Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks143 from public data
- ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding443
ULIP is introduced to learn a unified representation of image, text, and 3D point cloud by pre-training with object triplets from the three modalities, using a pre-trained vision-language model that has already learned a common visual and textual space by training with massive image-text pairs.
- Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral Images231
Experimental results demonstrated that the SDAE pretraining in conjunction with the LR fine-tuning and classification (SDAE_LR) can achieve higher accuracies than the popular support vector machine (SVM) classifier.
- PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report161
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.
- LRLSHMDA: Laplacian Regularized Least Squares for Human Microbe–Disease Association prediction123
A semi-supervised computational model of Laplacian Regularized Least Squares for Human Microbe–Disease Association (LRLSHMDA) is developed by introducing Gaussian interaction profile kernel similarity calculation and LaPlacian regularized least squares classifier to achieve better prediction performance relative to the previous model.
- Open Vocabulary Object Detection with Pseudo Bounding-Box Labels122
This work proposes a method to automatically generate pseudo bounding-box annotations of diverse objects from large-scale image-caption pairs that leverages the localization ability of pre-trained vision-language models to generate pseudo Bounding- box labels and then directly uses them for training object detectors.
- RFDT: A Rotation Forest-based Predictor for Predicting Drug-Target Interactions Using Drug Structure and Protein Sequence Information112
Experimental results demonstrate that the proposed method is effective in the prediction of DTI, and can provide assistance for new drug research and development.
- 99
- Camera Placement Considering Occlusion for Robust Motion Capture82
A quality metric that estimates the error caused by both image resolution and occlusion is proposed that reflects the dynamic self-occlusion of the target and can be applied toward the automatic design of more accurate and robust tracking systems.
- 79
- Range Scaling Global U-Net for Perceptual Image Enhancement on Mobile Devices54
This paper presents a novel deep learning based approach—the Range Scaling Global U-Net (RSGUNet)—for perceptual image enhancement on mobile devices that learns a global feature vector as well as a novel range scaling layer that alleviate artifacts in the enhanced images.
- An occlusion metric for selecting robust camera configurations38
This work introduces a configuration quality metric based on the likelihood of dynamic occlusion, which is extensively evaluated experimentally using hundreds of different camera configurations and found to correlate very closely with the actual probability of feature occlusions.
- GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation33
GlueGen is proposed, which applies a newly proposed GlueNet model to align features from single-modal or multi-modal encoders with the latent space of an existing T2I model, allowing for flexible and efficient integration of new functionality into existing T2I models and sheds light on X-to-image (X2I) generation.
- Mask-Free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations27
This work learns both base and novel categories from pseudo-mask annotations generated by the vision-language model in a weakly supervised manner using the proposed Mask-free OVIS pipeline, which significantly improves the mAP scores on the MS-COCO dataset and OpenImages dataset.
- Identification of self-interacting proteins by exploring evolutionary information embedded in PSI-BLAST-constructed position specific scoring matrix25
A novel computational approach called RVMBIGP that combines the Relevance Vector Machine (RVM) model and Bi-gram probability (BIGP) to predict SIPs based on protein sequence is proposed and may provide a cost-effective alternative for Sips identification.
- 24
- 23
- Distributed image understanding with semantic dictionary and semantic expansion22
This paper proposes a semantic dictionary to describe the images on the level of semantic, which characterizes the probability distribution between visual appearances and semantic concepts, and the learning procedure of semantic dictionary is formulated into a minimization optimization problem.
- On Nonparametric Image Registration22
This article suggests solving the IR problem locally, by first studying the local properties of a mapping transformation, and proposes a local smoothing method that does not require any parametric form or other global regularity conditions on the mapping transformation.
- Total restrained domination in graphs22
The best possible upper and lower bounds for @c"t"r(G) are determined, those graphs achieving these bounds are characterized and the best possible lower bounds are found.
- Feature based image registration using non-degenerate pixels21
A new type of image features is studied, which has the following two properties: they should be easy to identify by a computer algorithm so that the entire feature extraction procedure is computer automatic, and they should provide proper information to approximate the geometric matching transformation accurately.
- 20
- Moving Target Shadow Analysis and Detection for ViSAR Imagery18
The frame rate and the shadow feature are analyzed, the velocity limitation of ViSAR moving target shadow detection is discussed and the expression of velocity limitation is quantitatively given.
- 17
- 17
- Spectral 3D reconstruction of impressionist oil paintings based on macroscopic OCT imaging15
This work presents a hybrid scanning platform combined with an effective algorithm for real-time sampling and artifact removal to achieve macroscopic OCT (macro-OCT) imaging and spectral 3D reconstruction of impressionist style oil paintings.
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 2026-10-15. 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.