一、Python所有方向的学习路线
Python所有方向路线就是把Python常用的技术点做整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。
二、学习软件
工欲善其事必先利其器。学习Python常用的开发软件都在这里了，给大家节省了很多时间。
三、入门学习视频
我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。
网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。
一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！
E-CIR: Event-Enhanced Continuous Intensity Recovery(事件增强的连续强度恢复)
keywords: Event-Enhanced Deblurring, Video Representation
图像编辑/图像修复(Image Edit/Inpainting)
High-Fidelity GAN Inversion for Image Attribute Editing(用于图像属性编辑的高保真 GAN 反演)
Style Transformer for Image Inversion and Editing(用于图像反转和编辑的样式transformer)
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting(用于高保真图像修复的多级交互式 Siamese 过滤)
HairCLIP: Design Your Hair by Text and Reference Image(通过文本和参考图像设计你的头发)
keywords: Language-Image Pre-Training (CLIP), Generative Adversarial Networks
Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding(增量transformer结构增强图像修复与掩蔽位置编码)
keywords: Image Inpainting, Transformer, Image Generation
图像翻译(Image Translation)
Globetrotter: Connecting Languages by Connecting Images(通过连接图像连接语言)
QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation(图像翻译中对比学习的查询选择注意)
FlexIT: Towards Flexible Semantic Image Translation(迈向灵活的语义图像翻译)
Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks(探索图像到图像翻译任务中对比学习的补丁语义关系)
keywords: image translation, knowledge transfer,Contrastive learning
风格迁移(Style Transfer)
Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization(任意风格迁移和域泛化的精确特征分布匹配)
Style-ERD: Responsive and Coherent Online Motion Style Transfer(响应式和连贯的在线运动风格迁移)
CLIPstyler: Image Style Transfer with a Single Text Condition(具有单一文本条件的图像风格转移)
keywords: Style Transfer, Text-guided synthesis, Language-Image Pre-Training (CLIP)
人脸(Face)
Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?(跨模态感知者：可以从声音中收集面部几何形状吗？)
Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data(利用 3D 合成数据去除人像眼镜和阴影)
HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network(分层解析胶囊网络的无监督人脸部分发现)
FaceFormer: Speech-Driven 3D Facial Animation with Transformers(FaceFormer：带有transformer的语音驱动的 3D 面部动画)
Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning(用于鲁棒人脸对齐和地标固有关系学习的稀疏局部补丁transformer)
人脸识别/检测(Facial Recognition/Detection)
Privacy-preserving Online AutoML for Domain-Specific Face Detection(用于特定领域人脸检测的隐私保护在线 AutoML)
An Efficient Training Approach for Very Large Scale Face Recognition(一种有效的超大规模人脸识别训练方法)
人脸生成/合成/重建/编辑(Face Generation/Face Synthesis/Face Reconstruction/Face Editing)
FENeRF: Face Editing in Neural Radiance Fields(神经辐射场中的人脸编辑)
GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors(一种没有面部和 GAN 先验的生成可控人脸超分辨率方法)
Sparse to Dense Dynamic 3D Facial Expression Generation(稀疏到密集的动态 3D 面部表情生成)
keywords: Facial expression generation, 4D face generation, 3D face modeling
人脸伪造/反欺骗(Face Forgery/Face Anti-Spoofing)
Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing(通过 Shuffled Style Assembly 进行域泛化以进行人脸反欺骗)
Voice-Face Homogeneity Tells Deepfake
Protecting Celebrities with Identity Consistency Transformer(使用身份一致性transformer保护名人)
目标跟踪(Object Tracking)
Transforming Model Prediction for Tracking(转换模型预测以进行跟踪)
MixFormer: End-to-End Tracking with Iterative Mixed Attention(具有迭代混合注意力的端到端跟踪)
Unsupervised Domain Adaptation for Nighttime Aerial Tracking(夜间空中跟踪的无监督域自适应)
Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects(迭代对应几何：融合区域和深度以实现无纹理对象的高效 3D 跟踪)
paper | [code]( )
TCTrack: Temporal Contexts for Aerial Tracking(空中跟踪的时间上下文)
Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds(超越 3D 连体跟踪：点云中 3D 单对象跟踪的以运动为中心的范式)
keywords: Single Object Tracking, 3D Multi-object Tracking / Detection, Spatial-temporal Learning on Point Clouds
Correlation-Aware Deep Tracking(相关感知深度跟踪)
图像&视频检索/视频理解(Image&Video Retrieval/Video Understanding)
图像&视频检索/视频理解(Image&Video Retrieval/Video Understanding)
Bridging Video-text Retrieval with Multiple Choice Questions(桥接视频文本检索与多项选择题)
BEVT: BERT Pretraining of Video Transformers(视频Transformer的 BERT 预训练)
keywords: Video understanding, Vision transformers, Self-supervised representation learning, BERT pretraining
行为识别/动作识别/检测/分割/定位(Action/Activity Recognition)
E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition(用于以自我为中心的动作识别的运动增强事件流)
Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos(寻找变化：从未修剪的网络视频中学习对象状态和状态修改操作)
DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition(鲁棒动作识别的 Transformer 方法中的定向注意)
Self-supervised Video Transformer(自监督视频transformer)
Spatio-temporal Relation Modeling for Few-shot Action Recognition(小样本动作识别的时空关系建模)
RCL: Recurrent Continuous Localization for Temporal Action Detection(用于时间动作检测的循环连续定位)
OpenTAL: Towards Open Set Temporal Action Localization(走向开放集时间动作定位)
End-to-End Semi-Supervised Learning for Video Action Detection(视频动作检测的端到端半监督学习)
Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos(模态特定注释视频上多模态动作识别的可学习不相关模态丢失)
Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation(通过代表性片段知识传播的弱监督时间动作定位)
Colar: Effective and Efficient Online Action Detection by Consulting Exemplars(通过咨询示例进行有效且高效的在线动作检测)
keywords: Online action detection(在线动作检测)
行人重识别/检测(Re-Identification/Detection)
Cascade Transformers for End-to-End Person Search(用于端到端人员搜索的级联transformer)
图像/视频字幕(Image/Video Caption)
Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources(通过在线资源对上下文外图像进行开放域、基于内容、多模式的事实检查)
Hierarchical Modular Network for Video Captioning(用于视频字幕的分层模块化网络)
X -Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning(使用 Transformer 进行 3D 密集字幕的跨模式知识迁移)
医学影像(Medical Imaging)
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical
最低0.47元/天 解锁文章
扫一扫
1118
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
