data like implicit feedback. To fill this gap, we propose a Discrete Content-aware Matrix Factorization (DCMF) model, 1) to derive compact yet informative binary codes at the presence of user/item content information; 2) to support the classification task based on a local upper bound of logit loss; 3) to introduce an interaction regularization for dealing with the sparsity issue. We further develop an efficient discrete optimization algorithm for parameter learning. Based on extensive experiments on three real-world datasets, we show that DCFM outperforms the state-of-the-arts on both regression and classification tasks.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 1-6
Risk sources analysis method on aero engine IFSD based on big data
In the case of rapid development of domestic civil aviation, they are investigated in detail that the trend of In Flight Shut-down (IFSD) of aero engines, the composition of domestic aero engines and the existing analysis method on IFSD. Refer to the Total Quality Management method, the analysis tree of risk sources in IFDS cased is established. And the data-driven method on risk sources analysis in aero engine IFSD is given, based on the grey relation grade. The real data of IFSD cases are used and Type A aero engine is chosen to certify the effectiveness and correctness of the method presented in this paper combined the data in Service Difficulty Report system.
- 1 October 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4, 1-6
Risk sources analysis method on aero engine IFSD based on big data
In the case of rapid development of domestic civil aviation, they are investigated in detail that the trend of In Flight Shut-down (IFSD) of aero engines, the composition of domestic aero engines and the existing analysis method on IFSD. Refer to the Total Quality Management method, the analysis tree of risk sources in IFDS cased is established. And the data-driven method on risk sources analysis in aero engine IFSD is given, based on the grey relation grade. The real data of IFSD cases are used and Type A aero engine is chosen to certify the effectiveness and correctness of the method presented in this paper combined the data in Service Difficulty Report system.
- 1 March 2013
- Published by Binary Information Press in Journal of Information and Computational Science
- Vol. 10 (4) , 1025-1034
Global and Local Information Based Spherical Marginal Fisher Analysis for Face Recognition
- 1 March 2013
- Published by Binary Information Press in Journal of Information and Computational Science
- Vol. 10 (4) , 1025-1034
Global and Local Information Based Spherical Marginal Fisher Analysis for Face Recognition