All Stories

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