QViC-MF-7B is a LoRA adapter trained on top of
LLaVA-Video-7B-Qwen2 for long-term video understanding. It introduces
Question-guided Multimodal Selective Attention (QMSA), which learns to preserve visual information related to the given question from both the current clip and past related frames stored in a context memory. The compressor and memory feedback work iteratively for each clip of the entire video, enabling strong performance on tasks that require understanding complete events (e.g., temporal ordering).
Please refer to the
official code repository for inference and evaluation scripts.
1@inproceedings{yamao2026qvicmf,
2 title={Question-guided Visual Compression with Memory Feedback for Long-Term Video Understanding},
3 author={Yamao, Sosuke and Miyahara, Natsuki and Qi, Yuankai and Takeuchi, Shun},
4 booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
5 year={2026}
6}
This model is released under the
CC-BY-NC-ND-4.0 license.
