All Stories

  1. Learning Partially-Decorrelated Common Spaces for Ad-hoc Video Search
  2. ChinaOpen: A Dataset for Open-world Multimodal Learning
  3. Revisiting Code Search in a Two-Stage Paradigm
  4. Learn to Understand Negation in Video Retrieval
  5. Partially Relevant Video Retrieval
  6. Lesion Localization in OCT by Semi-Supervised Object Detection
  7. Unsupervised Domain Expansion for Visual Categorization
  8. Multi-Modal Multi-Instance Learning for Retinal Disease Recognition
  9. Improving Fake News Detection by Using an Entity-enhanced Framework to Fuse Diverse Multimodal Clues
  10. Multi-Level Visual Representation with Semantic-Reinforced Learning for Video Captioning
  11. Mining Dual Emotion for Fake News Detection
  12. Towards annotation-free evaluation of cross-lingual image captioning
  13. A W2VV++ Case Study with Automated and Interactive Text-to-Video Retrieval
  14. W2VV++
  15. Exploring Content-based Video Relevance for Video Click-Through Rate Prediction
  16. Imagination Based Sample Construction for Zero-Shot Learning
  17. Detecting Violence in Video using Subclasses
  18. Socializing the Semantic Gap
  19. Adding Chinese Captions to Images
  20. Image Tag Assignment, Refinement and Retrieval
  21. Zero-shot Image Tagging by Hierarchical Semantic Embedding
  22. Music Positioning and Annotation For Television Videos
  23. Semantic Concept Annotation For User Generated Videos Using Soundtracks
  24. Few-Example Video Event Retrieval using Tag Propagation
  25. Source Separation Improves Music Emotion Recognition
  26. Classifying tag relevance with relevant positive and negative examples
  27. Fusing concept detection and geo context for visual search