Jingke Meng  孟静珂

Associate professor
 Intelligence Science and System Lab (iSEE)
School of Computer Science and Engineering
 Sun Yat-sen University, China

Email: mengjk3@mail.sysu.edu.cn / mengjke@gmail.com

Brief biography: Jingke Meng received Ph.D. degree in Computer Science and Technology from Sun Yat-sen University in 2020 (advisors: Prof. Wei-Shi Zheng). She is a recipient of the National Natural Science Foundation of China Young Scientist Fund (国家自然科学基金青年科学基金项目), the National Natural Science Foundation of China General Program (国家自然科学基金面上项目), and the General Program of the Guangdong Provincial Natural Science Foundation (广东省自然科学基金面上项目).

Research interests: My research focuses on multi-modality learning for computer vision, and embodied navigation.

News

2026

RaFM-Nav: A Risk-Aware Flow Matching Framework for Collision-Free Visual Navigation

Accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026.

Project

CoRL 2026

Group-Aware Social Navigation

GRACE helps a robot navigate human environments while respecting personal space and the shared space between people in a group.

Explore the project

IROS 2026

Risk-Aware Visual Navigation

RaFM-Nav improves visual navigation safety by modeling obstacle occupancy and aligning generated trajectories toward collision-free, open-space paths.

Explore the project

Publication [Google scholar]

GRACE: Group-Aware Socially Compliant Visual Navigation in Human Environments. Conference on Robot Learning (CoRL), 2026.

ProEdit: Inversion-based Editing From Prompts Done Right. Conference on Neural Information Processing Systems (NeurIPS), 2026.

RaFM-Nav: A Risk-Aware Flow Matching Framework for Collision-Free Visual Navigation. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026.

Distilling LLM prior to flow model for generalizable agent’s imagination in object goal navigation. Conference on Neural Information Processing Systems (NeurIPS), 2025.

monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation. IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

VIPerson: Flexibly Generating Virtual Identity for Person Re-Identification. IEEE/CVF International Conference on Computer Vision (ICCV), 2025.

Audio-Visual Collaborative Learning for Weakly Supervised Video Anomaly Detection. IEEE Transactions Multimedia (TMM), 2025.

Person De-reidentification: A Variation-guided Identity Shift Modeling. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

ChainHOI: Joint-based Kinematic Chain Modeling for Human-Object Interaction Generation. The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.

Cross-Modal Adaptive Dual Association for Text-to-Image Person Retrieval. IEEE Transactions Multimedia (TMM), 2024.

Adaptive Weight Generator for Multi-task Image Recognition by Task Grouping Prompt. IEEE Transactions Multimedia (TMM), 2024.

Rethinking Few-shot Class-incremental Learning: Learning from Yourself. European Conference on Computer Vision (ECCV), 2024.

Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024.

PRET: Planning with Directed Fidelity Trajectory for Vision and Language Navigation. European Conference on Computer Vision (ECCV), 2024.

Loc4Plan: Locating Before Planning for Outdoor Vision and Language Navigation. ACM International Conference on Multimedia (ACM MM), 2024.

EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding. European Conference on Computer Vision (ECCV), 2024.

Event-Guided Procedure Planning from Instructional Videos with Text Supervision. IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

Deep Graph Metric Learning for Weakly Supervised Person Re-Identification. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.

Weakly Supervised Person Re-Identification. IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2019.

Deep Asymmetric Video-based Person Re-Identification. Pattern Recognition (PR), 2019.