Shijian Lu

Assistant Professor

Nanyang Technological University (NTU)

Singapore

Research Interests

Explore related searches

Professors in Computer Vision

Contact this professor

ORCID

Google Scholar

About

Dr. Shijian Lu is an Assistant Professor at Nanyang Technological University in Singapore. His research interests include multimodal large language models, adversarial machine learning, and remote sensing, as evidenced by his recent articles on topics such as backdoor attacks, self-paced sampling, and object detection. He is actively contributing to advancing methodologies in deep learning and image recognition.

Shijian Lu

Research Interests

Explore related searches

Contact this professor

About

Articles (28)

Visual Instruction Tuning towards General-Purpose Multimodal Large Language Model: A Survey

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior

S2Match: Self-paced sampling for data-limited semi-supervised learning

Foundation Models for Remote Sensing and Earth Observation: A survey

HPMF: Hypergraph-guided Prototype Mining Framework for Few-Shot Object Detection in Remote Sensing Images

SyNet: A Synergistic Network for 3D Object Detection Through Geometric-Semantic-Based Multi-Interaction Fusion

Toward Model Resistant to Transferable Adversarial Examples via Trigger Activation

Towards Gradient Equalization and Feature Diversification for Long-Tailed Multi-Label Image Recognition

One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching

Self-Supervised 3D Action Representation Learning With Skeleton Cloud Colorization

Open-vocabulary object detection via debiased curriculum self-training

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking With Transformer

Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion

A Survey of Label-Efficient Deep Learning for 3D Point Clouds

Domain Adaptive LiDAR Point Cloud Segmentation With 3D Spatial Consistency

Domain Adaptive LiDAR Point Cloud Segmentation via Density-Aware Self-Training

Exploring Prototype-Anchor Contrast for Semantic Segmentation

MorphNeRF: Text-Guided 3D-Aware Editing via Morphing Generative Neural Radiance Fields

Audio-driven talking face generation with diverse yet realistic facial animations

Unsupervised Point Cloud Representation Learning With Deep Neural Networks: A Survey

Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction

Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Learning Disentangled Representation Implicitly Via Transformer for Occluded Person Re-Identification

Multimodal Image Synthesis and Editing: A Survey and Taxonomy

Prototypical Bidirectional Adaptation and Learning for Cross-Domain Semantic Segmentation

AppFuse: An Appearance Fusion Framework for Saliency Cues

GMLight: Lighting Estimation via Geometric Distribution Approximation

Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation

Collaborators (3)

Jianfei Cai

Alex Kot

Jun Liu

How do I reach out?

Meet Kite AI