發(fā)簡信
IP屬地：陜西
-
文本生成-機(jī)器翻譯評估指標(biāo)及代碼
BLEU-4 簡介：BLEU-4（Bilingual Evaluation Understudy）：BLEU是一種常用的自動評估指標(biāo)斩祭，用于測量候...
-
Graph Neural Networks in Vision-Language Image Understanding: A Survey
論文地址：2303.03761.pdf (arxiv.org)[https://arxiv.org/pdf/2303.03761.pdf] 摘要...
-
A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Pers...論文地址：2209.13232.pdf (arxiv.org)[https://arxiv.org/pdf/2209.13232.pdf]香港大...
-
基于ESPFNet結(jié)腸息肉分割方法代碼實現(xiàn)
數(shù)據(jù)預(yù)處理 下載數(shù)據(jù)集放置在對應(yīng)文件夾 環(huán)境配置 需要預(yù)先安裝好Anaconda和Python環(huán)境问顷，建議Python3.8 啟動測試 模型結(jié)構(gòu)及...
-
Invariant grounding for video question answering 論文閱讀論文地址：https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Invariant_...
-
Video Question Answering: Datasets, Algorithms and Challenges 論文閱讀論文地址：2203.01225v1.pdf (arxiv.org)[https://arxiv.org/pdf/2203.01225v1.pdf...
-
IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition 論文閱讀論文地址：https://arxiv.org/abs/2207.12100[https://arxiv.org/abs/2207.12100] ...
-
Video Graph Transformer for Video Question Answering 論文筆記
論文地址： http://arxiv.org/pdf/2207.05342[http://arxiv.org/pdf/2207.05342]代碼...
-
Unified Contrastive Learning in Image-Text-Label Space 論文筆記論文地址：https://arxiv.org/abs/2204.03610[https://arxiv.org/abs/2204.03610]代...