heyichang
Follow
Stars
Full retriever for art and metadata in http://wikiart.org/
Image-embodied Knowledge Representation Learning (IJCAI-2017)
[Paper][ISWC 2021] Zero-shot Visual Question Answering using Knowledge Graph
MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering
This is the official repository for Retrieval Augmented Visual Question Answering
Binary VQA test set for testing Visual Question Answering Models
[ECCV 2024 Oral] DriveLM: Driving with Graph Visual Question Answering
OpenKG-ORG / OpenRichpedia
Forked from z1514/OpenRichpedia东南大学多模态知识图谱-OpenRichpedia工程文件
Repository for VisualSem: a high-quality knowledge graph to support research in vision and language.
Several data modalities for KBs (visual, numerical, temporal, etc.)
A PyTorch reimplementation of bottom-up-attention models
Compact Trilinear Interaction for Visual Question Answering (ICCV 2019)
Efficiently computes derivatives of NumPy code.
A collection of resources on multimodal knowledge graph, including datasets, papers and contests.
PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.
北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。
刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.
Optimized primitives for collective multi-GPU communication
An updated PyTorch implementation of hengyuan-hu's version for 'Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering'
Qengineering / caffe
Forked from weiliu89/caffeCaffe-ssd: a fast open framework for deep learning adapted for Raspberry Pi, Jetson Nano and Ubuntu. Fixed for cuDNN 8
The official GitHub page for the survey paper "A Survey of Large Language Models".
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.