| 学习笔记 | 课程 | 笔记 |
|---|---|---|
| Evidential Deep Learning | MIT 6.S191: Evidential Deep Learning and Uncertainty - YouTube | EDL |
| C++ | C++ | |
| Diffusion model | Diffusion model |
| 文章名称 | 代码 | 笔记 | |
|---|---|---|---|
| Delta Denoising Score | ICCV2023 | GitHub非官方实现 | DDS |
- 视频编辑(Diffusion Model)
| 文章名称 | 代码 | 笔记 | 阅读时间 | 复现笔记 | |
|---|---|---|---|---|---|
| Delta Denoising Score | ICCV2023 | GitHub非官方实现 | DDS | 2024.9.7 |
- 视频理解(动作识别)
| 文章名称 | 代码 | 笔记 | 阅读时间 | 复现笔记 | |
|---|---|---|---|---|---|
| CLIP-guided Prototype Modulating for Few-shot Action Recognition | IJCV2023 | GitHub | CLIP-FSAR | 2023.11.1~11.6 | |
| Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition | AAAI2023 | 无 | SloshNet | 2023.11.1~11.6 | |
| Learning Discriminative Representations for Skeleton Based Action Recognition | CVPR2023 | GitHub | FR_Head | 2023.11.1~11.6 | |
| Graph Contrastive Learning for Skeleton-based Action Recognition | ICLR2023 | GitHub | SkeletonGCL | 2023.11.1~11.6 | |
| AIM: Adapting Image Models for Efficient Video Action Recognition | ICLR2023 | GitHub | AIM | 2023.11.10 | |
| Temporal-Relational CrossTransformers for Few-Shot Action Recognition | CVPR2021 | GitHub | TRX | 2023.11.11 | |
| Few-shot Action Recognition via Intra- and Inter-Video Information Maximization | arxiv | 无 | VIM | 2023.11.15 | |
| Hybrid Relation Guided Set Matching for Few-shot Action Recognition | CVPR2022 | GitHub | HyRSM | 2023.11.17 | |
| TA2N: Two-Stage Action Alignment Network for Few-Shot Action Recognition | AAAI2022 | GitHub | TA2N | 2023.11.22 | |
| M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition | MM2023 | 无 | M3Net | 2023.11.24 | |
| Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching | ICCV2023 | 无 | GgHM | 2023.11.30 | |
| Spatio-temporal Relation Modeling for Few-shot Action Recognition | CVPR2022 | GitHub | STRM | 2023.12.2 | |
| On the Importance of Spatial Relations for Few-shot Action Recognition | MM2023 | 无 | SA-CT | 2023.12.7 |
- 小样本学习
| 文章名称 | 代码 | 笔记 | 阅读时间 | 复现笔记 | |
|---|---|---|---|---|---|
| CLIP-guided Prototype Modulating for Few-shot Action Recognition | IJCV2023 | GitHub | CLIP-FSAR | 2023.11.1~11.6 | |
| Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition | AAAI2023 | 无 | SloshNet | 2023.11.1~11.6 | |
| Few-shot Action Recognition via Intra- and Inter-Video Information Maximization | arxiv | VIM | 2023.11.15 | ||
| Hybrid Relation Guided Set Matching for Few-shot Action Recognition | CVPR2022 | GitHub | HyRSM | 2023.11.17 | |
| TA2N: Two-Stage Action Alignment Network for Few-Shot Action Recognition | AAAI2022 | GitHub | TA2N | 2023.11.22 | |
| FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning | NeurIPS2023 | GitHub | FD-Align | 2023.11.25 | |
| Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching | ICCV2023 | 无 | GgHM | 2023.11.30 | |
| Spatio-temporal Relation Modeling for Few-shot Action Recognition | CVPR2022 | GitHub | STRM | 2023.12.2 | |
| On the Importance of Spatial Relations for Few-shot Action Recognition | MM2023 | 无 | SA-CT | 2023.12.7 | |
| Focus Your Attention when Few-Shot Classification | NeurIPS2023 | 无 | FORT | 2023.12.9 |
- 多模态
| 文章名称 | 代码 | 笔记 | 阅读时间 | 复现笔记 | |
|---|---|---|---|---|---|
| CLIP-guided Prototype Modulating for Few-shot Action Recognition | arxiv | GitHub | CLIP-FSAR | 2023.11.1~11.6 | |
- 对比学习
| 文章名称 | 代码 | 笔记 | 阅读时间 | 复现笔记 | |
|---|---|---|---|---|---|
| Graph Contrastive Learning for Skeleton-based Action Recognition | ICLR2023 | GitHub | SkeletonGCL | 2023.11.1~11.6 |
- 自监督
| 文章名称 | 代码 | 笔记 | 阅读时间 | 复现笔记 | |
|---|---|---|---|---|---|
| VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training | NeurIPS2022 | Github | VideoMAE | 2023.11.9 | |
| Sequential Modeling Enables Scalable Learning for Large Vision Models | arXiv | 无 | LVM | 2023.12.5 |