Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks392 from public data
- 3,666
- Bayesian CP Factorization of Incomplete Tensors with Automatic Rank Determination613
The method is characterized as a tuning parameter-free approach, which can effectively infer underlying multilinear factors with a low-rank constraint, while also providing predictive distributions over missing entries, which outperforms state-of-the-art approaches for both tensor factorization and tensor completion in terms of predictive performance.
- Dynamic visual attention: searching for coding length increments489
A dynamic visual attention model based on the rarity of features is proposed and the Incremental Coding Length (ICL) is introduced to measure the perspective entropy gain of each feature to maximize the entropy of the sampled visual features.
- Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer317
Evo-ViT is presented, a self-motivated slow-fast token evolution approach for vision transformers that can accelerate vanilla transformers of both flat and deep-narrow structures from the very beginning of the training process.
- Credit Card Fraud Detection Using Convolutional Neural Networks310
A CNN-based fraud detection framework, to capture the intrinsic patterns of fraud behaviors learned from labeled data is proposed, on which a convolutional neural network is applied to identify a set of latent patterns for each sample.
- Leaf image based cucumber disease recognition using sparse representation classification291
This work proposes a novel cucumber disease recognition approach which consists of segmenting diseased leaf images by K-means clustering, extracting shape and color features from lesion information, and classifying disease leaf images using sparse representation (SR).
- DoveNet: Deep Image Harmonization via Domain Verification273
This work contributes an image harmonization dataset iHarmony4 by generating synthesized composite images based on COCO (resp., Adobe5k, Flickr, day2night) dataset, leading to the HCOCO sub-dataset, and proposes a new deep image harmonized method DoveNet using a novel domain verification discriminator.
- 269
- 259
- 258
- Bayesian Robust Tensor Factorization for Incomplete Multiway Data239
A generative model for robust tensor factorization in the presence of both missing data and outliers that can discover the groundtruth of CP rank and automatically adapt the sparsity inducing priors to various types of outliers is proposed.
- 217
- Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow187
The approach, namely Diffusion-based Conditional Inpainting for Virtual Try-ON(DCI-VTON), effectively utilizes the power of the diffusion model, and the incorporation of the warping module helps to produce high-quality and realistic virtual try-on results.
- Feature learning from incomplete EEG with denoising autoencoder163
The Lomb-Scargle periodogram is employed to estimate the spectral power from incomplete EEG (after removing only parts contaminated by artefacts), and Denoising Autoencoder (DAE) for learning and the results show that the method can successfully decode incomplete EEG to good effect.
- MindFinder149
By scaling up the database to more than two million images, MindFinder not only helps users to easily present whatever they are imagining, but also has the potential to retrieve the most desired images in their mind.
- 137
- Neurophysiological substrates of stroke patients with motor imagery-based brain-computer interface training132
It is demonstrated that MI-based BCI training can enhance the motor function of the upper extremity for stroke patients by inducing the optimal cerebral motor functional reorganization.
- Spatio-Temporal Attention-Based Neural Network for Credit Card Fraud Detection126
The result shows that STAN performs better than other state-of-the-art baselines in both AUC and precision-recall curves and demonstrates the effectiveness of the proposed method in both detecting suspicious transactions and mining fraud patterns.
- 125
- High-Resolution Image Harmonization via Collaborative Dual Transformations120
This work proposes a high-resolution image harmonization network with Collaborative Dual Transformation (CDTNet) to combine pixel- to-pixel transformation and RGB-to-RGB transformation coherently in an end-to -end network.
- End-to-End Video Object Detection with Spatial-Temporal Transformers116
TransVOD is presented, an end-to-end video object detection model based on a spatial-temporal Transformer architecture that streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow, recurrent neural networks, relation networks.
- DESIGN OF ASSISTIVE WHEELCHAIR SYSTEM DIRECTLY STEERED BY HUMAN THOUGHTS114
An electroencephalogram (EEG)-based wheelchair which can be steered by users' own thoughts without any other involvements implies that people can steer wheelchair only by their thoughts, and may have a potential perspective in daily application for disabled people.
- Bargainnet: Background-Guided Domain Translation for Image Harmonization109
This work forms image harmonization task as background-guided domain translation, which is regulated by well-tailored triplet losses, and uses a domain code extractor to capture the background domain information to guide the foreground harmonization.
- The N-terminal Domain of NPC1L1 Protein Binds Cholesterol and Plays Essential Roles in Cholesterol Uptake108
It is demonstrated that plasma membrane-localized NPC1L1 binds exogenous cholesterol via its NTD, and facilitates the formation of NPC1 L1-flotillin-cholesterol membrane microdomains that are then internalized into cells through the clathrin-AP2 pathway.
- Knowledge Graph-based Event Embedding Framework for Financial Quantitative Investments106
A knowledge graph-based event embedding framework for quantitative investments that first extracts structured events from raw texts, and construct the knowledge graph with the mentioned entities and relations simultaneously, and leverages a joint model to merge theknowledge graph information into the objective function of anevent embedding learning model.
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 2026-10-16. 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.