Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks37 from public data
- Transformer Tracking1,446
This work presents a novel attention-based feature fusion network, which effectively combines the template and search region features solely using attention and presents a Transformer tracking method based on the Siamese-like feature extraction backbone, the designed attention- based fusion mechanism, and the classification and regression head.
- The impact of gamification in educational settings on student learning outcomes: a meta-analysis337
Findings from a meta-analysis that integrated the empirical, quantitative research on gamification in formal educational settings on student learning outcomes are provided by examining the overall effect size, identifying which gamification design elements were used, and determining under what circumstances gamification works.
- 130
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge78
This work proposes StreamChat, a training-free framework for streaming video reasoning and conversational interaction that leverages a novel hierarchical memory system to efficiently process and compress video features over extended sequences, enabling real-time, multi-turn dialogue.
- 77
- High-Performance Transformer Tracking76
To determine whether a better feature fusion method exists than correlation, a novel attention-based feature fusion network, inspired by the transformer, is presented and effectively combines the template and search region features using attention mechanism.
- A meta-analysis on the influence of gamification in formal educational settings on affective and behavioral outcomes69
The purpose of this study was to examine the effects of gamification used in formal educational settings on student affective and behavioral outcomes and examined contextual elements as moderators, including the discipline, student level, and publication source.
- Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking56
This work proposes a novel asymmetric Siamese tracker named AsymTrack, which devise an efficient template modulation mechanism to unidirectional inject crucial cues into the search features, and design an object perception enhancement module that integrates abstract semantics and local details to overcome the limited representation in lightweight tracker.
- DCPT: Darkness Clue-Prompted Tracking in Nighttime UAVs39
A novel architecture called Darkness Clue-Prompted Tracking (DCPT) is proposed that achieves robust UAV tracking at night by efficiently learning to generate darkness clue prompts and efficiently injects anti-dark knowledge without extra modules.
- Tracking with Human-Intent Reasoning39
This work proposes a tracker called TrackGPT, which is capable of performing complex reasoning-based tracking, which uses LVLM to understand tracking instructions and condense the cues of what target to track into referring embeddings and generates the tracking results based on the embeddings.
- 37
- 35
- Self-regulated learning strategies and student video engagement trajectory in a video-based asynchronous online course: a Bayesian latent growth modeling approach35
Student video engagement was found to increase over time and student management strategies contributed to the upward change, and it was found that the growth of engagement predicted student achievement in the course.
- 32
- Multimodal Zero-Shot Hateful Meme Detection29
Results show that TAME can significantly improve the state-of-the-art hateful meme classification methods’ performance in seen and unseen settings, and the proposed framework is a novel deep generative framework that can improve existing hateful memes classification models' performance in detecting unseen types of hateful memes.
- AutoChart: A Dataset for Chart-to-Text Generation Task25
This paper proposes AutoChart, a large dataset for the analytical description of charts, which aims to encourage more research into this important area and offers a novel framework that generates the charts and their analytical description automatically.
- YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection23
YOLO-Master, a novel YOLO-like framework that introduces instance-conditional adaptive computation for RTOD, is proposed through a Efficient Sparse Mixture-of-Experts (ES-MoE) block that dynamically allocates computational resources to each input according to its scene complexity.
- Personalized Recommendation in the Adaptive Learning System: The Role of Adaptive Testing Technology20
The results showed that the experimental group students achieved significantly higher scores and demonstrated higher learning abilities than the control group students, suggesting that the adapted testing technology that is being used for personalized recommendation is effective in improving learning performance.
- 15
- The influence of the multimedia and modality principles on the learning outcomes, satisfaction, and mental effort of college students with and without dyslexia9
A reverse modality effect for students with dyslexia who performed better than their peers without dyslexian in Onscreen Text conditions is shown, and studies that could inform the eventual design of adaptive and personalized multimedia learning solutions for learners with Dyslexia are suggested.
- 8
- UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain Retrieval7
The UCDR-Adapter is proposed, which enhances pre-trained models with adapters and dynamic prompt generation through a two-phase training strategy and dynamically adapts to evolving data distributions, enhancing both flexibility and generalization.
- Concerning rural undergraduates’ knowledge absorption in large-scale online learning: inspired by three digital divides and beyond7
The findings imply that the public sector should be concerned about the diversity of the digital divide and proposes a new framework (access-skills-absorption-outcome) that will complement current models of the digital divide.
- 7
- 6
- An Analysis of Online and Hybrid EdD Programs in Educational Technology6
The structure of these programs, curriculum (core courses, specialized courses, research courses, dissertation credits) and professional outcomes are presented, and areas of consideration for others embarking on creating online or hybrid EdD programs and those engaged in improving their existing programs are provided.
- Are we ready for undergraduate educational technology programs? Lessons and experience from student satisfaction in China4
The overall undergraduate EdTech students’ satisfaction with their programs has much room for improvement, and suggestions for the program satisfaction improvement are provided.
- 2
- Does participating in online communities enhance the effectiveness and experience of micro-learning? Evidence from a randomized control trial2
Findings have implications for course designers and researchers aiming to enhance micro-learning through online learning communities, and for course designers and researchers aiming to enhance micro-learning through online learning communities.
- 2
- ViMIC 2.0: an updated database of human disease-related viral mutations, integration sites, and multi-omics data1
The database provides comprehensively curated data on virus mutations, viral integration sites, and multi-omics datasets related to human diseases and serves as a user-friendly, up-to-date, and well-maintained resource for the virology research community.
- Unleashing Vision-Language Semantics for Deepfake Video Detection–
This work proposes VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection, and substantially outperforms state-of-the-art methods at both frame and video levels.
- InCTRLv2: Generalist Residual Models for Few-Shot Anomaly Detection and Segmentation–
This work introduces InCTRLv2, a novel few-shot Generalist Anomaly Detection and Segmentation (GADS) framework that significantly extends the previously proposed GAD model, InCTRL, and introduces two new, complementary perspectives of anomaly perception under a dual-branch framework.
- –
- –
- Predicting Users’ Age Range in Micro-blog Network–
This report presents the work on WISE 2013 Challenge Track II to predict the age range of Weibo users, and shows that ensemble classifiers based on AdaBoost achieves the best prediction results.
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 2026-10-11. 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.