Owner

MCG-NJU

75 indexed repositories · View on GitHub

VideoMAE
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Python · 1795 stars
SteadyDancer
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

Python · 645 stars
MOTIP
[CVPR 2025] Multiple Object Tracking as ID Prediction

Python · 565 stars
MixFormer
[CVPR 2022 Oral & TPAMI 2024] MixFormer: End-to-End Tracking with Iterative Mixed Attention

Python · 540 stars
EMA-VFI
[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio

Python · 501 stars
SparseBEV
[ICCV 2023 & TPAMI 2026] SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos

Python · 471 stars
SparseOcc
[ECCV 2024] Fully Sparse 3D Occupancy Prediction & RayIoU Evaluation Metric

Python · 443 stars
VideoChat3
A generalist video MLLM built for fine-grained motion, long-form reasoning, temporal grounding, and online proactive response.

Python · 424 stars
DDT
[CVPR 2026] DDT: Decoupled Diffusion Transformer

Python · 420 stars
TDN
[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition

Python · 386 stars
MOC-Detector
[ECCV 2020] Actions as Moving Points

Python · 271 stars
CamLiFlow
[CVPR 2022 Oral & TPAMI 2023] Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion

Python · 252 stars
AdaMixer
[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector

Jupyter Notebook · 237 stars
MeMOTR
[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

Python · 235 stars
SportsMOT
[ICCV 2023] SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes

Python · 229 stars
MixFormerV2
[NeurIPS 2023] MixFormerV2: Efficient Fully Transformer Tracking

Python · 229 stars
PixNerd
[ICLR 2026] PixNerd: Pixel Neural Field Diffusion

Python · 188 stars
VFIMamba
[NeurIPS 2024] VFIMamba: Video Frame Interpolation with State Space Models

Python · 155 stars
MultiSports
[ICCV 2021] MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions

Python · 138 stars
Video-o3
[ICML 2026] Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning

Python · 135 stars
55 more repositories live on View on GitHub

Beginner friendly Everything

Open All

Verify evals on Papers with Code Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/VideoMAE-Action-Detection#8 · Opened Sep 14, 2026
Verify evals on Papers with Code Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

MCG-NJU/VideoMAE#139 · Opened Sep 14, 2026
Verify evals on Papers with Code Open

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

MCG-NJU/SparseBEV#100 · Opened Sep 14, 2026
Verify evals on Papers with Code Open

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

MCG-NJU/PixNerd#12 · Opened Sep 14, 2026
Verify evals on Papers with Code Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/EMA-VFI#30 · Opened Aug 28, 2026
Verify evals on Papers with Code Open

Difficulty 3/5 1-2 days Newbie friendliness 48/100

MCG-NJU/VFIMamba#16 · Opened Aug 28, 2026
Verify evals on Papers with Code Open

Difficulty 3/5 1-2 days Newbie friendliness 48/100

MCG-NJU/MixFormer#116 · Opened Aug 28, 2026
Replace deprecated config.torch_dtype with config.dtype in llava.py Open

Difficulty 1/5 Under an hour Newbie friendliness 90/100

MCG-NJU/VideoChat3#6 · Opened Aug 28, 2026
Request: release of the 100-sample test set used in Table 1 evaluation Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/Sora2-mini#3 · Opened Aug 27, 2026
codalab 提交的时候出现 Submissions have been disabled by admins Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MCG-NJU/SportsMOT#24 · Opened Aug 11, 2026
size=224以及feat_sz=96应该怎么训练 Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

MCG-NJU/MixFormerV2#55 · Opened Aug 6, 2026
Only the policy on a target LIBERO Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

MCG-NJU/CoMo#1 · 1 comment · Opened Aug 6, 2026
期待尽早开源🥺 Open

Difficulty 5/5 Over a week Newbie friendliness 10/100

MCG-NJU/UniAVGen#1 · Opened Aug 5, 2026
model Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MCG-NJU/MIMFlow#2 · Opened Jul 21, 2026
Verify evals on Papers with Code Open

Difficulty 2/5 1-3 hours Newbie friendliness 48/100

MCG-NJU/VideoChat3#1 · 2 comments · Opened Jul 17, 2026
报告一些关于 RayIoU 的小错误，希望指标计算细节社区能统一一下（已⭐️） Open

Difficulty 4/5 3-5 days Newbie friendliness 48/100

MCG-NJU/SparseOcc#71 · 2 comments · Opened Jul 15, 2026
[Will be FIXED] A minor bug in the returned matching indices. Open

bug in planning

Difficulty 3/5 1-2 days Newbie friendliness 55/100

MCG-NJU/MOTIP#90 · 2 comments · Opened Jul 6, 2026
Release MIMFlow model checkpoints on Hugging Face Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MCG-NJU/MIMFlow#1 · Opened Jun 30, 2026
Release SpikeTAD on Hugging Face Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/SpikeTAD#1 · Opened Jun 11, 2026
Clarification on the annotation files used for evaluation Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/Video-o3#11 · 1 comment · Opened Jun 9, 2026
Unable to generate videos longer than ~5 seconds due to GPU OOM Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

MCG-NJU/SteadyDancer#36 · 1 comment · Opened Jun 9, 2026
Process hangs Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

MCG-NJU/Video-o3#8 · 4 comments · Opened May 31, 2026
Some questions on text encoder Open

Difficulty 1/5 Under an hour Newbie friendliness 25/100

MCG-NJU/MobileViCLIP#5 · Opened May 28, 2026
Query Regarding Evaluation Open

Difficulty 1/5 Under an hour Newbie friendliness 25/100

MCG-NJU/StreamForest#12 · Opened May 22, 2026
The frequency setting of the DCT-based Positional Encoding Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

MCG-NJU/PixNerd#11 · 2 comments · 1 reaction · Opened May 10, 2026
Request for Data Construction Pipeline Scripts Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MCG-NJU/Video-o3#7 · 1 comment · Opened May 6, 2026
有人试过其他更好的LC模型吗 Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MCG-NJU/SparseBEV#98 · Opened Apr 30, 2026
vit_L checkpoint on ssv2 Open

Difficulty 4/5 3-5 days Newbie friendliness 30/100

MCG-NJU/VideoMAE#138 · Opened Apr 28, 2026
missing self.blocks adaLN-Zero Open

Difficulty 4/5 3-5 days Newbie friendliness 38/100

MCG-NJU/DDT#14 · Opened Apr 23, 2026
FLOPS count vs FID Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/DDT#13 · Opened Apr 21, 2026
A request for Kefan22/TS_Retrieval Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MCG-NJU/StreamForest#11 · 1 comment · Opened Apr 20, 2026
OOM of CPU Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/Video-o3#5 · 3 comments · Opened Apr 1, 2026
导出onnx模型报错 Open

Difficulty 3/5 1-2 days Newbie friendliness 68/100

MCG-NJU/MixFormerV2#54 · Opened Mar 27, 2026
尊敬的作者 Open

Difficulty 3/5 1-2 days Newbie friendliness 20/100

MCG-NJU/MixSort#22 · Opened Mar 22, 2026
Character Reversal Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/SteadyDancer#35 · Opened Mar 19, 2026
raise RuntimeError(f"You should not use 'two stage'.") Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MCG-NJU/MOTIP#86 · 1 comment · Opened Mar 19, 2026
Is 48GB of VRAM sufficient for using the model? And if I want to use the code from this repository to use bf16 or fp8 models instead of ComfyUI, is that possible? Open

Difficulty 5/5 Over a week Newbie friendliness 10/100

MCG-NJU/SteadyDancer#34 · Opened Mar 19, 2026
video file Open

documentation good first issue

Difficulty 1/5 Under an hour Newbie friendliness 35/100

MCG-NJU/Video-o3#4 · 5 comments · 1 reaction · Opened Mar 18, 2026
How long does the entire RL training take? Open

Difficulty 4/5 3-5 days Newbie friendliness 35/100

MCG-NJU/Video-o3#3 · 1 comment · Opened Mar 17, 2026
MixFomerV2 Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

MCG-NJU/MixSort#20 · Opened Mar 16, 2026
Streaming Bench Accuracy Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

MCG-NJU/StreamForest#10 · 1 comment · Opened Mar 16, 2026
RL Training RuntimeError in vLLM rollout when videos have different frame lengths Open

documentation good first issue help wanted

Difficulty 4/5 3-5 days Newbie friendliness 38/100

MCG-NJU/Video-o3#2 · 5 comments · Opened Mar 12, 2026
slow-fast Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

MCG-NJU/SparseBEV#97 · Opened Mar 11, 2026
Loading MixFormerV2-S Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

MCG-NJU/MixFormerV2#53 · Opened Mar 2, 2026
Will the training code be open sourced？ Open

Difficulty 5/5 Over a week Newbie friendliness 20/100

MCG-NJU/RGE#1 · Opened Mar 1, 2026
problem with output (resolution of pose) Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

MCG-NJU/SteadyDancer#32 · 2 comments · Opened Feb 20, 2026
hi 是否有支持wan2.2的计划 Open

Difficulty 5/5 Over a week Newbie friendliness 10/100

MCG-NJU/SteadyDancer#31 · Opened Feb 19, 2026
Example workflow 04 up to date ? Open

Difficulty 3/5 1-2 days Newbie friendliness 35/100

MCG-NJU/SteadyDancer#30 · Opened Feb 9, 2026
您好，我想请问一下，我使用TrackEval评估BDD100K的val数据集，得到的指标是：“HOTA(↑) DetA(↑) AssA(↑)”这些，论文里的：“mTETA mHOTA mLocA mAssocA mAssA“指标是使用什么方法进行评估的啊？ Open

Difficulty 3/5 1-2 days Newbie friendliness 25/100

MCG-NJU/MeMOTR#38 · 1 comment · Opened Jan 30, 2026
关于下载openvid-1k数据集，解压之后没有openvid-1m.parquet文件 Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

MCG-NJU/MotionRAG#4 · 1 comment · Opened Jan 29, 2026

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

MCG-NJU

Showing the newest 100

Get new issues in your inbox