Egocentric recognition of handled objects: Benchmark and analysis

By Xiaofeng Ren, Matthai Philipose. 2009

121 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

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

In Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

Wanderlust: Online Continual Object Detection in the Real World (2021, background): “Another related research direction is ego-centric video recognition [38, 12, 20].”
C3D: Generic Features for Video Analysis (2014, methodology): “Our C3D features outperforms [38] by 3 .”
Continual egocentric object recognition (2019, background): “As far as we know only two public datasets satisfy these requirements [24, 14].”
You-Do, I-Learn: Egocentric unsupervised discovery of objects and their modes of interaction towards video-based guidance (2015, background): “[15, 46, 48]) which are interesting in their own right.”
Egocentric Hand Track and Object-Based Human Action Recognition (2019, methodology): “We train a detector for each available hand dataset (except IEORD) and one for the combined train sets.”
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions (2015, background): “Other first-person video datasets that have been proposed [13, 21, 26, 28] are designed to test recognition of activities or handled objects, with minimal interaction with other people.”
Learning Spatiotemporal Features with 3D Convolutional Networks (2014, methodology): “For object recognition, we test C3D on egocentric dataset [32] which consists 42 types of everyday objects.”
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living (2012, background): “Papers reviewed using such techniques [93, 111, 112] emphasize how wearable cameras avoid the body to occlude”
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, background): “Other datasets exist, but they are mostly provided to support specific findings and thus are either limited in terms of total number of frames, [8,21,25,47], or do not exhibit a sufficient variety in terms of content [1, 4, 5, 15, 17, 20, 41, 46].”
Figure-ground segmentation improves handled object recognition in egocentric video (2010, methodology): “For SIFT matching, we follow the approach as originally discussed in the Intel egocentric object recognition benchmark [18].”
Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey (2019, background): “Due to its powerful ability of simultaneously extracting both spatial and temporal features from multiple frames, the network achieved state-of-the-art on several video analysis tasks including human action recognition [63], action similarity labeling [64], scene classification [65], and object reco”
ViBand: High-Fidelity Bio-Acoustic Sensing Using Commodity Smartwatch Accelerometers (2016, background): “Most approaches rely on markers [7, 20, 26, 40, 42] or special-purpose tags [28, 57, 58].”