Jianran Liu
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
Research Subjects
Jianran Liu has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Wen Ji
Chinese Academy of Sciences, Institute of Computing Technology, Beijing, China
2 shared publications Chan Li
1 shared publication- Jun Yao
LonganPi Intelligent Information Technology Co., Ltd., China
1 shared publication - Rui Zhang
Institute of Computing Technology, Chinese Academy of Sciences
1 shared publication Shiping Wang
Fuzhou Univ, Fujian Prov Key Lab Network Comp & Intelligent In, Fuzhou 350000, Fujian, Peoples R China
1 shared publication- Wancai Zhang
NARI Technology Co., Ltd., Nanjing, Jiangsu, CHINA
1 shared publication
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1870-1878
Toward Generation-Centric Coding: Compressing Latents representation for TI2V Synthesis
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1870-1878
Open AccessToward Generation-Centric Coding: Compressing Latents representation for TI2V Synthesis
- Open Access
- 22 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (8) , 1-23
End-to-End Coding Based on ViT Feature for Compression Distortion
Standard image codecs are misaligned with the feature space of vision-language models like CLIP, because they are designed to exploit spatial redundancies in pixel grids. In contrast, these features are dominated by channel-wise redundancy and contain only limited spatial structure. We empirically find that ViT-B/32 and ViT-B/16 features exhibit weak yet non-negligible spatial redundancy, sufficient to benefit from light local modeling but not from the aggressive spatial downsampling commonly used in learned image codecs. Guided by this, we develop an end-to-end feature compression framework for ViT-based CLIP. A compact transform maintains essential local structure while focusing modeling capacity on channel dependencies and entropy efficiency. Beyond the codec, we present a distortion-aware post-training strategy that adjusts CLIP to compression-related perturbations. A min–max optimization objective enhances robustness against worst-case feature distortions, and a comparison with an MSE-based post-training variant highlights the benefit of the robust formulation. Experiments on Flickr30k retrieval with \(224\times 224\) inputs show that our method consistently outperforms both traditional codecs (e.g., BPG and VVC intra) and learning based codecs (e.g., MLIC++ and STF), even without post-training. Additional post-training further increases this advantage across bitrates. Additional results with ViT-B/16, latent-space visualizations, kernel-size and stride ablations, and CPU inference measurements support the effectiveness and practicality of the proposed framework.- 22 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (8) , 1-23
Open AccessEnd-to-End Coding Based on ViT Feature for Compression Distortion
Standard image codecs are misaligned with the feature space of vision-language models like CLIP, because they are designed to exploit spatial redundancies in pixel grids. In contrast, these features are dominated by channel-wise redundancy and contain only limited spatial structure. We empirically find that ViT-B/32 and ViT-B/16 features exhibit weak yet non-negligible spatial redundancy, sufficient to benefit from light local modeling but not from the aggressive spatial downsampling commonly used in learned image codecs. Guided by this, we develop an end-to-end feature compression framework for ViT-based CLIP. A compact transform maintains essential local structure while focusing modeling capacity on channel dependencies and entropy efficiency. Beyond the codec, we present a distortion-aware post-training strategy that adjusts CLIP to compression-related perturbations. A min–max optimization objective enhances robustness against worst-case feature distortions, and a comparison with an MSE-based post-training variant highlights the benefit of the robust formulation. Experiments on Flickr30k retrieval with \(224\times 224\) inputs show that our method consistently outperforms both traditional codecs (e.g., BPG and VVC intra) and learning based codecs (e.g., MLIC++ and STF), even without post-training. Additional post-training further increases this advantage across bitrates. Additional results with ViT-B/16, latent-space visualizations, kernel-size and stride ablations, and CPU inference measurements support the effectiveness and practicality of the proposed framework. - Open Access
- 7 October 2021
- Published by Tsinghua University Press in International Journal of Crowd Science
- Vol. 5 (3) , 281-292
Crowd intelligence evolution based on complex network
Purpose: In recent years, with the increase in computing power, artificial intelligence can gradually be regarded as intelligent agents and interact with humans, this interactive network has become increasingly complex. Therefore, it is necessary to model and analyze this complex interactive network. This paper aims to model and demonstrate the evolution of crowd intelligence using visual complex networks. Design/methodology/approach: This paper uses the complex network to model and observe the collaborative evolution behavior and self-organizing system of crowd intelligence. Findings: The authors use the complex network to construct the cooperative behavior and self-organizing system in crowd intelligence. Determine the evolution mode of the node by constructing the interactive relationship between nodes and observe the global evolution state through the force layout. Practical implications: The simulation results show that the state evolution map can effectively simulate the distribution, interaction and evolution of crowd intelligence through force layout and the intelligent agents’ link mode the authors proposed. Originality/value: Based on the complex network, this paper constructs the interactive behavior and organization system in crowd intelligence and visualizes the evolution process.
- 7 October 2021
- Published by Tsinghua University Press in International Journal of Crowd Science
- Vol. 5 (3) , 281-292
Open AccessCrowd intelligence evolution based on complex network
Purpose: In recent years, with the increase in computing power, artificial intelligence can gradually be regarded as intelligent agents and interact with humans, this interactive network has become increasingly complex. Therefore, it is necessary to model and analyze this complex interactive network. This paper aims to model and demonstrate the evolution of crowd intelligence using visual complex networks. Design/methodology/approach: This paper uses the complex network to model and observe the collaborative evolution behavior and self-organizing system of crowd intelligence. Findings: The authors use the complex network to construct the cooperative behavior and self-organizing system in crowd intelligence. Determine the evolution mode of the node by constructing the interactive relationship between nodes and observe the global evolution state through the force layout. Practical implications: The simulation results show that the state evolution map can effectively simulate the distribution, interaction and evolution of crowd intelligence through force layout and the intelligent agents’ link mode the authors proposed. Originality/value: Based on the complex network, this paper constructs the interactive behavior and organization system in crowd intelligence and visualizes the evolution process.
- 1 December 2019
- Published by Elsevier in Neurocomputing
- Vol. 369, 122-133
Sparse autoencoder for social image understanding
- 1 December 2019
- Published by Elsevier in Neurocomputing
- Vol. 369, 122-133
Sparse autoencoder for social image understanding
- Open Access
- 4 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 73802-73814
Supervised Learning via Unsupervised Sparse Autoencoder
- 4 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 73802-73814
Open AccessSupervised Learning via Unsupervised Sparse Autoencoder