Downloads · 30 days
16
12% of all-time downloads
charades-stage1
VideoSearchR1/charades-stage1
charades-stage1 is a video-text-to-text model from VideoSearchR1. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This is the Stage 1 VideoSearch-R1 checkpoint trained for Charades-STA, presented in the paper VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement.
All-time downloads
138
Public
Parameters
2.1B
4.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors4.3 GB · 99%
Parameter types
How the weights are stored.
BF162.1B · 99%
Base models
Model card
From the Hugging Face model README
VideoSearch-R1 Charades-STA Stage 1
This is the Stage 1 VideoSearch-R1 checkpoint trained for Charades-STA, presented in the paper VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement.
- Project Page: https://mlvlab.github.io/VideoSearch-R1/
- GitHub Repository: https://github.com/mlvlab/VideoSearch-R1
Usage
Use with the VideoSearch-R1 codebase:
bash scripts/data_construct/download_preextracted_data.bash charades
EVAL_GPUS=0 bash scripts/inference/inference.bash charades --checkpoint VideoSearchR1/charades-stage1
Citation
@inproceedings{lee2026videosearchr1,
title = {VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement},
author = {Lee, Seohyun and Choi, Seoung and Ko, Dohwan and Kim, Jongha and Kim, Hyunwoo J.},
booktitle = {European Conference on Computer Vision (ECCV)},
year = {2026}
}
- Task
- Video-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Jun 20, 2026
- Updated
- Jul 3, 2026