siyisan's repositories
LeetcodeTop
汇总各大互联网公司容易考察的高频leetcode题🔥
deeplab2
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.
AdelaiDet
AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.
STCN
Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
SOLQ
"SOLQ: Segmenting Objects by Learning Queries", SOLQ is an end-to-end instance segmentation framework with Transformer.
Group-Free-3D
Group-Free 3D Object Detection via Transformers
motiongrouping
Repository accompanying the paper: Self-supervised Video Object Segmentation by Motion Grouping. C. Yang, H. Lamdouar, E. Lu, A. Zisserman, W. Xie.
interview
2021秋招 计算机视觉算法岗面经整理——包含实习和校招等 内推整理
BASNet
Code for CVPR 2019 paper. BASNet: Boundary-Aware Salient Object Detection
TransT
Transformer Tracking (CVPR2021)
swin-transformer-pytorch
Implementation of the Swin Transformer in PyTorch.
SipMask
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)
SOLO
SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
siyisan
Config files for my GitHub profile.
SimVODIS
Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
VisTR
[CVPR2021 Oral] End-to-End Video Instance Segmentation with Transformers
Insta-DM
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency (AAAI 2021)
detr
End-to-End Object Detection with Transformers
Deformable-DETR
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
axial-attention
Implementation of Axial attention - attending to multi-dimensional data efficiently
coder2gwy
互联网首份程序员考公指南,由3位已经进入体制内的前大厂程序员联合献上。
TransTrack
Multiple-Object Tracking with Transformer
Awesome-algorithm-interview
算法工程师(人工智能CV方向)面试问题及相关资料
tartanvo
TartanVO: A Generalizable Learning-based VO