Figure-ground segmentation improves handled object recognition in egocentric video

By Xiaofeng Ren, Chunhui Gu. 2010

190 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

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, background): “Ren and Gu [52] proposed a bottom-up motion-based approach to segment hand and object using the different motion patterns between hands and background in egocentric videos.”
Delving into Egocentric Actions (2015, neutral): “By taking advantage of a point-of-view camera, there have been several recent advances in First-Person Vision (FPV) [14], also known as egocentric vision, such as video summarization [20], video stabilization [16], object recognition [29] and action and activity recognition [33, 6, 27].”
Learning Image Representations Tied to Ego-Motion (2015, methodology): “Recent methods use ego-motion cues to separate foreground and background [25, 35] or infer the firstperson gaze [36, 18].”
A Review of Wearable Technologies for Elderly Care that Can Accurately Track Indoor Position, Recognize Physical Activities and Monitor Vital Signs in Real Time (2017, methodology): “In camera types used include RGB video, depth video and RGB-D video [49–53].”
Learning Image Representations Tied to Egomotion from Unlabeled Video (2017, methodology): “Recent methods use egomotion cues to separate foreground and background (Ren and Gu 2010; Xu et al. 2012) or infer the first-person gaze (Yamada et al.”
First Person Action-Object Detection with EgoNet (2016, methodology): “We acknowledge that our deﬁned concept of action-objects overlaps with several concepts from prior work such as object-action complexes (OAC) [26], handled-objects [44, 6], objects-in-action [16], or object affordances [24].”
Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals (2017, unknown): “5 23 640×360 Head/Wrist X - - House Activity Intel-Ego [53] 2 10 2.”
Story-Driven Summarization for Egocentric Video (2013, background): “Recent work uses supervised learning to recognize activities [25, 7, 20, 9, 8], handled objects [23], and novel events [1].”
Model Recommendation with Virtual Probes for Egocentric Hand Detection (2013, methodology): “As in many segmentation techniques, we formulate the task of hand region contour segmentation as an energy minimization problem [1] over super-pixel regions [13, 15, 5].”
H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions (2019, background): “While reasoning about hands in action, object interactions can be exploited as additional constraints [41, 49, 51, 53].”
Action recognition in RGB-D egocentric videos (2017, background): “For these reasons, increasing works have been proposed to investigate the egocentric videos from different aspects, like video summarization [15–17], visual recognition [18–21], social interaction [22], gaze detection [23] and many others.”
Temporal Perception and Prediction in Ego-Centric Video (2015, background): “There has been recent work on object recognition [12, 31], activity recognition [30, 9, 33], gaze prediction [25], and interaction detection [10] in first person video.”
Detecting activities of daily living in first-person camera views (2012, background): “Low-level features such as motion [9, 15, 20, 33] and skin-based color models [28] likely play a large role in analyzing wearable camera footage.”
Understanding egocentric activities (2011, background): “There has been significant recent interest in the egocentric approach to vi sion [26, 30, 7, 31] .”
Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video (2016, methodology): “First-person pose Limited research explores ways to infer the body pose of an egocentric camera wearer [4, 1, 13, 2, 11, 12].”
Learning image representations equivariant to ego-motion (2015, methodology): “Recent methods use ego-motion cues to separate foreground and background [23] [33] or infer the firstperson gaze [34] [16].”
Learning to Recognize Daily Actions Using Gaze (2012, methodology): “First-Person Vision: The idea of using wearable cameras is not new [22], however, recently there has been a growing interest in using them in the computer vision community, motivated by the advances in hardware technology [23,5,13,21,28,7,6,15,19].”
Discovering important people and objects for egocentric video summarization (2012, background): “, activity recog nition [5], object recognition [12], and action clustering [8]), to our knowledge, we are the first to perform visual summarization for egocentric data.”
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions (2015, background): “Ren and Gu [27] were among the first to study hand detection in first-person video, specifically in the context of held object detection.”