A stochastic graph grammar for compositional object representation and recognition

By Liang Lin, Tianfu Wu, Jake Porway, Zijian Xu. 2009

140 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

1. Xiaodan Liang
2. Song-Chun Zhu
3. Liang Lin
4. Lei Zhang
5. X. Wang
6. Tianfu Wu
7. Ping Luo
8. Yixin Zhu

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Xiaogang Wang
4. Ming-Hsuan Yang
5. Yi Yang
6. Lei Zhang
7. Liang Lin
8. Trevor Darrell

Citations in the corpus

• 3D Human Activity Recognition with Reconfigurable Convolutional Neural Networks (2014, methodology): “In this work, we develop an expressive configurable human activity model to address the above mentioned issues, absorbing the powers of two promising techniques of broad interests: deep learning [13, 7, 11, 8, 34, 18, 32] and recon-figurable part-based models [41, 1, 22, 16].”
• Learning latent spatio-temporal compositional model for human action recognition (2013, methodology): “Recently, the And-Or graph models [47] have been discussed for several vision tasks such as object recognition [21] and shape modeling [20].”
• AOGNets: Compositional Grammatical Architectures for Deep Learning (2017, background): “Object detection grammar was the dominant approaches for object detection [9, 70, 52, 38, 36, 37], and has recently been integrated with DNNs [57, 58, 5].”
• Deep feature learning with relative distance comparison for person re-identification (2015, background): “Despite the considerable efforts of computer vision researchers, however, it is still an unsolved problem due to the dramatic variations caused by light, viewpoint and pose changes [1].”
• AOGNets: Deep AND-OR Grammar Networks for Visual Recognition (2017, methodology): “odule [58], the deeply fused nets [63] and the DLA [69]. Grammars. A general framework of image grammar was proposed in [75]. Object detection grammar was the dominant approaches for object detection [10,74,55,41, 39,40], and has recently been integrated with DNNs [60, 61,6]. Probabilistic program i”
• Clothing Co-parsing by Joint Image Segmentation and Labeling (2014, background): “, spatial locations and mutual relations of clothes items, inspired by the successes of object/scene context modeling [14, 19, 12].”
• A Deep Structured Model with Radius–Margin Bound for 3D Human Activity Recognition (2015, background): “Recently, the And-Or graph representations are introduced as extensions of the part-based models [56, 32, 22, 39, 23], and produce very competitive performance to deal with large data variations.”
• RAVEN: A Dataset for Relational and Analogical Visual REasoNing (2019, methodology): “Specifically, we use the A-SIG as the representation of RPM; each RPM is a parse tree that instantiates from the A-SIG.”