wusize

CAT-Seg

Official Implementation of "CAT-Seg🐱: Cost Aggregation for Open-Vocabulary Semantic Segmentation"

CLIM

[AAAI2024] Code Release of CLIM: Contrastive Language-Image Mosaic for Region Representation

CLIP

CLIPSelf

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

colorization

This is the code of the colorization project of the National Innovation Program.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

F-LMM

Code Release of F-LMM: Grounding Frozen Large Multimodal Models

multiview_pose

[ICCV2021] Code Release of Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

ovdet

[CVPR2023] Code Release of Aligning Bag of Regions for Open-Vocabulary Object Detection

wusize.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

wusize/ovdet

[CVPR2023] Code Release of Aligning Bag of Regions for Open-Vocabulary Object Detection

wusize/CLIPSelf

[ICLR2024 Spotlight] Code Release of CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

wusize/multiview_pose

[ICCV2021] Code Release of Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images

wusize/CLIM

[AAAI2024] Code Release of CLIM: Contrastive Language-Image Mosaic for Region Representation

wusize/F-LMM

Code Release of F-LMM: Grounding Frozen Large Multimodal Models

wusize/wusize.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

wusize/colorization

This is the code of the colorization project of the National Innovation Program.

wusize/CAT-Seg

Official Implementation of "CAT-Seg🐱: Cost Aggregation for Open-Vocabulary Semantic Segmentation"

wusize/CLIP

wusize/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

wusize/LLaVA-Grounding

wusize/lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

wusize/open_clip-1

An open source implementation of CLIP.

wusize/OVD_Contest

wusize/RegionCLIP

[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"

wusize/SAN

Open-vocabulary Semantic Segmentation

wusize/UNINEXT

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

wusize/Visual-CoT

Visual CoT: Unleashing Chain-of-Thought Reasoning in the Multi-Modal Language Model