Shijian Lu lists you as their PhD student. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeAdvisors
Works37 from public data
- Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection222
An automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks and is capable of synthesizing various defects with superior diversity and fidelity is presented.
- Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitation204
Experiments show that the proposed Meta-DETR outperforms state-of-the-art methods by large margins, and introduces a novel inter-class correlational meta-learning strategy to capture and leverage the correlation among different classes for robust and accurate few-shot object detection.
- Accelerating DETR Convergence via Semantic-Aligned Matching136
SAM-DETR is presented, a Semantic-Aligned-Matching DETR that greatly accelerates DETR's convergence without sacrificing its accuracy and is like a plug and play, which complements existing convergence solutions well yet only introduces slight computational overhead.
- Cascade EF-GAN: Progressive Facial Expression Editing With Local Focuses119
The introduction of the local focus enables the Cascade EF-GAN to better preserve identity-related features and details around eyes, noses and mouths, which further helps reduce artifacts and blurs within the generated facial images.
- Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency96
A novel and unified framework, Multi-Level Consistency Network (MLC-Net), which employs a teacher-student paradigm to generate adaptive and reliable pseudo-targets and out-performs existing state-of-the-art methods on standard benchmarks.
- DA-DETR: Domain Adaptive Detection Transformer with Information Fusion77
Inspired by the unique DETR attention mechanisms, DA-DETR is designed, a domain adaptive object detection transformer that introduces information fusion for effective transfer from a labeled source domain to an unlabeled target domain and achieves superior detection performance consistently across multiple widely adopted domain adaptation benchmarks.
- Unbalanced Feature Transport for Exemplar-based Image Translation74
A general image translation framework that incorporates optimal transport for feature alignment between conditional inputs and style exemplars in image translation and a semantic-activation normalization scheme that injects style features of exemplars into the image translation process successfully is presented.
- Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining56
A comprehensive study of CD-FSS is undertaken and reveals the necessity of a fine-tuning stage to effectively transfer the learned meta-knowledge across domains, and the overfitting risk during the naive fine-tuning due to the scarcity of novel category examples is uncovered.
- Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors53
The proposed Iterative Multi-scale Feature Aggregation (IMFA) is a generic paradigm that enables efficient use of multi-scale features in Transformer-based object detectors by exploiting sparse multi- scale features from just a few crucial locations.
- 51
- GenCo: Generative Co-training for Generative Adversarial Networks with Limited Data43
This work designs GenCo, a Generative Co-training network that mitigates the discriminator over-fitting issue by introducing multiple complementary discriminators that provide diverse supervision from multiple distinctive views in training.
- 39
- Semantic-Aligned Matching for Enhanced DETR Convergence and Multi-Scale Feature Fusion38
Semantic-Aligned-Matching DETR++ (SAM-DETR++) is designed to accelerate DETR’s convergence and improve detection performance, and can complement existing DETR convergence solutions with even better performance.
- Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking With Transformer36
This work proposes Point Tracking TRansformer (PTTR), which efficiently predicts high-quality 3D tracking results in a coarse-to-fine manner with the help of transformer operations, and designs a more advanced framework named PTTR++, which incorporates both the point-wise view and BEV representation to exploit their complementary effect in generating high-quality tracking results.
- DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention36
This work proposes DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D object detection in multi-view images, and designs a novel projective cross-attention mechanism for query-image interaction to address the limitations of existing methods.
- 27
- 23
- TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection18
TransPillars is a novel transformer-based feature aggregation technique that exploits temporal features of consecutive point cloud frames for multi-frame 3D object detection and introduces a hierarchical coarse-to-fine strategy to fuse multi-scale features progressively to effectively capture the motion of moving objects and guide the aggregation of fine features.
- 13
- On the Generalization Capacities of MLLMs for Spatial Intelligence10
It is shown that camera-awareness is not only beneficial but also a prerequisite for robust and generalizable spatial intelligence in MLLMs, indicating that camera-awareness is not only beneficial but also a prerequisite for robust and generalizable spatial intelligence in MLLMs.
- Towards Scalable Spatial Intelligence Via 2D-To-3D Data Lifting9
This work presents a scalable pipeline that converts single-view images into comprehensive, scale- and appearance-realistic 3D representations - including point clouds, camera poses, depth maps, and pseudo-RGBD - via integrated depth estimation, camera calibration, and scale calibration.
- 8
- 7
- From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model5
Camera-Centric VLA (CamVLA), a new VLA model that decouples manipulation controls from camera geometry by predicting a camera-centric end-effector action expressed in the local camera frame, and a 6-DoF hand-eye matrix relating cameras to the robot base.
- 5
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.