Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
video-retrieval
temporal-grounding
videosearch-r1
Instructions to use VideoSearchR1/didemo-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VideoSearchR1/didemo-stage2 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("VideoSearchR1/didemo-stage2") model = AutoModelForMultimodalLM.from_pretrained("VideoSearchR1/didemo-stage2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_jsonl": "eval/external_verified_test_temporal_grounding.check.jsonl", | |
| "num_examples": 4013, | |
| "final_retrieval": { | |
| "N": 4013, | |
| "R@1": 0.5898330426115126, | |
| "R@5": 0.8195863443807625, | |
| "R@10": 0.8778968352853227, | |
| "R@100": 0.975080986792923, | |
| "MRR": 0.6891669260789297, | |
| "mean_rank": 11.761774233740343 | |
| }, | |
| "original_retrieval": { | |
| "N": 4013, | |
| "R@1": 0.551457762272614, | |
| "R@5": 0.7931721903812609, | |
| "R@10": 0.8562172937951658, | |
| "R@100": 0.9698479940194368, | |
| "MRR": 0.6583015862230686, | |
| "mean_rank": 13.97408422626464 | |
| }, | |
| "final_temporal": { | |
| "N": 4013, | |
| "mIoU@R1": 0.26725640214899044, | |
| "IoU@0.3@R1": 0.3331672065786195, | |
| "IoU@0.5@R1": 0.3025168203339148, | |
| "IoU@0.7@R1": 0.1976077747321206 | |
| }, | |
| "turns": { | |
| "1": { | |
| "retrieval": { | |
| "N": 4013, | |
| "R@1": 0.5895838524794418, | |
| "R@5": 0.8193371542486918, | |
| "R@10": 0.8778968352853227, | |
| "R@100": 0.975080986792923, | |
| "MRR": 0.689068532671443, | |
| "mean_rank": 11.76052828307999 | |
| }, | |
| "temporal": { | |
| "N": 4013, | |
| "mIoU@R1": 0.24688095568333712, | |
| "IoU@0.3@R1": 0.30824819337154247, | |
| "IoU@0.5@R1": 0.2790929479192624, | |
| "IoU@0.7@R1": 0.18165960627959132 | |
| } | |
| }, | |
| "2": { | |
| "retrieval": { | |
| "N": 1181, | |
| "R@1": 0.2938187976291279, | |
| "R@5": 0.6375952582557155, | |
| "R@10": 0.7476714648602879, | |
| "R@100": 0.9483488569009314, | |
| "MRR": 0.4417973908465668, | |
| "mean_rank": 23.166807790008466 | |
| }, | |
| "temporal": { | |
| "N": 4013, | |
| "mIoU@R1": 0.020126256333582525, | |
| "IoU@0.3@R1": 0.02466982307500623, | |
| "IoU@0.5@R1": 0.02317468228258161, | |
| "IoU@0.7@R1": 0.01569897832045851 | |
| } | |
| }, | |
| "3": { | |
| "retrieval": { | |
| "N": 878, | |
| "R@1": 0.21867881548974943, | |
| "R@5": 0.5990888382687927, | |
| "R@10": 0.7209567198177677, | |
| "R@100": 0.9419134396355353, | |
| "MRR": 0.3830839938747691, | |
| "mean_rank": 25.518223234624145 | |
| }, | |
| "temporal": { | |
| "N": 4013, | |
| "mIoU@R1": 0.00024919013207077, | |
| "IoU@0.3@R1": 0.00024919013207077, | |
| "IoU@0.5@R1": 0.00024919013207077, | |
| "IoU@0.7@R1": 0.00024919013207077 | |
| } | |
| } | |
| } | |
| } | |