Adding Knowledge to Unsupervised Algorithms for the Recognition of Intent

Synakowski, Stuart; Feng, Qianli; Martı́nez, Aleix M.

doi:10.1007/s11263-020-01404-0

Cited by 9 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the condition that DHJ is equal to 0 and uhj is equal to 1, RHJ = SHJ means that sample j belongs to level h and the membership is 1. [8][9][10][11][12] 4. Conclusion To sum up, speech recognition, as a new input mode with high speed and automatization under the development of computer technology, is also an important basis for the future industry innovation and development to achieve automation.…”

Section: Relative Membership Methodsmentioning

confidence: 99%

Application of Fuzzy Mathematics Algorithm in Computer Speech Recognition

Zhou

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Speech recognition, as one of the key artificial intelligence technologies in modern development, plays an important role in any aspect. However, there are still problems in practical application, such as poor anti-interference and low degree of perfection. Therefore, this paper aims at the content of existing computer speech recognition technology, grasps fuzzy mathematical algorithm, and analyzes how to use this algorithm to better study computer speech recognition.

show abstract

Section: Relative Membership Methodsmentioning

confidence: 99%

Application of Fuzzy Mathematics Algorithm in Computer Speech Recognition

Zhou

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…[66] focuses on predicting the action, motivation and scenes from an image by using a third order factor graph built using text. [58] proposes an unsupervised algorithm to discriminate between an intentional and unintentional action performed by an agent. [15] too focuses on discriminating between an intentional and unintentional action, as well as predicting the point in an unintentional video when the action deviates from it's original goal, but does this in a supervised manner.…”

Section: Related Workmentioning

confidence: 99%

“…However, it does not contain well defined classes for the goaldirected action or why this goal gets disrupted. [58] focuses on predicting whether an activity was intentional or unintentional, but not the understanding of the underlying goal of an unintentional action. Previous efforts [16,32,77] have tried to speculate about all possible effects of actions but do not explore which effects are undesirable.…”

Section: Introductionmentioning

confidence: 99%

Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos

Chakravarthy¹,

Fang²,

Yang³

2022

Preprint

View full text Add to dashboard Cite

In videos that contain actions performed unintentionally, agents do not achieve their desired goals. In such videos, it is challenging for computer vision systems to understand high-level concepts such as goal-directed behavior, an ability present in humans from a very early age. Inculcating this ability in artificially intelligent agents would make them better social learners by allowing them to evaluate human action under a teleological lens. To validate this ability of deep learning models to perform this task, we curate the W-Oops dataset, built upon the Oops dataset [15]. W-Oops consists of 2,100 unintentional human action videos, with 44 goal-directed and 30 unintentional video-level activity labels collected through human annotations. Due to the expensive segment annotation procedure, we propose a weakly supervised algorithm for localizing the goaldirected as well as unintentional temporal regions in the video leveraging solely video-level labels. In particular, we employ an attention mechanism based strategy that predicts the temporal regions which contributes the most to a classification task. Meanwhile, our designed overlap regularization allows the model to focus on distinct portions of the video for inferring the goal-directed and unintentional activity, while guaranteeing their temporal ordering. Extensive quantitative experiments verify the validity of our localization method. We further conduct a video captioning experiment which demonstrates that the proposed localization module does indeed assist teleological action understanding. Project website can be found at: https://asuapg.github.io/TragedyPlusTime.

show abstract

“…Research has also been carried out on detecting the intentions of human actions (Pezzelle et al, 2020); the task definition differs from ours, however, as their goal is to automatically choose the correct action for a given image and intention. Other related work includes (Synakowski et al, 2020), a visionbased classification model between intentional and non-intentional actions and Intentonomy (Jia et al, 2021), a dataset on human intent behind images on Instagram.…”

Section: Related Workmentioning

confidence: 99%

Identifying Visible Actions in Lifestyle Vlogs

Ignat

Burdick

Deng

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

We consider the task of identifying human actions visible in online videos. We focus on the widely spread genre of lifestyle vlogs, which consist of videos of people performing actions while verbally describing them. Our goal is to identify if actions mentioned in the speech description of a video are visually present. We construct a dataset with crowdsourced manual annotations of visible actions, and introduce a multimodal algorithm that leverages information derived from visual and linguistic clues to automatically infer which actions are visible in a video. We demonstrate that our multimodal algorithm outperforms algorithms based only on one modality at a time.

show abstract

Adding Knowledge to Unsupervised Algorithms for the Recognition of Intent

Cited by 9 publications

References 19 publications

Application of Fuzzy Mathematics Algorithm in Computer Speech Recognition

Application of Fuzzy Mathematics Algorithm in Computer Speech Recognition

Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos

Identifying Visible Actions in Lifestyle Vlogs

Contact Info

Product

Resources

About