Xu Zheng

Orcid: 0000-0003-4008-8951

Affiliations:
  • AI Thrust, Hong Kong University of Science and Technology (HKUST), Guangzhou, China


According to our database1, Xu Zheng authored at least 22 papers between 2022 and 2025.

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

2025
Distilling efficient Vision Transformers from CNNs for semantic segmentation.
Pattern Recognit., 2025

2024
Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentation.
CoRR, 2024

EIT-1M: One Million EEG-Image-Text Pairs for Human Visual-textual Recognition and More.
CoRR, 2024

OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All.
CoRR, 2024

360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes.
CoRR, 2024

GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation.
CoRR, 2024

EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition.
CoRR, 2024

ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More.
CoRR, 2024

UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All.
CoRR, 2024

Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation.
CoRR, 2024

Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024

EventBind: Learning a Unified Representation to Bind Them All for Event-Based Open-World Understanding.
Proceedings of the Computer Vision - ECCV 2024, 2024

Learning Modality-Agnostic Representation for Semantic Segmentation from Any Modalities.
Proceedings of the Computer Vision - ECCV 2024, 2024

Semantics, Distortion, and Style Matter: Towards Source-Free UDA for Panoramic Segmentation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
E-CLIP: Towards Label-efficient Event-based Open-world Understanding by CLIP.
CoRR, 2023

Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks.
CoRR, 2023

A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Transformer-CNN Cohort: Semi-supervised Semantic Segmentation by the Best of Both Students.
CoRR, 2022

All One Needs to Know about Priors for Deep Image Restoration and Enhancement: A Survey.
CoRR, 2022


  Loading...