Towards Good Practices for Action Video Encoding
By Jianxin Wu, Yu Zhang, Weiyao Lin. 2014
75 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mehrtash Harandi
- Fatih Murat Porikli
- Jianfei Cai
- Samitha Herath
- Yu-Gang Jiang
- Xiangyang Xue
- Jianxin Wu
- Chong-Wah Ngo
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Jianfei Cai
- Trevor Darrell
- Xiaogang Wang
- Yi Yang
- Cordelia Schmid
- Ming-Hsuan Yang
Citations in the corpus
- Actions ~ Transformations (2015, neutral): “STIP+BoW [23] 23.0% STIP+BoW [42] 43.9% DCS+VLAD [15] 52.1% CNN[21] 65.4% VLAD Encoding [56] 56.4% IDT+FV [51] 85.9% IDT+FV [51] 57.2% IDT+HSV [31] 87.9% Two Stream [39] 59.4% Two Stream [39] 88.0% IDT+HSV [31] 61.1% LSTM with 88.6% Two Stream [30] TDD+FV [52] 63.2% TDD+FV [52] 90.3% inputs…”
- Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice (2014, neutral): “[58] propose a simple, lightweight, but powerful bimodal encoding method.”
- Rank Pooling for Action Recognition (2015, unknown): “Wu et al [70] 56.”
- Modeling video evolution for action recognition (2015, unknown): “[42] 56.”
- Human Action Recognition in Unconstrained Videos by Explicit Motion Modeling (2015, methodology): “Compared with a recent work on the sampling of local features [18], a new VLAD encoding approach [60], and the approach of Jain et al.”
- What do 15,000 object categories tell us about classifying and localizing actions? (2015, unknown): “Three of the best performers on UCF101 [1, 32, 55] propose improved encoding methods.”
- Weakly Supervised Fine-Grained Categorization With Part-Based Image Representation (2016, background): “Data normalization has been shown to effectively improve the discriminative power of a representation [46].”
- Discriminative Hierarchical Rank Pooling for Activity Recognition (2016, unknown): “[35] – 56.”
- Action Recognition in Still Images With Minimum Annotation Efforts (2016, background): “Different from video-based action recognition [4], [5] where”
- Going deeper into action recognition: A survey (2016, methodology): “A comparison of speed and accuracy of FV against VLAD can be found in Kantorov and Laptev (2014); Wu et al. (2014).”