SD-MVSum: Script-Driven Multimodal Video Summarization Method and Datasets
cs.CV
Submitted: 2025-10-07
Updated: 2026-10-29
Comments: IEEE Access, vol.14, 2026
DOI: 10.1109/ACCESS.2026.3746362
Code: https://github.com/IDT-ITI/SD-MVSum
Project page: https://videoxum.github.io/5https://huggingface.co/sentence-transformers/clip-ViT-B-32
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Qwen3-VL Technical Report
- No Language Left Behind: Scaling Human-Centered Machine Translation
- OpenAI GPT-5 System Card
- Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos
- GPT-4 Technical Report
- Qwen2.5 Technical Report
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs