CaReBench data, CaRe models and all the contrastively trained MLLMs (including InternVL2, MiniCPM-V 2.6, LLaVA NeXT Video, Qwen2-VL and Tariser).

Multimedia Computing Group-Nanjing University
university
AI & ML interests
Computer Vision; Video Understanding; Action Recognition
Recent Activity
Organization Card
We release the code, model and data of the research work done by the Multimedia Computing Group (MCG), Nanjing University🔥
Collections
1
models
28

MCG-NJU/DDT-XL-22en6de-R256
Text-to-Image
•
Updated

MCG-NJU/DDT-XL-22en6de-R512
Updated

MCG-NJU/VideoChatOnline-4B
Video-Text-to-Text
•
Updated
•
58

MCG-NJU/Tarsier-7B-RA
Updated
•
3

MCG-NJU/MiniCPM-V-2_6-RA
Updated
•
4

MCG-NJU/InternVL2-8B-RA
Updated
•
5

MCG-NJU/CaRe-7B
Updated
•
4

MCG-NJU/CaRe-7B-Stage-1
Updated
•
6

MCG-NJU/MoG
Updated
•
13
•
3

MCG-NJU/videomae-base-ssv2
Video Classification
•
Updated
•
384
•
2
datasets
7
MCG-NJU/KS-Gen
Viewer
•
Updated
•
24k
•
2
MCG-NJU/OVBench
Viewer
•
Updated
•
1.46k
•
424
•
4
MCG-NJU/CaReBench
Viewer
•
Updated
•
1k
•
184
MCG-NJU/VideoChatOnline-IT
Viewer
•
Updated
•
221k
•
209
•
2
MCG-NJU/SportsMOT
Viewer
•
Updated
•
240
•
91
•
4
MCG-NJU/SportsHHI
Preview
•
Updated
•
33
•
4
MCG-NJU/MultiSports
Updated
•
354
•
30