Bo Wang

ORCID: 0000-0001-8848-3497
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Video Analysis and Summarization
  • Human Pose and Action Recognition
  • Human Motion and Animation
  • Gait Recognition and Analysis
  • Multimodal Machine Learning Applications
  • Hydrological Forecasting Using AI
  • Remote-Sensing Image Classification
  • Advanced Vision and Imaging
  • Video Surveillance and Tracking Methods
  • Flood Risk Assessment and Management

Kuaishou (China)
2024

China Geological Survey
2023

As an indispensable material for animals, plants and human beings, obtaining accurate water body information rapidly is of great significance to maintain the balance ecosystems ensure normal production life beings. Due its independence time day weather conditions, synthetic aperture radar (SAR) data have been increasingly applied in extraction bodies. However, there a deal speckle noise SAR images, which seriously affect accuracy water. At present, most processing methods are filtering...

10.3390/rs15102690 article EN cc-by Remote Sensing 2023-05-22

Videos showcasing specific products are increasingly important for E-commerce. Key moments naturally exist as the first appearance of a product, presentation its distinctive features, presence buying link, etc. Adding proper sound effects (SFX) to such moments, or video decoration with SFX (VDSFX), is crucial enhancing user engaging experience. Previous work adds videos by video-to-SFX matching at holistic level, lacking ability adding moment. Meanwhile, previous studies on highlight...

10.1609/aaai.v39i5.32585 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2025-04-11

The proliferation of online short video platforms has driven a surge in user demand for editing. However, manually selecting, cropping, and assembling raw footage into coherent, high-quality remains laborious time-consuming. To accelerate this process, we focus on user-friendly new task called Video Moment Montage (VMM), which aims to accurately locate the corresponding segments based pre-provided narration text then arrange these clips create complete that aligns with descriptions....

10.48550/arxiv.2412.09276 preprint EN arXiv (Cornell University) 2024-12-12
Coming Soon ...