Jun Liu

Orcid: 0000-0002-6985-8238

Affiliations:
  • Tencent Youtu Lab, Shenzhen, China


According to our database1, Jun Liu authored at least 37 papers between 2018 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Large-Scale Universal Defect Generation: Foundation Models and Datasets.
CoRR, April, 2026

Learning Trajectory-Aware Multimodal Large Language Models for Video Reasoning Segmentation.
CoRR, March, 2026

AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison.
CoRR, March, 2026

ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning.
CoRR, February, 2026

Towards fine-grained vision-language alignment for few-shot anomaly detection.
Pattern Recognit., 2026

AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection.
CoRR, December, 2025

DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning.
CoRR, October, 2025

BoxSeg: Quality-Aware and Peer-Assisted Learning for Box-supervised Instance Segmentation.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
Cross-Modal Alternating Learning With Task-Aware Representations for Continual Learning.
IEEE Trans. Multim., 2024

Spider: Any-to-Many Multimodal LLM.
CoRR, 2024

DualAnoDiff: Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation.
CoRR, 2024

Enhancing Multi-Class Anomaly Detection via Diffusion Refinement with Dual Conditioning.
CoRR, 2024

SoftPatch: Unsupervised Anomaly Detection with Noisy Data.
CoRR, 2024

Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation.
Proceedings of the Computer Vision - ECCV 2024, 2024

Learning Task-Aware Language-Image Representation for Class-Incremental Object Detection.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

MatchDet: A Collaborative Framework for Image Matching and Object Detection.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Clustered-patch Element Connection for Few-shot Learning.
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Instance and Category Supervision are Alternate Learners for Continual Learning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Rethinking Gradient Projection Continual Learning: Stability/Plasticity Feature Space Decoupling.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection.
CoRR, 2022

Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Hierarchical Walking Transformer for Object Re-Identification.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Not All Pixels Are Matched: Dense Contrastive Learning for Cross-Modality Person Re-Identification.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Towards Continual Adaptation in Industrial Anomaly Detection.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

HDNet: A Hierarchically Decoupled Network for Crowd Counting.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2022

tSF: Transformer-Based Semantic Filter for Few-Shot Learning.
Proceedings of the Computer Vision - ECCV 2022, 2022

Surface Representation for Point Clouds.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021
Single-Shot Face Anti-Spoofing for Dual Pixel Camera.
IEEE Trans. Inf. Forensics Secur., 2021

LVIS Challenge Track Technical Report 1st Place Solution: Distribution Balanced and Boundary Refinement for Large Vocabulary Instance Segmentation.
CoRR, 2021

Learning Inner-Group Relations on Point Clouds.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2018
First Demonstration of Machine-Learning-Based Self-Optimizing Optical Networks (SOON) Running on Commercial Equipment.
Proceedings of the European Conference on Optical Communication, 2018


  Loading...