论文《HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval》笔记
0%
论文笔记 | Less is More:CLIP BERT for Video-and-Language Learning via Sparse Sampling
论文《Less is More: CLIP BERT for Video-and-Language Learning via Sparse Sampling》笔记
2021-CIKM-QQ浏览器AI算法大赛-赛后分享会笔记
CIKM-QQ浏览器 联合举办的 2021AI算法大赛，赛道一，多模态视频相似度，赛后top分享会笔记。
对比学习 Contrastive Learning
Posted on Edited on In MachineLearning Disqus:
Symbols count in article: 4.9k Reading time ≈ 12 mins.
Symbols count in article: 4.9k Reading time ≈ 12 mins.
对比学习 Contrastive Learning笔记
论文笔记 | Support-set bottlenecks for video-text representation learning
论文《Support-set bottlenecks for video-text representation learning》笔记
从VLAD到NetVLAD，再到NeXtVlad
VLAD，NetVLAD和到NeXtVlad笔记，搬运知乎
论文笔记 | HANet:Hierarchical Alignment Networks for Video-Text Retrieval
论文《HANet: Hierarchical Alignment Networks for Video-Text Retrieval》笔记
论文笔记 | VisionTransformer综述笔记
《Transformers in Vision: A Survey》部分笔记
论文写作
论文撰写 | 常用句式和词汇
一些常见的论文写作词汇和句式，拯救写作困难症
LTR精排序笔记整理[转]
看到的一篇讲排序学习的博客，转自LTR精排序
论文笔记 | Airbert: In-domain Pretraining for Vision-and-Language Navigation
论文《Airbert: In-domain Pretraining for Vision-and-Language Navigation》阅读笔记
模仿学习-Imitation-Learning
Posted on Edited on In MachineLearning Disqus:
Symbols count in article: 1.4k Reading time ≈ 3 mins.
Symbols count in article: 1.4k Reading time ≈ 3 mins.
模仿学习（Imitation Learning），属于强化学习（Reinforcement Learning）的范畴。
论文分享笔记 | vln-speaker-follower
VLN中的spaker-follower论文分享的简单记录
论文笔记 | Diagnosing the Environment Bias in Vision-and-Language Navigation
2020 IJCAI 《Diagnosing the Environment Bias in Vision-and-Language Navigation》论文笔记