Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks102 from public data
- 187
- 170
- Gradient-based Parameter Estimation for a Nonlinear Exponential Autoregressive Time-series Model by Using the Multi-innovation127
A forgetting factormulti-innovation stochastic gradient algorithm derived by using the multi-inn innovation theory for improving the estimation accuracy and the effectiveness of the proposed algorithms is proved.
- Cross-SRN: Structure-Preserving Super-Resolution Network With Cross Convolution83
A hierarchical feature exploitation network to probe and preserve structural information in a multi-scale feature fusion manner, invoking a lightweight structure-preserving network named as Cross-SRN, which outperforms the state-of-the-art methods on the selected benchmark.
- Exposing video inter-frame forgery by Zernike opponent chromaticity moments and coarseness analysis71
A novel video forgery detection algorithm for detecting an inter-frame forgery based on Zernike opponent chromaticity moments and a coarseness feature analysis by matching from the coarse-to-fine models is put forward.
- 57
- Contrasting Biogeographic Patterns of Bacterial and Archaeal Diversity in the Top- and Subsoils of Temperate Grasslands45
Compared patterns and drivers of microbial alpha and beta diversity in and between topsoils and subsoils of temperate grasslands in Inner Mongolia of China are compared, finding contrasting biogeographic patterns of diversity and influencing factors for different bacterial and archaeal groups and between depths.
- 40
- Iterative Network for Image Super-Resolution39
A novel iterative super-resolution network (ISRN) is proposed on top of the iterative optimization of conventional SISR algorithm, and a feature normalization (F-Norm, FN) method to regulate the features in network is proposed.
- 35
- 31
- 28
- Rec-GPT4V: Multimodal Recommendation with Large Vision-Language Models27
This work proposes the novel reasoning scheme named Rec-GPT4V: Visual-Summary Thought (VST) of leveraging large vision-language models for multimodal recommendation and conducts comprehensive experiments across four datasets with three LVLMs, indicating the efficacy of VST.
- Effects of Soil Properties and Microbiome on Highbush Blueberry (Vaccinium corymbosum) Growth26
The growth of blueberry was significantly related to soil organic matter, soil enzyme activity and soil microbial community diversity, and the flavonoids were correlated positively with soil fungi abundance.
- Semi-online scheduling on two identical machines with a common due date to maximize total early work26
This paper proves a tight bound 6 5 for scheduling jobs with a common due date when assuming that the total processing time of all jobs, or, the optimal criterion value is known in advance.
- An Improved Tuna-YOLO Model Based on YOLO v3 for Real-Time Tuna Detection Considering Lightweight Deployment22
A Tuna-YOLO, which is a lightweight object detection network for mobile devices based on YOLOv3, which provides a basis for subsequent deployment of algorithms to mobile devices and real-time catch statistics.
- 20
- Time-aware Hyperbolic Graph Attention Network for Session-based Recommendation17
Time-aware Hyperbolic Graph Attention Network (TA-HGAT) is proposed — a novel hyperbolic graph neural network framework to build a session-based recommendation model considering temporal information that has the best performance compared to ten baseline models on two real-world datasets.
- 17
- 16
- Rising Star Forecasting Based on Social Network Analysis16
StarRank is proposed, which is an improved PageRank method to calculate the initial values of rising stars, construct the social network via explicit and implicit links, and apply the neural network to predict scholars’ rankings in the future.
- A novel video forgery detection algorithm for blue screen compositing based on 3-stage foreground analysis and tracking16
A 3-stage Foreground Analysis and Tracking algorithm (3FAT) to detect blue screen compositing and can not only rule out the distractions of noise and other moving foregrounds, but also be applied to any video format, bit rate and encoding mechanism.
- Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution15
The self-similarity is considered and a hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing and the experimental result shows that HSRNet achieves better quantitative and visual performance than other works and remits the aliasing more effectively.
- Coupling Deep Textural and Shape Features for Sketch Recognition15
This paper explicitly explores the shape properties of sketches, which has almost been neglected before in the context of deep learning, and proposes a sequential dual learning strategy that combines both shape and texture features.
- Possibilistic C-means with novel image representation for image segmentation12
The proposed VBPCM algorithm incorporates neighborhood information and uses a vector representation method to describe image pixels and outperforms the conventional PCM, obtaining uplifiting gains of 4%, 2%, and 9% in Pixel Accuracy, Mean Pixel Accuracy, and Mean Intersection over Union, respectively.
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 2026-10-14. 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.