[Doc] Update tech report link (kennymckormick#30)

.github/workflows/lint.yml

@@ -17,10 +17,6 @@ jobs:
           python-version: 3.7
       - name: Install pre-commit hook
         run: |
-          # markdownlint requires ruby >= 2.7
-          sudo apt-add-repository ppa:brightbox/ruby-ng -y
-          sudo apt-get update
-          sudo apt-get install -y ruby2.7
           pip install pre-commit
           pre-commit install
       - name: Linting

README.md

@@ -14,15 +14,16 @@ This repo is the official implementation of [PoseConv3D](https://arxiv.org/abs/2
 
 ## News
 
+- Release a [tech report](https://arxiv.org/abs/2205.09443) about this repository (**2022-05-20**).
 - Support spatial augmentations and provide a benchmark on ST-GCN++  (**2022-05-12**).
 - Support skeleton action recognition demo with GCN algorithms  (**2022-05-03**).
-- Release the skeleton annotations (generated by HRNet), config files, and pre-trained checkpoints for Kinetics-400. Note that Kinetics-400 is a large-scale dataset (even for skeleton) and you should have `memcached` and `pymemcache` installed for efficient training and testing on Kinetics-400 (**2022-05-01**).
-- Provide an example for processing a custom video dataset (we use diving48), generating 2D skeleton annotations, and using PoseC3D for skeleton-based action recognition. The tutorial for skeleton extraction part is available in [diving48_example](/examples/extract_diving48_skeleton/diving48_example.ipynb)  (**2022-04-15**).
+- Release the skeleton annotations (HRNet 2D Pose), config files, and pre-trained ckpts for Kinetics-400. K400 is a large-scale dataset (even for skeleton), you should have `memcached` and `pymemcache` installed for efficient training & testing on K400 (**2022-05-01**).
+- Provide an example (diving48) for processing a custom video dataset, generating 2D skeleton annotations, and using PoseC3D for skeleton-based action recognition. The tutorial for skeleton extraction part is available in [diving48_example](/examples/extract_diving48_skeleton/diving48_example.ipynb)  (**2022-04-15**).
 
 ## Supported Algorithms
 
 - [x] ST-GCN (AAAI 2018): https://arxiv.org/abs/1801.07455 [[MODELZOO](/configs/stgcn/README.md)]
-- [x] ST-GCN++ (PYSKL): [Tech Report Coming Soon](https://github.com/kennymckormick/pyskl/tree/main/configs/stgcn%2B%2B) [[MODELZOO](/configs/stgcn++/README.md)]
+- [x] ST-GCN++ (PYSKL, Tech Report): https://arxiv.org/abs/2205.09443 [[MODELZOO](/configs/stgcn++/README.md)]
 - [x] PoseConv3D (CVPR 2022 Oral): https://arxiv.org/abs/2104.13586 [[MODELZOO](/configs/posec3d/README.md)]
 - [x] AAGCN (TIP): https://arxiv.org/abs/1912.06971 [[MODELZOO](/configs/aagcn/README.md)]
 - [x] MS-G3D (CVPR 2020 Oral): https://arxiv.org/abs/2003.14111 [[MODELZOO](/configs/msg3d/README.md)]
@@ -77,12 +78,12 @@ For specific examples, please go to the README for each specific algorithm we su
 If you use PYSKL in your research or wish to refer to the baseline results published in the Model Zoo, please use the following BibTeX entry and the BibTex entry corresponding to the specific algorithm you used.
 
 ```BibTeX
-% Tech Report Coming Soon!
-@misc{duan2022pyskl,
-    title={PYSKL: a toolbox for skeleton-based video understanding},
-    author={PYSKL Contributors},
-    howpublished = {\url{https://github.com/kennymckormick/pyskl}},
-    year={2022}
+@misc{duan2022PYSKL,
+  url = {https://arxiv.org/abs/2205.09443},
+  author = {Duan, Haodong and Wang, Jiaqi and Chen, Kai and Lin, Dahua},
+  title = {PYSKL: Towards Good Practices for Skeleton Action Recognition},
+  publisher = {arXiv},
+  year = {2022}
 }
 ```
 

configs/stgcn++/README.md

@@ -2,16 +2,17 @@
 
 ## Introduction
 
-STGCN++ is a variant of STGCN we developed in PYSKL with some modifications in the architecture of the spatial module and the temporal module. We provide STGCN++ trained on NTURGB+D with 2D skeletons (HRNet) and 3D skeletons with **PYSKL** training setting. We provide checkpoints for four modalities: Joint, Bone, Joint Motion, and Bone Motion. We will describe the architecture of STGCN++ in the upcoming tech report.
+STGCN++ is a variant of STGCN we developed in PYSKL with some modifications in the architecture of the spatial module and the temporal module. We provide STGCN++ trained on NTURGB+D with 2D skeletons (HRNet) and 3D skeletons with **PYSKL** training setting. We provide checkpoints for four modalities: Joint, Bone, Joint Motion, and Bone Motion. The architecture of STGCN++ is described in PYSKL [tech report](https://arxiv.org/abs/2205.09443).
 
 ## Citation
 
 ```BibTeX
-@misc{duan2022pyskl,
-    title={PYSKL: a toolbox for skeleton-based video understanding},
-    author={PYSKL Contributors},
-    howpublished = {\url{https://github.com/kennymckormick/pyskl}},
-    year={2022}
+@misc{duan2022PYSKL,
+  url = {https://arxiv.org/abs/2205.09443},
+  author = {Duan, Haodong and Wang, Jiaqi and Chen, Kai and Lin, Dahua},
+  title = {PYSKL: Towards Good Practices for Skeleton Action Recognition},
+  publisher = {arXiv},
+  year = {2022}
 }
 ```