Classifying Actions and Measuring Action Similarity by Modeling the Mutual Context of Objects and Human Poses

By Bangpeng Yao, Aditya Khosla, Li Fei-Fei. 2011

How researchers see this paper

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

Citations in the corpus

Large scale visual recommendations from street fashion images (2014, methodology): “This validation procedure is in line with the established validation protocols for image retrieval [18].”
A survey on still image based human action recognition (2014, methodology): “In their later methods [30,38], the model was extended to deal with any number of objects, instead of being limited to the interactions between one person and one object.”
Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses (2012, unknown): “A preliminary version of our paper was described in [50] and extended in [16].”
Learning in high-dimensional multimedia data: the state of the art (2015, background): “High-dimensional data pose many intrinsic challenges for pattern recognition problems [19, 61, 74, 99, 104], for example, the curse of dimensionality and the diminishment of specificity in similarities between points in a highdimensional space [8, 17, 41].”
Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions (2017, background): “Early work focused on capturing actors and objects implicitly in a low-level descriptor [4, 60], while more recently the benefit of explicitly representing detected objects [8], their scores, and spatial properties was proven effective [16, 49, 61, 62].”
Image retrieval using scene graphs (2015, background): “5) learns models for particular relations between pairs of objects, similar in spirit to [25] or [66].”