All Stories

  1. Fine-Grained Alignment Network for Zero-Shot Cross-Modal Retrieval
  2. Learning Event-Specific Localization Preferences for Audio-Visual Event Localization
  3. Unsupervised Readability Assessment via Learning from Weak Readability Signals
  4. Learning Robust Multi-Modal Representation for Multi-Label Emotion Recognition via Adversarial Masking and Perturbation
  5. A Consistent Dual-MRC Framework for Emotion-cause Pair Extraction