2013 IEEE International Conference on Robotics and Automation 2013
DOI: 10.1109/icra.2013.6631291
|View full text |Cite
|
Sign up to set email alerts
|

Language for learning complex human-object interactions

Abstract: Abstract-In this paper we use a Hierarchical Hidden Markov Model (HHMM) to represent and learn complex activities/task performed by humans/robots in everyday life. Action primitives are used as a grammar to represent complex human behaviour and learn the interactions and behaviour of human/robots with different objects. The main contribution is the use of a probabilistic model capable of representing behaviours at multiple levels of abstraction to support the proposed hypothesis. The hierarchical nature of the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2014
2014
2016
2016

Publication Types

Select...
4
1
1

Relationship

1
5

Authors

Journals

citations
Cited by 9 publications
(5 citation statements)
references
References 21 publications
0
5
0
Order By: Relevance
“…Language in Vision: The community has recently been incorporating natural language into computer vision, such as generating sentences from images [20,15,36], producing visual models from sentences [44,38], and aiding in contextual models [26,22]. In our work, we seek to mine language models trained on a massive text corpus to extract some knowledge that can assist computer vision systems.…”
Section: Related Workmentioning
confidence: 99%
“…Language in Vision: The community has recently been incorporating natural language into computer vision, such as generating sentences from images [20,15,36], producing visual models from sentences [44,38], and aiding in contextual models [26,22]. In our work, we seek to mine language models trained on a massive text corpus to extract some knowledge that can assist computer vision systems.…”
Section: Related Workmentioning
confidence: 99%
“…-were located, not the actual interactions between user and objects. Grasping and object manipulation activities have also been studied with RGB-D cameras within the context of HHMM frameworks [22] in small 3D working envelopes. A framework based on an H-DBN was able to infer user's mode of transportation and desired destination [23] in an urban setting, and guidance cues where proposed when it was felt the user was deviating from his normal activities.…”
Section: Related Workmentioning
confidence: 99%
“…Each image depicts the output of hand-object tracking algorithm. For more details please refer to [77], i.e. the origin of this figure.…”
Section: 9mentioning
confidence: 99%
“…Here, we present two approaches that exploit our 3D hand tracking methods to perform higher level inference, which regards understanding of hand motion, in the context of object manipulation. These approaches have been proposed by Song et al [92] and Patel et al [77].…”
Section: Higher Level Inferencementioning
confidence: 99%
See 1 more Smart Citation