Recognizing Human-Object Interactions in Still Images by Modeling the Mutual Context of Objects and Human Poses

By Bangpeng Yao, Li Fei-Fei. 2012

218 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Relation Networks for Object Detection (2017, background): “Human centered scenarios Quite a few works focus on human-object relation [51, 22, 20, 21].”
A self-organizing neural network architecture for learning human-object interactions (2017, neutral): “Other research studies have modeled the mutual context between objects and human pose through graphical models such as Conditional Ran-2 dom Fields (CRF) [35, 23, 36].”
Fuzzy human motion analysis: A review (2014, methodology): “For example, [251] proposed a method to recognize the human-object interactions in still images by explicitly modeling the mutual context between the human poses and the objects, so that each can facilitate the recogn ition of the other.”
Recognize complex events from static images by fusing deep channels (2015, background): “Analyzing human actions [10] with the help of human poses [21, 38] and human-object interactions [2, 40] also provides significant cues in recognizing certain categories of events.”
Jointly Learning Heterogeneous Features for RGB-D Activity Recognition (2015, background): “These greatly limit the application of depth cameras on recognizing complex human activities with object and interactions, such as human-object interactions [10], [50] and fine grained activities [16], where the color appearance is also important.”
Human-object interaction recognition by learning the distances between the object and the skeleton joints (2015, background): “In another work of Yao et al [9], it treated object and human pose as the context of each other in human-object interaction activities.”
Pose for Action - Action for Pose (2016, methodology): “A similar approach is adopted in [40] to model object-pose relations.”
RMPE: Regional Multi-person Pose Estimation (2016, methodology): “ation To directly learn the distribution P(δB|P) is difﬁcult due to the variation of human poses. So instead, we attempt to learn the distribution P(δB|atom(P)), where atom(P) denotes the atomic pose [36] of P. We follow the method used by Andriluka et al [3] to learn the atomic poses. To derive the”
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images (2015, background): “Although there is previous work on action recognition from still images using other representations [42], we choose CNN activations for its simplicity and state-of-the-art performance in several action recognition tasks [29, 15, 39].”
PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction Detection (2019, background): “Human-Object Interaction (HOI) detection [30, 11, 10, 9, 12, 16, 22] has received increasing attention recently.”
MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain (2022, background): “HOI detection models mostly consider one single object involved in the interaction [43, 42, 39, 99, 8].”
A Discriminative Model with Multiple Temporal Scales for Action Prediction (2014, unknown): “In addition, recognizing human actions from a set of keyframes [12,22] and static images [25,24] have also been investigated in previous studies.”
A similarity measure for analyzing human activities using human-object interaction context (2014, methodology): “A conditional random field is used in [6] to model this correlation and use it human action recognition.”