TREC 2025 Proceedings
T2V_VILA_NVILA_VideoLLaMA3_v2
Submission Details
- Organization
- NII_UIT
- Track
- Adhoc Video Search
- Task
- Video Search Task
- Date
- 2025-07-28
Run Description
- Is this run manual or automatic?
- automatic
- Describe the retrieval model used.
- InternVL-G
BEiT-3
CLIP-L/14 DataComp
CLIP-H/14 Laion2B
CLIP-H/14 DFN5b
OpenAI RN101
BLIP-2
XCLIP
InternVideo2
TeachCLIP
Side4Video
CLIP4Clip
TS2Net
VILA-1.5-40B
NVILA-15B
VideoLLaMA3-7B
- Describe any external resources used.
- I retrained the following models on the MSR-VTT dataset:
- TeachCLIP
- Side4Video
- CLIP4Clip
All other models utilized will be their pre-trained versions.
- Training type:
- D
Evaluation Files
Paper