A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Domain and View-point Agnostic Hand Action Recognition
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
This work introduces a novel skeleton-based hand motion representation model that tackles this problem. The framework we propose is agnostic to the application domain or camera recording view-point. ...
And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed ...
Up to our knowledge, generalization to unseen hand view-points and domains is still to be studied. ...
arXiv:2103.02303v3
fatcat:2gjitbedjfaurbotqjqb2xmhom
AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This paper proposes a novel adaptability decomposing encoder-decoder network to transfer reliable knowledge between trimmed and untrimmed videos for action recognition and localization via bidirectional ...
As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in untrimmed videos has attracted intensive research attention. ...
As we know, the domain-adaptable and domain-specific representations depict the video from different point of view. ...
arXiv:1911.11961v1
fatcat:qxptpsr5djcd5nnpagxnqvnrpu
DeepGRU: Deep Gesture Recognition Utility
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic. ...
For instance, we achieve a recognition accuracy of 84.9% and 92.3% on cross-subject and cross-view tests of the NTU RGB+D dataset respectively, and also 100% recognition accuracy on the UT-Kinect dataset ...
Portions of this research used the NTU RGB+D Action Recognition Dataset [46] made available by the ROSE Lab at the Nanyang Technological University, Singapore. ...
arXiv:1810.12514v4
fatcat:wrkdmeczvbfufmvzhk4ty7vscq
Activity, Plan, and Goal Recognition: A Review
2021
Frontiers in Robotics and AI
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
While action and plan recognition are tasks that humans perform naturally and with little effort, they are still an unresolved problem from the point of view of artificial intelligence. ...
This review is meant to provide a general view of the problem of activity, plan, and goal recognition as a whole. ...
the point of view of a higher layer that takes its outputs as elementary actions. ...
doi:10.3389/frobt.2021.643010
pmid:34041274
pmcid:PMC8141730
fatcat:hgoy6wjz7rgsxeta5olmpumlj4
Episodic Training for Domain Generalization
2019
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. ...
Furthermore, we consider the pervasive workflow of using an ImageNet trained CNN as a fixed feature extractor for downstream recognition tasks. ...
The goal is to train an action recognition model on a set of source views (domains), and recognise the action from a novel target view (domain). ...
doi:10.1109/iccv.2019.00153
dblp:conf/iccv/LiZYLSH19
fatcat:a4fhygn7cjagrfybv4pboqguwy
Recent Developments in Boolean Matrix Factorization
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In the last decade, BMF has received a considerable amount of attention in the data mining and formal concept analysis communities and, more recently, the machine learning and the theory communities also ...
In this survey, we give a concise summary of the efforts of all of these communities and raise some open questions which in our opinion require further investigation. ...
Acknowledgements The research leading to these results is partially supported by Accenture LTD and by the Center for Research on Computation and Society at Harvard University. ...
doi:10.24963/ijcai.2020/675
dblp:conf/ijcai/KerenGK20
fatcat:v2av6qtykrbn3oai3fyqi7aide
Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
To achieve this, it first uses a category-agnostic affordance prediction algorithm to select and execute among four different grasping primitive behaviors. ...
Exhaustive experimental results demonstrate that our multi-affordance grasping achieves high success rates for a wide variety of objects in clutter, and our recognition algorithm achieves high accuracy ...
/1539099), NVIDIA, and Facebook for hardware, technical, and financial support. ...
arXiv:1710.01330v5
fatcat:yyytldcvnfbvnailib366awsg4
Episodic Training for Domain Generalization
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Domain generalization (DG) is the challenging and topical problem of learning models that generalize to novel testing domains with different statistics than a set of known training domains. ...
Furthermore, we consider the pervasive workflow of using an ImageNet trained CNN as a fixed feature extractor for downstream recognition tasks. ...
The goal is to train an action recognition model on a set of source views (domains), and recognise the action from a novel target view (domain). ...
arXiv:1902.00113v3
fatcat:o5t2vmlmsrfh5mahcwvxncstpy
Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching
2019
The international journal of robotics research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
It then executes the action with the highest affordance and recognizes picked objects with a cross-domain image classification framework that matches observed images to product images. ...
To achieve this, it first uses an object-agnostic grasping framework to map from visual observations to actions: inferring dense pixel-wise probability maps of the affordances for four different grasping ...
and technical support. ...
doi:10.1177/0278364919868017
fatcat:tjzvct4y7rfnfiqk5bhlegpiwi
On the Ethics of Building AI in a Responsible Manner
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We argue that a formalism of AI alignment that does not distinguish between strategic and agnostic misalignments is not useful, as it deems all technology as un-safe. ...
The AI-alignment problem arises when there is a discrepancy between the goals that a human designer specifies to an AI learner and a potential catastrophic outcome that does not reflect what the human ...
As much as those issues require immediate and focused attention, there is a bigger potential danger at hand of a technology whose ultimate evolutionary end-point could get out of hand and cause havoc on ...
arXiv:2004.04644v1
fatcat:cxlid5sj2jdwnkopwhjfetymei
Data Augmentation vs. Domain Adaptation—A Case Study in Human Activity Recognition
2020
Technologies
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we fill this gap by providing ample experimental results comparing data augmentation and domain adaptation techniques on a cross-viewpoint, human activity recognition task from pose information ...
This is especially true for video data, and in particular for human activity recognition (HAR) tasks. ...
under the "Action for the Strategic Development on the Research and Technological Sector", funded by the Operational Programme "Competitiveness, Entrepreneurship and Innovation" (NSRF 2014-2020) and co-financed ...
doi:10.3390/technologies8040055
fatcat:k3ooqxpbrjfzvhwpe535wx5ao4
Learning task-agnostic representation via toddler-inspired learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Inspired by the toddler's learning procedure, we design an interactive agent that can learn and store task-agnostic visual representation while exploring and interacting with objects in the virtual environment ...
To tackle this problem, we derive inspiration from a highly intentional learning system via action: the toddler. ...
For the classification and recognition, we suppose that it is because the agent must recognize and classify the objects to achieve maximal reward, while action of the agent is dependent on the transferred ...
arXiv:2101.11221v1
fatcat:d6fhxvc22fclvcmvkndpyqmgoq
Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2104.05482v1 fatcat:p7ekmlhuazbphnjhat6of25mrq
Extensive experiments, conducted on the challenging task of skeleton-based action recognition, show the generalization ability and the outperformance of our proposed Laplacian design w.r.t. different baselines ...
filtered signals onto the input graph domain. ...
RELATED WORK In this section, we discuss the related work both from the methodological and the application point-of-view. ...
arXiv:2104.05482v2
fatcat:lyn6gjm36bbwnmr7w4s5x6zfay
Action Recognition with Kernel-based Graph Convolutional Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Experiments conducted on the challenging task of skeleton-based action recognition show the superiority of the proposed method against different baselines as well as the related work. ...
and well defined. ...
Table 2 shows a comparison of action recognition performances (and also runtime per epoch during training), using our KGCN (with different kernels) against standard GCN (referred to as SGCN), shown in ...
arXiv:2012.14186v1
fatcat:7jza4ltbczhffk46wajapjbope
Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Visual cues we employ include object-object interactions, hand grasps and motion within regions that are a function of hand locations. ...
This enables transfer of action classification models across public datasets captured with diverse scene and action configurations. ...
ACKNOWLEDGMENTS The authors would like to thank David Joseph Tan for the valuable discussions and constructive feedback. This work was supported by Microsoft. ...
arXiv:1907.09382v2
fatcat:aj7rdwx5ongd7dd2tsk6ybyeuu
« Previous
Showing results 1 — 15 out of 7,669 results