Skip to content

@MCG-NJU Multimedia Computing Group, Nanjing University

Change the repository type filter

All

    Repositories list

    95 repositories

    • Video-o3

      Public
      Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
      Python
      •0•58•0•0•Updated Feb 16, 2026Feb 16, 2026

    • LongVPO

      Public
      [NeurIPS 2025] LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
      Python
      •0•2•0•0•Updated Feb 4, 2026Feb 4, 2026

    • AMD

      Public
      [CVPR 2024] Asymmetric Masked Distillation for Pre-Training Small Foundation Models
      action-recognitionvideo-understandingdistillationself-supervised-learningtemporal-action-detectionfoundation-modelssmall-modelscvpr2024
      Python
      •1•18•0•0•Updated Jan 11, 2026Jan 11, 2026

    • SportsVideo

      Public
      HTML
      •0•2•0•0•Updated Jan 3, 2026Jan 3, 2026

    • SteadyDancer

      Public
      SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation
      Python
      •
      Apache License 2.0
      •36•577•6•0•Updated Dec 23, 2025Dec 23, 2025

    • Sora2-mini

      Public
      UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions
      Python
      •2•43•2•0•Updated Dec 16, 2025Dec 16, 2025

    • SAM2-Plus

      Public
      SAM 2++: Tracking Anything at Any Granularity
      Python
      •
      Apache License 2.0
      •5•54•0•0•Updated Dec 15, 2025Dec 15, 2025

    • UniAVGen

      Public
      HTML
      •0•4•0•0•Updated Dec 14, 2025Dec 14, 2025

    • MobileViCLIP

      Public
      [ICCV 2025] MobileViCLIP: An Efficient Video-Text Model for Mobile Devices
      Python
      •
      MIT License
      •1•16•4•0•Updated Dec 11, 2025Dec 11, 2025

    • PixNerd

      Public
      [ICLR 2026] PixNerd: Pixel Neural Field Diffusion
      Python
      •
      MIT License
      •5•170•5•0•Updated Dec 10, 2025Dec 10, 2025

    • FlowBack

      Public
      [AAAI 2026] Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
      computer-visionimage-generationnormalizing-flowsflow-matching
      Python
      •
      Apache License 2.0
      •0•13•1•0•Updated Dec 9, 2025Dec 9, 2025

    • RGE

      Public
      Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval
      Python
      •0•10•0•0•Updated Nov 29, 2025Nov 29, 2025

    • steadydancer-web

      Public
      JavaScript
      •0•2•0•0•Updated Nov 25, 2025Nov 25, 2025

    • StreamForest

      Public
      [NeurIPS 2025 Spotlight] StreamForest: Efficient Online Video Understanding with Persistent Event Memory
      Python
      •
      Apache License 2.0
      •4•148•5•0•Updated Nov 4, 2025Nov 4, 2025

    • JointFormer

      Public
      [TPAMI] JointFormer: A Unified Framework with Joint Modeling for Video Object Segmentation
      Python
      •0•11•0•0•Updated Oct 21, 2025Oct 21, 2025

    • MeMOTR

      Public
      [ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking
      trackingcomputer-visiondeep-learningmulti-object-tracking
      Python
      •
      MIT License
      •18•216•4•0•Updated Oct 15, 2025Oct 15, 2025

    • MotionRAG

      Public
      [NeurIPS 2025] MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
      Python
      •
      MIT License
      •4•22•3•0•Updated Oct 9, 2025Oct 9, 2025

    • VideoChat-Online

      Public
      [CVPR 2025] Online Video Understanding: OVBench and VideoChat-Online
      Python
      •5•89•10•0•Updated Oct 7, 2025Oct 7, 2025

    • ArbInterp-Web

      Public
      JavaScript
      •0•0•0•0•Updated Oct 2, 2025Oct 2, 2025

    • CycleACR

      Public
      [TPAMI-2025] CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection
      Python
      •
      Apache License 2.0
      •0•3•0•0•Updated Sep 11, 2025Sep 11, 2025

    • DDT

      Public
      DDT: Decoupled Diffusion Transformer
      Python
      •17•362•5•0•Updated Aug 22, 2025Aug 22, 2025

    • MOTIP

      Public
      [CVPR 2025] Multiple Object Tracking as ID Prediction
      trackingcomputermulti-object-trackingmultiple-object-tracking
      Python
      •
      Apache License 2.0
      •38•475•9•0•Updated Aug 20, 2025Aug 20, 2025

    • VideoEval

      Public
      VideoEval: Comprehensive Benchmark Suite for Low-Cost Evaluation of Video Foundation Model
      Python
      •0•14•0•0•Updated Jul 31, 2025Jul 31, 2025

    • Video-DC

      Public
      Python
      •
      Apache License 2.0
      •1•11•1•0•Updated Jul 30, 2025Jul 30, 2025

    • CaReBench

      Public
      A Fine-grained Benchmark for Video Captioning and Retrieval
      Python
      •1•26•4•0•Updated Jul 16, 2025Jul 16, 2025

    • NeuralSolver

      Public
      [ICML 2025] Differentiable Solver Search for Fast Diffusion Sampling
      Python
      •
      MIT License
      •0•21•1•0•Updated Jul 7, 2025Jul 7, 2025

    • p-MoD

      Public
      [ICCV 2025] p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
      Python
      •
      Apache License 2.0
      •2•43•1•0•Updated Jun 26, 2025Jun 26, 2025

    • DEQDet

      Public
      [ICCV 2023] Deep Equilibrium Object Detection
      Jupyter Notebook
      •1•27•1•0•Updated Jun 18, 2025Jun 18, 2025

    • SORCE

      Public
      Small Object Retrieval in Complex Environments (SORCE)
      Python
      •1•5•0•0•Updated Jun 2, 2025Jun 2, 2025

    • DMM

      Public
      DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
      Python
      •4•47•3•0•Updated Apr 27, 2025Apr 27, 2025