haoshuai714's repositories
mix-generation
MixGen: A New Multi-Modal Data Augmentation
ALBEF
Code for ALBEF: a new vision-language pre-training method
chatgpt_academic
科研工作专用ChatGPT拓展,特别优化学术Paper润色体验,支持自定义快捷按钮,支持markdown表格显示,Tex公式双显示,代码显示功能完善,新增本地Python工程剖析功能/自我剖析功能
coot-videotext
COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
crossmodal-contrastive-learning
CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations, ICCV 2021
CVPR2023-3D-Occupancy-Prediction
CVPR2023-Occupancy-Prediction-Challenge
E-Com-AI
AI-Functions for cross-border e-com biz
FashionAI-KeyPointsDetectionOfApparel
FashionAI Key Points Detection using CPN model in Pytorch
FashionAI-MultiTask
这是天池FashionAI复赛用的多任务部分代码
FashionAI-retrieval
工作时的一些工具程序
FashionAI_Tianchi_2018
FashionAI Global Challenge—Attributes Recognition of Apparel—Ranked 21st solution.
GCN
GCN using TensorFlow
MapTR
[ICLR'23 Spotlight] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
metaseq
Repo for external large-scale work
similarities
Similarities: a toolkit for similarity calculation and semantic search. 语义相似度计算、匹配搜索工具包,支持文本和图像,开箱即用。
text2vec
text2vec, text to vector. 文本向量表征工具,把文本转化为向量矩阵,实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型,开箱即用。
Tianchi-FashionAI-Tag
阿里天池竞赛——服饰属性标签识别 代码
torch-single-model
3D engine with realistic physics simulation and collisions bettween different types of objects
ZeroVL
The implementation of ZeroVL