Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
AI & ML interests
Computer Vision; Video Understanding; Action Recognition
Recent Activity
View all activity
Papers
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
Organization Card
We release the code, model and data of the research work done by the Multimedia Computing Group (MCG), Nanjing University🔥
Generalist Video Temporal Grounding with Multimodal LLMs
-
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper • 2607.17423 • Published • 100 -
MCG-NJU/TimeLens2-93K
Viewer • Updated • 71.4k • 7.08k • 13 -
MCG-NJU/TimeLens2-8B
Video-Text-to-Text • 9B • Updated • 1.28k • 17 -
MCG-NJU/TimeLens2-4B
Video-Text-to-Text • 4B • Updated • 1.35k • 13
Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction
Generalist Video Temporal Grounding with Multimodal LLMs
-
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
Paper • 2607.17423 • Published • 100 -
MCG-NJU/TimeLens2-93K
Viewer • Updated • 71.4k • 7.08k • 13 -
MCG-NJU/TimeLens2-8B
Video-Text-to-Text • 9B • Updated • 1.28k • 17 -
MCG-NJU/TimeLens2-4B
Video-Text-to-Text • 4B • Updated • 1.35k • 13
models 59
MCG-NJU/OneStreamer-4B
Video-Text-to-Text • 4B • Updated • 40 • 6
MCG-NJU/VideoChat3-4B-Stage2
4B • Updated • 28 • 2
MCG-NJU/VideoChat3-4B-Stage1
4B • Updated • 49 • 2
MCG-NJU/VideoChat3-4B
Video-Text-to-Text • 4B • Updated • 2.69k • 27
MCG-NJU/I3D-ViT
Image Feature Extraction • 0.4B • Updated • 231 • 12
MCG-NJU/TimeLens2-2B-SFT
Video-Text-to-Text • 2B • Updated • 34 • 2
MCG-NJU/TimeLens2-4B-SFT
Video-Text-to-Text • 4B • Updated • 62 • 3
MCG-NJU/TimeLens2-8B-SFT
Video-Text-to-Text • 9B • Updated • 51 • 5
MCG-NJU/TimeLens2-2B
Video-Text-to-Text • 2B • Updated • 467 • 8
MCG-NJU/TimeLens2-4B
Video-Text-to-Text • 4B • Updated • 1.35k • 13
datasets 22
MCG-NJU/OneStreamer-1M
Preview • Updated • 198 • 3
MCG-NJU/VideoChat3-Training-Data-Annotations
Updated • 618 • 2
MCG-NJU/VideoChat3-OL617k
Viewer • Updated • 4.09k • 2.68k • 13
MCG-NJU/VideoChat3-Academic2M
Viewer • Updated • 19.2k • 1.55k • 24
MCG-NJU/VideoChat3-LV116k
Viewer • Updated • 8.07k • 17.9k • 15
MCG-NJU/TimeLens2-93K
Viewer • Updated • 71.4k • 7.08k • 13
MCG-NJU/Seeker-173K
Preview • Updated • 201 • 5
MCG-NJU/VIABench
Preview • Updated • 584 • 3
MCG-NJU/ODV-Bench
Viewer • Updated • 6.35k • 214
MCG-NJU/StreamForest-Annodata
Updated • 188 • 1