Oldest and Highest Rated Papers
Exploring physiological differences in injury response by skin tone: A scoping review
Pinar Avsar, Zena Moore, Declan Patton, Tom O'Connor, Lone Skoubo Bertelsen, Desmond J. Tobin, Giulio Brunetti, Keryln Carville, Vignesh Iyer, Hannah Wilson
Journal of Tissue Viability·2025·3 citations
No abstract available
★ 4.0 (1)
View paper →Facing Imbalanced Data–Recommendations for the Use of Performance Metrics
László A. Jeni, Jeffrey F. Cohn, Fernando De La Torre
2013 Humaine Association Conference on Affective Computing and Intelligent Interaction·2013·519 citations
Recognizing facial action units (AUs) is important for situation analysis and automated video annotation. Previous work has emphasized face tracking and registration and the choice of features classifiers. Relatively neglected is the effect of imbalanced data for action unit detection. While the machine learning community has become aware of the problem of skewed data for training classifiers, little attention has been paid to how skew may bias performance metrics. To address this question, we conducted experiments using both simulated classifiers and three major databases that differ in size, type of FACS coding, and degree of skew. We evaluated influence of skew on both threshold metrics (Accuracy, F-score, Cohen's kappa, and Krippendorf's alpha) and rank metrics (area under the receiver operating characteristic (ROC) curve and precision-recall curve). With exception of area under the ROC curve, all were attenuated by skewed distributions, in many cases, dramatically so. While ROC was unaffected by skew, precision-recall curves suggest that ROC may mask poor performance. Our findings suggest that skew is a critical factor in evaluating performance metrics. To avoid or minimize skew-biased estimates of performance, we recommend reporting skew-normalized scores along with the obtained ones.
★ 4.0 (1)
View paper →Randomly generating portfolio-selection covariance matrices with specified distributional characteristics
Markus Hirschberger, Yue Qi, Ralph E. Steuer
European Journal of Operational Research·2007·89 citations
In portfolio selection, there is often the need for procedures to generate “realistic” covariance matrices for security returns, for example to test and benchmark optimization algorithms. For application in portfolio optimization, such a procedure should allow the entries in the matrices to have distributional characteristics which we would consider “realistic” for security returns. Deriving motivation from the fact that a covariance matrix can be viewed as stemming from a matrix of factor loadings, a procedure is developed for the random generation of covariance matrices (a) whose off-diagonal (covariance) entries possess a pre-specified expected value and standard deviation and (b) whose main diagonal (variance) entries possess a likely different pre-specified expected value and standard deviation. The paper concludes with a discussion about the futility one would likely encounter if one simply tried to invent a valid covariance matrix in the absence of a procedure such as in this paper.
★ 4.0 (1)
View paper →A Systematic Comparison of Supervised Classifiers
Diego Raphael Amancio, Cesar Henrique Comin, Dalcimar Casanova, Gonzalo Travieso, Odemir Martinez Bruno, Francisco Aparecido Rodrigues, Luciano da Fontoura Costa
PLoS ONE·2014·168 citations
Pattern recognition has been employed in a myriad of industrial, commercial and academic applications. Many techniques have been devised to tackle such a diversity of applications. Despite the long tradition of pattern recognition research, there is no technique that yields the best classification in all scenarios. Therefore, as many techniques as possible should be considered in high accuracy applications. Typical related works either focus on the performance of a given algorithm or compare various classification methods. In many occasions, however, researchers who are not experts in the field of machine learning have to deal with practical classification tasks without an in-depth knowledge about the underlying parameters. Actually, the adequate choice of classifiers and parameters in such practical circumstances constitutes a long-standing problem and is one of the subjects of the current paper. We carried out a performance study of nine well-known classifiers implemented in the Weka framework and compared the influence of the parameter configurations on the accuracy. The default configuration of parameters in Weka was found to provide near optimal performance for most cases, not including methods such as the support vector machine (SVM). In addition, the k-nearest neighbor method frequently allowed the best accuracy. In certain conditions, it was possible to improve the quality of SVM by more than 20% with respect to their default parameter configuration.
★ 4.0 (1)
View paper →Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
Simon Giebenhain, Tobias Kirschstein, Martin Rünz, Lourdes Agapito, Matthias Nießner
arXiv·2025
We address the 3D reconstruction of human faces from a single RGB image. To this end, we propose Pixel3DMM, a set of highly-generalized vision transformers which predict per-pixel geometric cues in order to constrain the optimization of a 3D morphable face model (3DMM). We exploit the latent features of the DINO foundation model, and introduce a tailored surface normal and uv-coordinate prediction head. We train our model by registering three high-quality 3D face datasets against the FLAME mesh topology, which results in a total of over 1,000 identities and 976K images. For 3D face reconstruction, we propose a FLAME fitting opitmization that solves for the 3DMM parameters from the uv-coordinate and normal estimates. To evaluate our method, we introduce a new benchmark for single-image face reconstruction, which features high diversity facial expressions, viewing angles, and ethnicities. Crucially, our benchmark is the first to evaluate both posed and neutral facial geometry. Ultimately, our method outperforms the most competitive baselines by over 15% in terms of geometric accuracy for posed facial expressions.
★ 4.0 (1)
View paper →The Reckoning We Still Refuse
Future Tense
Substack·2025
It was the second year of his soiree, which drew the 1 percent of the 1 percent of the 1 percent for a Labor Day bash that was described as the closest thing to a night at Studio 54 or the Playboy Mansion.
For over a decade, Puff’s White Party was the flagship event of his social calendar. It was his calling card. A major part of the mythmaking that took him from scrappy label intern to young A&R executive to hotshot producer to millionaire rap mogul to global bon vivant. A Black Jay Gatsby if you will.
★ 4.0 (1)
View paper →Solving a Million-Step LLM Task with Zero Errors
Elliot Meyerson, Giuseppe Paolo, Roberto Dailey, Hormoz Shahrzad, Olivier Francon, Conor F. Hayes, Xin Qiu, Babak Hodjat, Risto Miikkulainen
arXiv·2025
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans, organizations, and societies has remained out of reach. The models have a persistent error rate that prevents scale-up: for instance, recent experiments in the Towers of Hanoi benchmark domain showed that the process inevitably becomes derailed after at most a few hundred steps. Thus, although LLM research is often still benchmarked on tasks with relatively few dependent logical steps, there is increasing attention on the ability (or inability) of LLMs to perform long range tasks. This paper describes MAKER, the first system that successfully solves a task with over one million LLM steps with zero errors, and, in principle, scales far beyond this level. The approach relies on an extreme decomposition of a task into subtasks, each of which can be tackled by focused microagents. The high level of modularity resulting from the decomposition allows error correction to be applied at each step through an efficient multi-agent voting scheme. This combination of extreme decomposition and error correction makes scaling possible. Thus, the results suggest that instead of relying on continual improvement of current LLMs, massively decomposed agentic processes (MDAPs) may provide a way to efficiently solve problems at the level of organizations and societies.
★ 4.0 (1)
View paper →Automated speech and language markers of longitudinal changes in psychosis symptoms
Sunny X. Tang, Michael J. Spilka, Majnu John, Michael L. Birnbaum, Ema Saito, Sarah A. Berretta, Leily M. Behbehani, Mark Y. Liberman, Anil K. Malhotra, William Simpson, John M. Kane
NPP—Digital Psychiatry and Neuroscience·2025·2 citations
<jats:title>Abstract</jats:title>
<jats:p>
We sought to evaluate the ability of automated speech and language features to longitudinally track fluctuations in the major psychosis domains:
<jats:italic>Thought Disorder</jats:italic>
,
<jats:italic>Negative Symptoms</jats:italic>
, and
<jats:italic>Positive Symptoms</jats:italic>
. Sixty-six participants with psychotic disorders were assessed soon after inpatient admission, at discharge, and at 3- and 6-months. Psychosis symptoms were measured with semi-structured interviews and standardized scales. Recordings were collected from paragraph reading, fluency, picture description, and open-ended tasks. Relationships between psychosis symptoms and 357 automated speech and language features were analyzed using a single component score and as individual features, using linear mixed models. We found that all three domains demonstrated significant longitudinal relationships with the single component score.
<jats:italic>Thought Disorder</jats:italic>
was particularly related to features describing more subordinated constructions, less efficient identification of picture elements, and decreased semantic distance between sentences.
<jats:italic>Negative Symptoms</jats:italic>
was related to features describing decreased speech complexity.
<jats:italic>Positive Symptoms</jats:italic>
domain score did not show relationships with individual features that survived p-value correction, but
<jats:italic>Suspiciousness</jats:italic>
was related to decreased use of nouns and
<jats:italic>Hallucinations</jats:italic>
was related to greater semantic distances. These relationships were largely robust to interactions with gender and race. Interactions with timepoint revealed variable relationships during different phases of illness (acute vs. stable). In summary, automated speech and language features show promise as scalable, objective markers of psychosis severity. Detailed attention to clinical setting and patient population is needed to optimize clinical translation.
</jats:p>
★ 4.0 (1)
View paper →A governance analysis of Ningaloo and Shark Bay Marine Parks, Western Australia: Putting the ‘eco’ in tourism to build resilience but threatened in long-term by climate change?
Peter J.S. Jones
Marine Policy·2021·14 citations
No abstract available
★ 4.0 (1)
View paper →Roma Lister, Aradia, and the Speculative Origins of a Witchcraft Revival — The Public Domain Review
A.D. Manns
The Public Domain Review·2025
In 1899, Charles Godfrey Leland published Aradia, “the gospel of the witches”, containing a goddess-orientated creation and saviour narrative, purported to descend from an ancient, hermetic tradition of witchcraft in Italy. A. D. Manns explores this text via an enchanting conjecture: that the writer, medium, and witch Roma Lister played a pivotal role in the formation of both Aradia and, therefore, a new form of paganism called Wicca.
★ 4.0 (1)
View paper →“For me, it is an intellectual freedom issue”: Drag storytimes, neutrality, and ALA core values
Shannon M. Oltmann, Vanessa Kitzie, Sarah Barriage
Journal of Librarianship and Information Science·2022·6 citations
<jats:p> Drag storytimes are increasingly popular programing events in which drag performers lead storytime in public libraries or other settings; they have been both popular and contentious. In this study, we utilized data from a national survey of 458 library staff and 26 subsequent interviews to investigate connections between drag storytime, intellectual freedom, neutrality, and other core librarianship values. The data was analyzed inductively and several key themes emerged: hosting drag storytimes is an intellectual freedom stance; various perspectives on the American Library Association stance in support of drag storytimes; connections to other core values; emphasizing diversity to serve one’s community; and contesting the neutrality of libraries. We found difficult-to-reconcile stances of “presenting all sides” and “taking a side,” but we suggest a way forward by focusing on the outcome of collective self-governance (based on core values of intellectual freedom and democracy). </jats:p>
★ 4.0 (1)
View paper →II: Notes for Lectures on "Private Experience" and "Sense Data"
Ludwig Wittgenstein
The Philosophical Review·1968·47 citations
No abstract available
★ 4.0 (1)
View paper →