Token Masked Pose Transformers Are Efficient Learners
Source abstract
Abstract
In recent years, Transformer has achieved remarkable results in the field of computer vision, with its built-in attention layers effectively modeling global dependencies in images by transforming image features into token for... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Augmented Reality Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (50)
Show source-provided references
1. Human pose as compositional tokens
2. BCCLR: a skeleton-based action recognition with graph convolutional network combining behavior dependence and context clues
3. Realtime multi-person 2D pose estimation using part affinity fields
4. A hybrid multi-person fall detection scheme based on optimized YOLO and ST-GCN
5. A survey on deep learning-based 2D human pose estimation models
6. Squirrel search optimization with deep convolutional neural network for human pose estimation
7. DeepPose: human pose estimation via deep neural networks
8. Convolutional pose machines
9. CSIT: channel spatial integrated transformer for human pose estimation10.1049/ipr2.12850 ↗
10. Towards accurate multi-person pose estimation in the wild
11. Xiao · Computer vision–ECCV 2018 · 2018 · 47210.1007/978-3-030-01231-1_29 ↗
12. A robustly optimized BERT pre-training approach with post-training10.1007/978-3-030-84186-7_31 ↗
13. Radford A, Narasimhan K, Salimans T, Sutskever I. Improving language understanding by generative pre-training. 2018 [cited 2024 Dec 10]. Available from: https://www.mikecaptain.com/resources/pdf/GPT-1.pdf.
14. Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, et al. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv:1910.13461. 2019.10.18653/v1/2020.acl-main.703 ↗
15. Exploring the limits of transfer learning with a unified text-to-text transformer
16. Zhang S, Roller S, Goyal N, Artetxe M, Chen M, Chen S, et al. OPT: open pre-trained transformer language models. arXiv:2205.01068. 2022.
17. HRFormer: high-resolution vision transformer for dense predict
18. Xu Y, Zhang J, Zhang Q, Tao D. ViTPose: simple vision transformer baselines for human pose estimation. arXiv:2204.12484. 2022.
19. Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, et al. An image is worth 16 × 16 words: transformers for image recognition at scale. arXiv:2010.11929. 2020.
20. Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y. Transformer in transformer. arXiv:2103.00112. 2021.
21. Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers
22. Zhu X, Su W, Lu L, Li B, Wang X, Dai J. Deformable detr: deformable transformers for end-to-end object detection. arXiv:2010.04159. 2020.
23. TokenPose: learning keypoint tokens for human pose estimation
24. Masked autoencoders are scalable vision learners
25. Bao H, Dong L, Piao S, Wei F. Beit: bert pre-training of image transformers. arXiv:2106.08254. 2021.
26. End-to-end video instance segmentation with transformers
27. Han S, Mao H, Dally WJ. Deep compression: compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv: 1510.00149. 2015.
28. Chen T, Cheng Y, Gan Z, Yuan L, Zhang L, Wang Z. Chasing sparsity in vision transformers: an end-to-end exploration. arXiv:2106.04533. 2021.
29. Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv:1503.02531. 2015.
30. DearKD: data-efficient early knowledge distillation for vision transformers
31. Q-BERT: hessian based ultra low precision quantization of BERT
32. Sun M, Ma H, Kang G, Jiang Y, Chen T, Ma X, et al. VAQF: fully automatic software-hardware co-design framework for low-bit vision transformer. arXiv:2201.06618. 2022.
33. Scaling language-image pre-training via masking
34. Tokens-to-Token ViT: training vision transformers from scratch on ImageNet
35. Rao Y, Zhao W, Liu B, Lu J, Zhou J, Hsieh CJ. DynamicViT: efficient vision transformers with dynamic token sparsification. arXiv:2106.02034. 2021.
36. Ma · Computer vision-ECCV 2022 · 2022 · 42410.1007/978-3-031-20065-6_25 ↗
37. TransPose: keypoint localization via transformer
38. Mao W, Ge Y, Shen C, Tian Z, Wang X, Wang Z. TFPose: direct human pose estimation with transformers. arXiv:2103.15320. 2021.10.1007/978-3-031-20068-7_5 ↗
39. Pose recognition with cascade transformers
40. End-to-end human pose and mesh reconstruction with transformers
41. 3D human pose estimation with spatial and temporal transformers
42. Zhao · Artificial intelligence · 2022 · 559
43. Deep high-resolution representation learning for human pose estimation
44. Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. arXiv:1706.03762. 2017.
45. Microsoft COCO: common objects in context
46. 2D human pose estimation: new benchmark and state of the art analysis
47. Lite-HRNet: a lightweight high-resolution network
48. EfficientPose: efficient human pose estimation with neural architecture search10.1007/s41095-021-0214-z ↗
49. Full scale-aware balanced high-resolution network for multi-person pose estimation
50. Efficient posenet with coarse to fine transformer