Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userThe Truth and Nothing but the Truth: Multimodal Analysis for Deception Detection
51
0
0.0
(
0
)
Added by
Mimansa Jaiswal
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We propose a data-driven method for automatic deception detection in real-life trial data using visual and verbal cues. Using OpenFace with facial action unit recognition, we analyze the movement of facial features of the witness when posed with questions and the acoustic patterns using OpenSmile. We then perform a lexical analysis on the spoken words, emphasizing the use of pauses and utterance breaks, feeding that to a Support Vector Machine to test deceit or truth prediction. We then try out a method to incorporate utterance-based fusion of visual and lexical analysis, using string based matching.
rate research
Read More
Classifiers commonly make use of pre-annotated datasets, wherein a model is evaluated by pre-defined metrics on a held-out test set typically made of human-annotated labels. Metrics used in these evaluations are tied to the availability of well-defined ground truth labels, and these metrics typically do not allow for inexact matches. These noisy ground truth labels and strict evaluation metrics may compromise the validity and realism of evaluation results. In the present work, we discuss these concerns and conduct a systematic posthoc verification experiment on the entity linking (EL) task. Unlike traditional methodologies, which asks annotators to provide free-form annotations, we ask annotators to verify the correctness of annotations after the fact (i.e., posthoc). Compared to pre-annotation evaluation, state-of-the-art EL models performed extremely well according to the posthoc evaluation methodology. Posthoc validation also permits the validation of the ground truth dataset. Surprisingly, we find predictions from EL models had a similar or higher verification rate than the ground truth. We conclude with a discussion on these findings and recommendations for future evaluations.
Across many scientific domains, there is a common need to automatically extract a simplified view or coarse-graining of how a complex systems components interact. This general task is called community detection in networks and is analogous to searching for clusters in independent vector data. It is common to evaluate the performance of community detection algorithms by their ability to find so-called ground truth communities. This works well in synthetic networks with planted communities because such networks links are formed explicitly based on those known communities. However, there are no planted communities in real world networks. Instead, it is standard practice to treat some observed discrete-valued node attributes, or metadata, as ground truth. Here, we show that metadata are not the same as ground truth, and that treating them as such induces severe theoretical and practical problems. We prove that no algorithm can uniquely solve community detection, and we prove a general No Free Lunch theorem for community detection, which implies that there can be no algorithm that is optimal for all possible community detection tasks. However, community detection remains a powerful tool and node metadata still have value so a careful exploration of their relationship with network structure can yield insights of genuine worth. We illustrate this point by introducing two statistical techniques that can quantify the relationship between metadata and community structure for a broad class of models. We demonstrate these techniques using both synthetic and real-world networks, and for multiple types of metadata and community structure.
Diverse promising datasets have been designed to hold back the development of fake audio detection, such as ASVspoof databases. However, previous datasets ignore an attacking situation, in which the hacker hides some small fake clips in real speech audio. This poses a serious threat since that it is difficult to distinguish the small fake clip from the whole speech utterance. Therefore, this paper develops such a dataset for half-truth audio detection (HAD). Partially fake audio in the HAD dataset involves only changing a few words in an utterance.The audio of the words is generated with the very latest state-of-the-art speech synthesis technology. We can not only detect fake uttrances but also localize manipulated regions in a speech using this dataset. Some benchmark results are presented on this dataset. The results show that partially fake audio presents much more challenging than fully fake audio for fake audio detection.
Home detection, assigning a phone device to its home antenna, is a ubiquitous part of most studies in the literature on mobile phone data. Despite its widespread use, home detection relies on a few assumptions that are difficult to check without ground truth, i.e., where the individual that owns the device resides. In this paper, we provide an unprecedented evaluation of the accuracy of home detection algorithms on a group of sixty-five participants for whom we know their exact home address and the antennas that might serve them. Besides, we analyze not only Call Detail Records (CDRs) but also two other mobile phone streams: eXtended Detail Records (XDRs, the ``data channel) and Control Plane Records (CPRs, the network stream). These data streams vary not only in their temporal granularity but also they differ in the data generation mechanism, e.g., CDRs are purely human-triggered while CPR is purely machine-triggered events. Finally, we quantify the amount of data that is needed for each stream to carry out successful home detection for each stream. We find that the choice of stream and the algorithm heavily influences home detection, with an hour-of-day algorithm for the XDRs performing the best, and with CPRs performing best for the amount of data needed to perform home detection. Our work is useful for researchers and practitioners in order to minimize data requests and to maximize the accuracy of home antenna location.
As automated vehicles are getting closer to becoming a reality, it will become mandatory to be able to characterise the performance of their obstacle detection systems. This validation process requires large amounts of ground-truth data, which is currently generated by manually annotation. In this paper, we propose a novel methodology to generate ground-truth kinematics datasets for specific objects in real-world scenes. Our procedure requires no annotation whatsoever, human intervention being limited to sensors calibration. We present the recording platform which was exploited to acquire the reference data and a detailed and thorough analytical study of the propagation of errors in our procedure. This allows us to provide detailed precision metrics for each and every data item in our datasets. Finally some visualisations of the acquired data are given.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
