A5073199084- Topic Modeling
- Multimodal Machine Learning Applications
- Sentiment Analysis and Opinion Mining
- Video Analysis and Summarization
- Data Stream Mining Techniques
- COVID-19 diagnosis using AI
- Advanced Image and Video Retrieval Techniques
- Physical Education and Training Studies
- Visual Attention and Saliency Detection
- Educational Technology and Pedagogy
- Generative Adversarial Networks and Image Synthesis
- Human Motion and Animation
- Spam and Phishing Detection
- Advanced Neural Network Applications
- Face recognition and analysis
- Artificial Intelligence in Healthcare
- Domain Adaptation and Few-Shot Learning
- Sports and Physical Education Research
- Industrial Vision Systems and Defect Detection
- Online Learning and Analytics
Microsoft Research (India)
2024
Microsoft Research Asia (China)
2021-2024
The defect detection task can be regarded as a realistic scenario of object in the computer vision field and it is widely used industrial field. Directly applying vanilla detector to achieve promising results, while there still exists challenging issues that have not been solved. first issue texture shift which means trained model will easily affected by unseen texture, second partial visual confusion indicates box visually similar with complete box. To tackle these two problems, we propose...
Recent works on language-guided image manipulation have shown great power of language in providing rich semantics, especially for face images. However, the other natural information, motions, is less explored. In this paper, we leverage motion information and study a novel task, animation, that aims to animate static with help languages. To better utilize both semantics motions from languages, propose simple yet effective framework. Specifically, recurrent generator extract series semantic...
Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts multimodal data available on social media platforms. Studying and investigating becomes central to various applications requires novel methods comprehensive analysis, comprehension, accurate prediction.
Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts multimodal data available on social media platforms. Studying and investigating becomes central to various applications requires novel methods comprehensive analysis, comprehension, accurate prediction. SMP Challenge an annual research activity has spurred academic exploration in this area. This paper summarizes the challenging...
Pre-training has been an emerging topic that provides a way to learn strong representation in many fields (e.g., natural language processing, computing vision). In the last few years, we have witnessed research works on multi-modal pre-training which achieved state-of-the-art performances multimedia tasks image-text retrieval, video localization, speech recognition). this workshop, aim gather peer researchers related topics for more insightful discussion. We also intend attract explore and...