A Scalable Approach to Activity Recognition based on Object Use

By Jianxin Wu, Adebola Osuntogun, Tanzeem Choudhury, Matthai Philipose, James M. Rehg. 2007

399 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

In Computer Vision and Pattern Recognition

Citations in the corpus

A self-organizing neural network architecture for learning human-object interactions (2017, background): “Typically, ﬁrst, objects are recognized and activities involving them are subsequently recognized, by analyzing the objects’ motion trajectories [30].”
Unstructured human activity detection from RGBD images (2011, methodology): “Most previous work on activity classification has focused on using 2D video (e.g., [26, 10]) or RFID sensors placed on humans and objects (e.g., [41]).”
Functional categorization of objects using real-time markerless motion capture (2011, methodology): “In [33], activities are inferred from the used objects that are observed and identified by video and RFID sensors.”
Deep Learning for RFID-Based Activity Recognition (2016, methodology): “We also compared the performance of our deep-learning system using RFID data for medical activity recognition with several state-of-the-art recognition systems for real-world application scenarios [14,38,39] (Table 6) .”
Human Activity Detection from RGBD Images (2011, methodology): “Most previous work on activity classiﬁcation has focused on using 2D video (e.g., Ning et al., 2009; Gupta et al., 2009) or RFID sensors placed on humans and objects (e.g., Wu et al., 2007).”
Progressively Parsing Interactional Objects for Fine Grained Action Detection (2016, methodology): “In some contextual object recognition works [17, 7, 33, 11], hands and objects are detected using different methods independently, and the detections are further fused via probabilistic graphical models for high level inference, e.”
Temporal segmentation and activity classification from first-person sensing (2009, methodology): “An alternative method to object recognition that can provide information about the objects in use is an RFID bracelet that reads tags on objects, as was successfully used in [29].”
Actions in context (2009, background): “In [8, 18, 22, 27] object context is used for action recognition and demonstrates improved recognition of objects and actions in video.”
You-Do, I-Learn: Discovering Task Relevant Objects and their Modes of Interaction from Multi-User Egocentric Video (2014, background): “Combining appearance with motion has also been attempted [9, 40].”
Script Data for Attribute-Based Recognition of Composite Activities (2012, methodology): “Language and cross-modal learning have been used for knowledge transfer [17, 11].”
Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions (2017, neutral): “[14, 34, 37, 53].”
Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition (2009, background): “They discovered that the weight of an object is most robustly estimated, while size and shape are harder to estimate.”
Probabilistic Plan Recognition Using Off-the-Shelf Classical Planners (2010, methodology): “These problems have been derived manually from the plan libraries given in (Geib and Goldman 2002; Bui et al. 2008; Wu et al. 2007).”
Audio-visual classification and detection of human manipulation actions (2014, background): “It has been shown [7]–[15] that it is advantageous to represent human activity both in terms”
Modeling Actions through State Changes (2013, background): “[28] recognize activities based on temporal patterns of object use.”