Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks67 from public data
- 496
- Vision-Based Anti-UAV Detection and Tracking307
A clear and simple tracking algorithm combined with detection that inherits the detector’s high precision is proposed, thus providing a new attempt at UAV tracking using the proposed DUT Anti-UAV dataset.
- Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline298
A large-scale benchmark with high diversity for visible-thermal UAV tracking (VTUAV), including 500 sequences with 1.7 million high-resolution (1920* 1080 pixels) frame pairs is constructed, and a coarse-to-fine attribute annotation is provided, where frame-level attributes are provided to exploit the potential of challenge-specific trackers.
- Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking206
This study develops a novel late fusion method to infer the fusion weight maps of both RGB and thermal (T) modalities and proposes a tracker switcher to switch the appearance and motion trackers flexibly.
- 130
- 37
- 35
- Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem33
This work introduces the Agentic Learning Ecosystem (ALE), a foundational infrastructure that optimizes the production pipeline for agentic model and releases ROME, an open-source agent grounded by ALE and trained on over one million trajectories.
- CloudSim 7G : An Integrated Toolkit for Modeling and Simulation of Future Generation Cloud Computing Environments31
Cloud simulators are an essential tool for academic and industrial researchers, to investigate the effectiveness of novel algorithms and mechanisms in large‐scale scenarios.
- Riker31
This work develops a new PQA framework (named Riker) that substantially outperforms previous state-of-the-art methods in both synthetic settings and real user evaluations, and compares keyword representations from Riker and those from attention mechanisms popularly used for deep neural networks through case studies, showing that the former are more effective and interpretable.
- Charge Prediction by Constitutive Elements Matching of Crimes29
A novel method named Constitutive Elements-guided Charge Prediction (CECP), which mimics human's charge identification process to extract potential instances of CEs and generate predictions accordingly and shows the superiority of CECP over competitive baselines.
- 21
- Leveraging the Power of Data Augmentation for Transformer-based Tracking19
This paper explores the impact of general data augmentations on transformer-based trackers via systematic experiments, and proposes two data augmentation methods customized for tracking, including a token-level feature mixing augmentation strategy which enables the model against challenges like background interference.
- 19
- Fundus Image Generation and Classification of Diabetic Retinopathy Based on Convolutional Neural Network13
A new conditional generative adversarial network with a self-attention mechanism named SACGAN is proposed to augment the number of diabetic retinopathy fundus images, thereby addressing the problems of insufficient and imbalanced data samples and gradient-weighted class activation mapping is utilized to prove the proposed model’s interpretability.
- Online Filtering Training Samples for Robust Visual Tracking12
An optimization module named MetricNet is proposed for online filtering training samples that applies a matching network containing the classification and distance branches, and uses multiple metric methods for different type samples to improve the tracking performance.
- An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective12
This work proposes an end-to-end deep neural network framework, which is trained by a novel group-level objective function that directly optimizes the answer triggering performance and penalizes three potential types of error.
- 11
- 10
- Video Annotation for Visual Tracking via Selection and Refinement10
A new framework to facilitate bounding box annotations for video sequences is presented, which investigates a selection-and-refinement strategy to automatically improve the preliminary annotations generated by tracking algorithms.
- 8
- Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning7
This work bridges the sim-to-real gap through a semi-virtual environment, including a real robot and real-time aspects, while utilizing a simulated sensor and obstacles to enable environment randomization and automated episode resetting.
- Texture Classification Using Scattering Statistical and Cooccurrence Features6
New approaches for texture features extraction using scattering transform derived from subbands of the scattering decomposition and original images and used for classification for the four datasets containing 20, 30, 112, and 129 texture images.
- 5
- Exploiting Lightweight Hierarchical ViT and Dynamic Framework for Efficient Visual Tracking5
The core innovation of HiT lies in its Bridge Module, which connects lightweight transformers to the tracking framework, enhancing feature representation quality, and a training-free acceleration method based on the dynamic routing architecture of DyHiT is introduced.
- Efficient Motion Prompt Learning for Robust Visual Tracking5
A lightweight and plug-and-play motion prompt tracking method that can be easily integrated into existing vision-based trackers to build a joint tracking framework leveraging both motion and vision cues, thereby achieving robust tracking through efficient prompt learning.
- 5
- Adversarial Training for Code Retrieval with Question-Description Relevance Regularization5
This work proposes adversarial learning for code retrieval, that is regularized by question-description relevance, such that a generated code snippet should contribute more to the code retrieval training loss, only if its paired natural language description is predicted to be less relevant to the user given question.
- 5
- 4
- 4
- High-Performance Mining of COVID-19 Open Research Datasets for Text Classification and Insights in Cloud Computing Environments4
This paper developed a system utilising the Aneka Platform as a Service middleware with parallel processing and multi-cloud capability to accelerate the data process pipeline and article categorising process using machine learning on a hybrid cloud.
- 4
- 4
- 4
- 3
- Recursive Least Squares Policy Control with Echo State Network3
This work proposes two novel policy control algorithms, ES NRLS-Q and ESNRLS-Sarsa, and presents a new mean-approximation method for updating the RLS autocorrelation matrix.
- 3
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- Efficient Mini-batch Training for Echo State Networks1
A novel mini-batch RLS (MRLS) algorithm is proposed to prevent overfitting in the ESN training, and an L 1 regularization method is suggested for MRLS to make ESNs more suitable for time-varying tasks.
- 1
- Noise Fuzzy Learning Vector Quantization1
Noise fuzzy learning vector quantization, called NFLVQ, uses the membership values from GNC as learning rates and clusters data containing noisy data better than FLVQ.
- 1
- –
- Less Repetition, Less Energy Cost: A Reinforcement Learning-Based Multiagent Energy-Saving Autonomous Exploration System–
This work proposes a distributed Multiagent Energy-saving Autonomous Exploration System (MEAES), and devise the consumption-exploration-balanced training framework (CEBF), which guides agents to transform from lazy exploration to energy-saving exploration strategies through dynamic reward shaping.
- –
- Learning‐Based Classification of B‐ and T‐Cell Lymphoma on Histopathological Images: A Multicenter Study–
These findings underscore the effectiveness of advanced CNN models in improving diagnostic precision while reducing dependency on manual staining and interpretation, and the integration of AI‐driven classification can provide valuable support for pathologists.
- –
- Generalized Hierarchical Co-Saliency Learning for Label-Efficient Tracking–
This work proposes a weakly supervised tracking method based on co-saliency learning, which can be flexibly integrated into various tracking frameworks to reduce annotation costs and further enhance the target representation in current search images.
- –
- –
- Application of Image Recognition Based on Deep Learning Model–
This paper can speed up the operation efficiency of the model, eliminate over-fitting, and improve the recognition accuracy by adding batch normalization layers to the neural network.
- –
- –
- –
- –
- –
- Improved Inter-Cluster Separation Algorithm–
It is claimed that IICS overcomes the noise sensitivity problem of ICS and the coincident clusters problem of possibilistic c-means (PCM) clustering and does not depend on the parameters that exist in IPCM.
- –
- –
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.