lxtgh Goto Github PK

followers: 530.0 following: 250.0 repos: 237.0 gists: 0.0

Name: Xiangtai Li

Type: User

Company: Nanyang Technological University

Bio: Work in Computer Vision, Deep Learning and Multi-Modal Models.

Twitter: xtl994

Location: Singapore

Blog: https://lxtgh.github.io/

My name is Xiangtai. I obtained my Ph.D. from Peking University.

I was a research fellow at MMlab@NTU, supervised by Prof. Chen Change Loy.

My published works are on my homepage, and I am open to discussing potential remote collaborations on research. Feel free to contact me via email at [email protected].

I love coding and building universal/larger/efficient models (pure vision and multi-modal large language models).

Moreover, most of my works, including the ones I have profoundly contributed to, are open-sourced on GitHub.

Xiangtai Li's Projects

octaveconv_pytorch

Pytorch implementation of newly added convolution

openpifpaf

Implementation of "PifPaf: Composite Fields for Human Pose Estimation" in PyTorch.

openpsg

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

opticalflow_visualization

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

ov-seg

This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.

ovr-cnn

A new framework for open-vocabulary object detection, based on maskrcnn-benchmark

paddleseg

End-to-end image segmentation kit based on PaddlePaddle.

panoptic-deeplab

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

panoptic-partformer

The First Unified End-to-End System for Panoptic Part Segmentation-ECCV-2022

panopticapi

COCO 2018 Panoptic Segmentation Task API (Beta version)

paper_tracking

this repo records the latest paper in Computer Vision

pcb_rpp_for_reid

person-reid-tiny-baseline

pfsegnets

PointFlow (CVPR-2021)

pkuthss

LaTeX template for dissertations in Peking University

polyphonicformer

pose-ae-train

Training code for "Associative Embedding: End-to-End Learning for Joint Detection and Grouping"

pose2seg

Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

poseflow

PoseFlow: Efficient Online Pose Tracking (BMVC'18)

poseval

Evaluation of multi-person pose estimation and tracking

preciseroipooling

Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).