All Stories

  1. Abstractive Visual Understanding of Multi-modal Structured Knowledge: A New Perspective for MLLM Evaluation
  2. Skynet-V1: Towards Early Warning of Video Abnormal Events via A Spatial-temporal Causal-enhanced MoE Framework
  3. EEG-MACS: Manifold Attention and Confidence Stratification for EEG-based Cross-Center Brain Disease Diagnosis under Unreliable Annotations
  4. Towards Better Chinese Spelling Check for Search Engines: A New Dataset and Strong Baseline
  5. Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling
  6. Text-based Person Search without Parallel Image-Text Data
  7. Fine-Grained Domain Adaptation for Chinese Syntactic Processing
  8. Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
  9. One Type Context Is Not Enough: Global Context-aware Neural Machine Translation
  10. Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations
  11. Search-oriented Micro-video Captioning
  12. Advancing Chinese Event Detection via Revisiting Character Information
  13. Dialogue History Matters! Personalized Response Selection in Multi-Turn Retrieval-Based Chatbots
  14. Improving Neural Machine Translation with Linear Interpolation of a Short-Path Unit
  15. Layer-Wise De-Training and Re-Training for ConvS2S Machine Translation
  16. Chinese Zero Pronoun Resolution
  17. Explicitly Modeling Word Translations in Neural Machine Translation