Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Multimedia Computing Group-Nanjing University

university
http://mcg.nju.edu.cn/
MCG-NJU
Activity Feed Request to join this org

AI & ML interests

Computer Vision; Video Understanding; Action Recognition

Recent Activity

Lanxingxuan  updated a dataset about 11 hours ago
MCG-NJU/Seeker-173K
yyd7  new activity about 11 hours ago
MCG-NJU/VIABench:Add video-text-to-text task category and GitHub link
Lanxingxuan  submitted a paper about 17 hours ago
VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
View all activity

Papers

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

View all Papers

Limin Wang's profile pictureZhan Tong's profile pictureRunyu He's profile pictureYiChun Yang's profile pictureGuozhen Zhang's profile pictureXinhao Li's profile picturewangshuai's profile pictureJun Zhang's profile pictureZhenpeng Huang's profile pictureYuhan Zhu's profile pictureYifan Xu's profile picturezhu chenhui's profile pictureSportsShot's profile pictureTianhui Song's profile pictureXiangyu Zeng's profile pictureKefan's profile pictureJiaming Zhang's profile pictureChunxu Liu's profile pictureHaoyue Tan's profile pictureTao Wu's profile pictureChuanyi Li's profile pictureZhiqiu Zhang's profile pictureYuandong Yang's profile picture
MCG-NJU 's papers 5
Submitted by
Limin Wang
108

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

MCG-NJU Multimedia Computing Group-Nanjing University
43 1
Submitted by
Jiaming Zhang
43

SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

MCG-NJU Multimedia Computing Group-Nanjing University
636 2
8

SAM 2++: Tracking Anything at Any Granularity

MCG-NJU Multimedia Computing Group-Nanjing University
68
-

Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation

MCG-NJU Multimedia Computing Group-Nanjing University
12
5

VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

MCG-NJU Multimedia Computing Group-Nanjing University
1.77k
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs