Multi-GAT: A Graphical Attention-Based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition

Islam, Md Mofijul; Iqbal, Tarıq

doi:10.1109/lra.2021.3059624

Cited by 61 publications

(18 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the addition of the attention mechanism makes the model interpretable to a certain degree. Due to these advantages of the GATs model, many graph neural networks models have been proposed that are based on GATs 21,22 or other specific types of attention mechanisms. [23][24][25]…”

Section: Preliminariesmentioning

confidence: 99%

Social influence‐based privacy inference attacks in online social networks

Zhu

et al. 2021

Security and Privacy

View full text Add to dashboard Cite

Privacy inference attacks in online social networks aim at inferring hidden attributes of target users based on released attributes of the users as well as information about social relationships in the networks. Although many privacy inference methods have been proposed in recent years, most of the methods have mostly focused on pursuing high accuracy of the inference results without paying too much attention on identifying users who make the most contributions to the inference, making it less useful in the development of effective countermeasures. In this paper, by taking full consideration of the roles of users in privacy inference, we propose a privacy inference method based on graph attention networks that can provide information about not only the private attributes of the target users, but also the importance of the users in the process of inferring the results. We also design a novel mechanism for the selection of influential users to make our proposed method adaptive to the characteristics of user influence diffusion, resulting in involving fewer number of users in privacy inference and hence improving the efficiency. We also performed some experiment to evaluate the proposed method using a real online social network dataset to show the effectiveness of the proposed method. Comparison with other comparable methods also shows that the results of our proposed method are more accurate.

show abstract

Section: Preliminariesmentioning

confidence: 99%

Social influence‐based privacy inference attacks in online social networks

Zhu

et al. 2021

Security and Privacy

View full text Add to dashboard Cite

show abstract

“…R OBOTS are started to be widely employed in various environments, including automating warehouses [1]- [4], controlling traffic [5], robot-guided evacuation [6], and human-robot interaction [7]- [9]. In many of these environments, multiple robots are deployed forming a multi-agent system, and each agent interacts with other agent or humans to complete an assigned task [10]- [13].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Agent-Specific Sub-Optimal Bounding Approach for Multi-Agent Path Finding

et al. 2022

Self Cite

View full text Add to dashboard Cite

A Multi-Agent Path Finding (MAPF) problem involves multiple agents who want to reach their destinations without obstructing other agents. Although a MAPF problem needs to be solved for many real-world deployments, solving such a problem optimally is NP-hard. Many approaches have been proposed in the literature that offers sub-optimal solutions to this problem. For example, the Enhanced Conflict Based Search (ECBS) algorithm compromises the solution quality up to a constant factor to gain a notable runtime improvement. However, these algorithms use a fixed global sub-optimal bound for all agents, regardless of their preferences. In effect, with the increase in the number of agents, the runtime performance degrades. Against this backdrop, with the intent to further speed up the runtime, we propose an adaptive agent-specific sub-optimal bounding approach, called ASB-ECBS, that can be executed statically or dynamically. Specifically, ASB-ECBS can assign sub-optimal bound considering an individual agent's requirement. Additionally, we theoretically prove that the solution cost of ASB-ECBS remains within the sub-optimal bound. Finally, our extensive empirical results depict a notable improvement in the runtime by using ASB-ECBS while reducing the search space compared to the state-of-the-art MAPF algorithms.

show abstract

“…There have been impressive advances activity recognition frameworks tailored for robotics applications [1], [2], [3], [4], [5], [6], [7], [8]. However, this task remains very challenging in practice, as agents mostly operate in an open constantly changing environment and we will never be able to capture and annotate a high amount of training examples for every possible category [9], which is a requirement in the majority of presented approaches.…”

Section: Introductionmentioning

confidence: 99%

ProFormer: Learning Data-efficient Representations of Body Movement with Prototype-based Feature Augmentation and Visual Transformers

Peng¹,

Roitberg²,

Yang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automatically understanding human behaviour allows household robots to identify the most critical needs and plan how to assist the human according to the current situation. However, the majority of such methods are developed under the assumption that a large amount of labelled training examples is available for all concepts-of-interest. Robots, on the other hand, operate in constantly changing unstructured environments, and need to adapt to novel action categories from very few samples. Methods for data-efficient recognition from body poses increasingly leverage skeleton sequences structured as image-like arrays and then used as input to convolutional neural networks. We look at this paradigm from the perspective of transformer networks, for the first time exploring visual transformers as data-efficient encoders of skeleton movement. In our pipeline, body pose sequences cast as image-like representations are converted into patch embeddings and then passed to a visual transformer backbone optimized with deep metric learning. Inspired by recent success of feature enhancement methods in semi-supervised learning, we further introduce PROFORMER -an improved training strategy which uses soft-attention applied on iteratively estimated action category PROtotypes used to augment the embeddings and compute an auxiliary consistency loss. Extensive experiments consistently demonstrate the effectiveness of our approach for one-shot recognition from body poses, achieving state-of-the-art results on multiple datasets and surpassing the best published approach on the challenging NTU-120 one-shot benchmark by 1.84%. Our code will be made publicly available at https: //github.com/KPeng9510/ProFormer.

show abstract

Multi-GAT: A Graphical Attention-Based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition

Cited by 61 publications

References 45 publications

Social influence‐based privacy inference attacks in online social networks

Social influence‐based privacy inference attacks in online social networks

An Adaptive Agent-Specific Sub-Optimal Bounding Approach for Multi-Agent Path Finding

ProFormer: Learning Data-efficient Representations of Body Movement with Prototype-based Feature Augmentation and Visual Transformers

Contact Info

Product

Resources

About