Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Chun YuanSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works20 from public data
- Learning Imbalanced Data with Vision Transformers80
This paper systematically investigates the ViTs' performance in LTR and proposes LiVT to train ViTs from scratch only with LT data, and derives the unbiased extension of Sigmoid and compensates extra logit margins for deploying it to ameliorate its performance.
- 55
- HyP 2 Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval51
A novel metric learning framework with Hybrid Proxy-Pair Loss (HyP$^2$ Loss) that constructs an expressive metric space with efficient training complexity and focuses on optimizing the hypersphere space by learnable proxies and excavating data-to-data correlations of irrelevant pairs.
- 50
- Constructing an Associative Memory System Using Spiking Neural Network50
The results show that the memory neural network could memorize different targets and could recall the images it had memorized, and the neural network building process was broken into two phases: the Structure Formation Phase and the Parameter Training Phase.
- HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details36
The static detail is modeled as the linear combination of a displacement basis and the dynamic detail is modeled as the linear interpolation of two displacement maps with polarized expressions, which enable HiFace to reconstruct high-fidelity 3D shapes with animatable details.
- Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization24
Semantic-Sparse Colorization Network (SSCN) is proposed to transfer both the global image style and detailed semantic-related colors to the gray-scale image in a coarse-to-fine manner and can perfectly balance the global and local colors while alleviating the ambiguous matching problem.
- CMS-LSTM: Context Embedding and Multi-Scale Spatiotemporal Expression LSTM for Predictive Learning19
This work designs CMS-LSTM to focus on context correlations and multi-scale spatiotemporal flow with details on fine-grained locals, containing two elaborate de-signed blocks: Context Embedding and Spatiotem temporal Expression blocks.
- Towards Effective Collaborative Learning in Long-Tailed Recognition17
This article observes that the knowledge transfer between experts is imbalanced in terms of class distribution, which results in limited performance improvement of the minority classes, and proposes a re-weighted distillation loss by comparing two classifiers' predictions, which are supervised by online distillation and label annotations.
- PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference16
PRANCE is introduced, a framework which can jointly optimize activated channels and tokens on a per-sample basis, aiming to accelerate ViTs’ inference process from a unified data and architectural perspective, and introduces a novel “Result-to-Go” training mechanism that models ViTs’ inference process as a Markov decision process, significantly reducing action space and mitigating delayed-reward issues during training.
- SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization15
A novel method for efficiently searching for effective MPQ policies using a small proxy dataset instead of the large-scale dataset used for training the model, offering several advantages, including high proxy data utilization, no excessive hyper-parameter tuning, and high searching efficiency.
- Research on learning mechanism designing for equilibrated bipolar spiking neural networks10
Inspired by the ancient Chinese “Yin and Yang” Theory, an ensemble learning optimized supervised learning method is designed and tailored for this SNN structure and results show that it could gain reasonable accuracy with much more compact structure and much more sparse synapse connections.
- 7
- Correlation Analysis-Based Neural Network Self-Organizing Genetic Evolutionary Algorithm7
Based on correlation analysis of training process, self-organizing combined with genetic evolutionary algorithm is applied to improve the performance efficiency and structural efficiency of the built neural network.
- 6
- Modernn: Towards Fine-Grained Motion Details for Spatiotemporal Predictive Learning5
This paper carefully design Detail Context Block (DCB) to extract fine-grained details and improve the isolated correlation between upper context state and current input state and introduces Motion Details RNN (MoDeRNN), which outperforms existing state-of-the-art techniques qualitatively and quantitatively with lower computation loads.
- 5
- 3
- Breaking the Curse of Knowledge: Towards Effective Multimodal Recommendation Using Knowledge Soft Integration1
A knowledge soft integration framework designed to balance the utilization of multimodal features with the biases they may introduce, and to mitigate the curse of knowledge in multimodal recommendation systems is proposed.
- 1
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. 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. You will be asked to sign in.