LI Minghan's starred repositories
make-a-video-pytorch
Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch
LaGOT
We enrich the LaSOT validation set with annotations of additional object tracks, up to 10 object tracks per video in total. Tracks consist of precise bounding box annotations of moving objects. Annotations are provided at 10 fps. The original LaSOT validation set annotations and video can be downloaded from: https://vision.cs.stonybrook.edu/~lasot/
pytracking
Visual tracking library based on PyTorch.
VIPOSeg-Benchmark
The benchmark for "Video Object Segmentation in Panoptic Wild Scenes".
Ask-Anything
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
LLMTest_NeedleInAHaystack
Doing simple retrieval from LLM models at various context lengths to measure accuracy
ControlVideo
[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"
LanguageBind
【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
Video-LLaVA
PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models
gigagan-pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs