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
Works113 from public data
- R1-VL: Learning to Reason with Multimodal Large Language Models via Step-Wise Group Relative Policy Optimization363
The proposed StepGRPO is designed, a new online reinforcement learning framework that enables MLLMs to self-improve reasoning ability via simple, effective and dense step-wise rewarding, and introduces R1-VL, a series of MLLMs with outstanding capabilities in step-by-step reasoning.
- Multimorbidity of cardiometabolic diseases: prevalence and risk for mortality from one million Chinese adults in a longitudinal cohort study234
The prevalence of cardiometabolic multimorbidity in a general Chinese population increased more than doubled over 5 years, indicating rapid evolution of cardiological diseases.
- Guiding Neural Machine Translation with Retrieved Translation Pieces148
This paper proposes a simple, fast, and effective method for recalling previously seen translation examples and incorporating them into the NMT decoding process, and compares favorably to another alternative retrieval-based method with respect to accuracy, speed, and simplicity of implementation.
- Using big data to improve cardiovascular care and outcomes in China: a protocol for the CHinese Electronic health Records Research in Yinzhou (CHERRY) Study133
The CHERRY Study will provide a unique platform and serve as a valuable big data resource for cardiovascular risk prediction and population management, for primary and secondary prevention of cardiovascular events in China.
- Self-Domain Adaptation for Face Anti-Spoofing119
A self-domain adaptation framework to leverage the unlabeled test domain data at inference and a meta-learning based adaptor learning algorithm is proposed using the data of multiple source domains at the training step to learn a better adaptor.
- Generative Domain-Migration Hashing for Sketch-to-Image Retrieval95
A Generative Domain-migration Hashing approach, which for the first time generates hashing codes from synthetic natural images that are migrated from sketches that can migrate sketches to their indistinguishable image counterparts while preserving the domain-invariant information of sketches.
- Spectral Unsupervised Domain Adaptation for Visual Recognition88
Spectral UDA is proposed, an effective and efficient UDA technique that works in the spectral space and can generalize across different visual recognition tasks and introduces multi-view spectral learning that learns useful unsupervised representations by maximizing mutual information among multiple ST-generated spectral views of each target sample.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- 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.
- Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation77
This work proposes a novel plug-and-play Probabilistic Uncertainty Modeling (PUM) module, which models each union region as a Gaussian distribution, whose variance measures the uncertainty of the corresponding visual content.
- LiDARCap: Long-range Markerless 3D Human Motion Capture with LiDAR Point Clouds62
Qualitative and qualitative experiments show that the LiDARHuman26M method outperforms the techniques based only on RGB images, and the experiments on the KITTI Dataset and the Waymo Open dataset show that it can be generalized to different LiDar sensor settings.
- Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors54
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.
- Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey37
This work aims to provide a systematic review of visual instruction tuning, covering the background that presents computer vision task paradigms and the development of VIT, the foundations of VIT that introduce commonly used network architectures, visual instruction tuning frameworks and objectives, and evaluation setups and tasks.
- RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation32
RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations, facilitates the development of trainable zero-shot VLN agents, showcasing the potential and challenges of advancing towards open-world navigation.
- Black-box Unsupervised Domain Adaptation with Bi-directional Atkinson-Shiffrin Memory30
BiMem is proposed, a bidirectional memorization mechanism that learns to remember useful and representative information to correct noisy pseudo labels on the fly, leading to robust black-box UDA that can generalize across different visual recognition tasks.
- 30
- 28
- 28
- Lipschitz Constrained Parameter Initialization for Deep Transformers26
This paper empirically demonstrate that a simple modification made in the official implementation, which changes the computation order of residual connection and layer normalization, can significantly ease the optimization of deep Transformers and presents a parameter initialization method that leverages the Lipschitz constraint on the initialization of Transformer parameters that effectively ensures training convergence.
- 26
- Learning to Prompt Segment Anything Models25
SSPrompt introduces spatial-semantic prompt learning (SSPrompt) that learns effective semantic and spatial prompts for better SAMs and optimize spatial prompts and semantic prompts directly over the embedding space and selectively leverage the knowledge encoded in pre-trained prompt encoders.
- 23
- Learning Source Phrase Representations for Neural Machine Translation23
This paper proposes an attentive phrase representation generation mechanism which is able to generate phrase representations from corresponding token representations and incorporates the generated phrase representations into the Transformer translation model to enhance its ability to capture long-distance relationships.
- 22
- 22
- 21
- 20
- 18
- 18
- 17
- 14
- 14
- 12
- 12
- 12
- 11
- 11
- Using Mutual Information Criterion to Design an Efficient Phoneme Set for Chinese Speech Recognition11
- 10
- 10
- 10
- 8
- 8
- 7
- 7
- 7
- 7
- 6
- Generative Reconstructive Hashing for Incomplete Video Analysis6
Generative Reconstructive Hashing is the first end-to-end framework for incomplete video analysis and outperforms the recent state-of-the-art methods by 5.44/3.22/4.82 in terms of MAPs on HMDB51/UCF101/CCV datasets, respectively.
- 6
- 6
- 5
- Learning Expressive And Generalizable Motion Features For Face Forgery Detection5
An effective sequence-based forgery detection framework based on an existing video classification method is proposed, and an alternative motion consistency block instead of the original motion features module is proposed to make the learned features more generalizable.
- Domain Adaptive Scene Text Detection via Subcategorization5
SCAST is a subcategory-aware self-training technique that mitigates the network overfitting and noisy pseudo labels in domain adaptive scene text detection effectively and generalizes well to other domain adaptive detection tasks such as vehicle detection.
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation3
A Prompt Ensemble Self-training (PEST) technique that exploits the synergy between vision and language to mitigate the domain discrepancies in image and text distributions simultaneously, which enables joint exploitation of vision andlanguage information and effective learning of image-text correspondences in the unlabelled target domains.
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Estimation and prediction of noise power based on variational Bayesian and adaptive ARMA time series1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- DNNRE: A Dynamic Neural Network for Distant Supervised Relation Extraction.–
A novel Dynamic Neural Network for Relation Extraction that can simultaneously handle the style shift problem and leverage mutual class relationships to enhance the prediction accuracy for long-tail classes is developed and can achieve superior performance over the state-of-the-art methods.
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. 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.