SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM

Documenti analoghi

• ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs
  di: Yu, An, et al.
  Pubblicazione: (2026)
• LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
  di: Lu, Weiheng, et al.
  Pubblicazione: (2024)
• MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval
  di: Cai, Weitong, et al.
  Pubblicazione: (2024)
• A New Benchmark and Model for Challenging Image Manipulation Detection
  di: Zhang, Zhenfei, et al.
  Pubblicazione: (2023)
• GranAlign: Granularity-Aware Alignment Framework for Zero-Shot Video Moment Retrieval
  di: Jeon, Mingyu, et al.
  Pubblicazione: (2026)