Animated Pose Templates for Modeling and Detecting Human Actions

By Benjamin Z. Yao, Xiaohan Nie, Zicheng Liu, Song-Chun Zhu. 2014

46 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Song-Chun Zhu
2. Luc Van Gool
3. Ming-Hsuan Yang
4. Jitendra Malik
5. Dacheng Tao
6. Andrew Zisserman
7. Trevor Darrell
8. Alan L. Yuille

In Control and Systems Engineering

1. Ying Nian Wu
2. Song-Chun Zhu
3. Siyuan Huang
4. Ronald Poppe
5. Josh Tenenbaum
6. Caiming Xiong
7. Siyuan Qi
8. Xiaohan Nie

Citations in the corpus

• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “actions like drinking and smoking [82, 83, 84, 85]; but most daily actions, such as opening a door, are defined by cause and effect (a door’s fluent changes from “closed” to “open,” regardless how it is opened), not by the human’s position, movement, or spatial-temporal features [86, 87].”
• Dyadic Interaction Detection from Pose and Flow (2014, methodology): “[10], optical flow is used to model transitions from one class of postures to the next.”
• Joint action recognition and pose estimation from video (2015, methodology): “However, existing methods train models for the two tasks separately and combine the inference sequentially: taking pose estimation as input for action recognition[15, 34, 25, 8, 27, 24].”
• Manifold Warp Segmentation of Human Action (2018, methodology): “Construct the bag-of-visual words [34] model on the basis”