All Stories

  1. Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair
  2. Explainable Deepfake Detection with Feature-robust Augmentation and Evidence-grounded Explanation Optimization
  3. Decoupled Low-Rank Prompt Subspace Learning for VLMs Adaptation in Biomedical Domain
  4. SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion
  5. Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement
  6. Investigating Domain Gaps for Indoor 3D Object Detection
  7. Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset
  8. Interact-Custom: Customized Human Object Interaction Image Generation
  9. RaT2IGen: Relation-aware Text-to-image Generation via Learnable Prompt
  10. Progressive Prototype Evolving for Dual-Forgetting Mitigation in Non-Exemplar Online Continual Learning
  11. Mitigate Catastrophic Remembering via Continual Knowledge Purification for Noisy Lifelong Person Re-Identification
  12. InsVP: Efficient Instance Visual Prompting from Image Itself
  13. SIA-OVD: Shape-Invariant Adapter for Bridging the Image-Region Gap in Open-Vocabulary Detection
  14. ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding
  15. RelScene: A Benchmark and baseline for Spatial Relations in text-driven 3D Scene Generation
  16. EOGT: Video Anomaly Detection with Enhanced Object Information and Global Temporal Dependency
  17. SPIRIT: Style-guided Patch Interaction for Fashion Image Retrieval with Text Feedback
  18. Fine-Grained Visual Prompt Learning of Vision-Language Models for Image Recognition
  19. MV-Diffusion: Motion-aware Video Diffusion Model
  20. Efficiency-optimized Video Diffusion Models
  21. Real20M: A Large-scale E-commerce Dataset for Cross-domain Retrieval
  22. CAT: a coarse-to-fine attention tree for semantic change detection
  23. Multi-Behavior Recommendation with Cascading Graph Convolution Networks
  24. LFR-GAN: Local Feature Refinement based Generative Adversarial Network for Text-to-Image Generation
  25. MKVSE: Multimodal Knowledge Enhanced Visual-Semantic Embedding for Image-Text Retrieval
  26. SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorization
  27. Learn from Unlabeled Videos for Near-duplicate Video Retrieval
  28. RCE-HIL
  29. Sequential Cross-Modal Hashing Learning via Multi-scale Correlation Mining
  30. A New Benchmark and Approach for Fine-grained Cross-media Retrieval
  31. CM-GANs