license: cc-by-nc-4.0
pipeline_tag: video-text-to-text
ST-Evidence-7B
We propose Evidence-Backed Video Question Answering (E-VQA), a task where multimodal models are designed to jointly produce a semantic textual answer and associated spatiotemporal evidence. This evidence includes temporal segments and dense, tracked object segmentation masklets. A masklet is defined as a temporal sequence of object segmentation masks tracked over time.
This model is presented in the paper Evidence-Backed Video Question Answering (ECCV 2026).
ST-Evidence-7B was fine-tuned from UniPixel, which is built upon Qwen2.5-VL and SAM 2.1. UniPixel is a unified model designed to handle both video question answering and mask generation.
This was released for research purposes only, in support of the academic paper Evidence-Backed Video Question Answering.
Resources
- Repository: SalesforceAIResearch/EVQA
- Paper: Evidence-Backed Video Question Answering
- Benchmark (ST-Evidence): Salesforce/ST-Evidence-Bench
- SFT Dataset (ST-Evidence-Instruct): Salesforce/ST-Evidence-Instruct
License
CC-BY-NC 4.0
Citation
If you find this work useful for your research, please cite our paper:
@inproceedings{wang2026evidence,
title={Evidence-Backed Video Question Answering},
author={Wang, Shijie and Zhou, Honglu and Wang, Ziyang and Xu, Ran and Xiong, Caiming and Savarese, Silvio and Sun, Chen and Niebles, Juan Carlos},
booktitle={European Conference on Computer Vision (ECCV)},
year={2026}
}