The role of temporal information in predicting human gaze in dynamic scenes remains a critical open question, underscored by the paradoxical finding that strong static models can outperform complex video-based models. This suggests that the true contribution of temporal cues has been obscured by confounding architectural variables. To resolve this, we present a rigorous, controlled experiment centered on a minimal architectural pair: a spatio-temporal saliency model (UniformerSal-ST) and its identical spatial-only counterpart (UniformerSal-S), designed to unambiguously isolate the impact of temporal feature integration. Our results demonstrate that principled temporal fusion yields a substantial Information Gain (IG) of +0.20 bits on temporally coherent datasets like LEDOV. Crucially, our controlled comparison also uncovers a key failure mode: on datasets with frequent hard cuts like DIEM, the same mechanism degrades performance, incurring a 0.07 bits IG deficit. We provide a mechanistic explanation for this dichotomy, revealing how certain visual scenarios (scene discontinuities, rapid camera zooms) can disrupt current temporal fusion approaches. By precisely quantifying both the benefits and drawbacks of temporal processing, our work provides the community with clear, actionable insights into when and why temporal information should be modeled for more robust and accurate video saliency prediction. The code will be made available at https: //github.com/peterjiz/uniformersal

MOTIVATION: Imaging mass spectrometry has emerged in the past decade as a label-free, spatially resolved and multi-purpose bioanalytical technique for direct analysis of biological samples. However, solving two everyday data analysis problems still requires expert judgment: (i) the detection of unknown molecules and (ii) the testing for presence of known molecules. RESULTS: We developed a measure of spatial chaos of a molecular image corresponding to a mass-to-charge value, which is a proxy for the molecular presence, and developed methods solving considered problems. The statistical evaluation was performed on a dataset from a rat brain section with test sets of molecular images selected by an expert. The measure of spatial chaos has shown high agreement with expert judges. The method for detection of unknown molecules allowed us to find structured molecular images corresponding to spectral peaks of any low intensity. The test for presence applied to a list of endogenous peptides ranked them according to the proposed measure of their presence in the sample. AVAILABILITY: The source code and test sets of mass-to-charge images are available at http://www.math.uni-bremen.de/∼theodore. SUPPLEMENTARY INFORMATION: Supplementary materials are available at Bioinformatics online. CONTACT: [email protected].

Resting state activity is brain activation that arises in the absence of any task, and is usually measured in awake subjects during prolonged fMRI scanning sessions where the only instruction given is to close the eyes and do nothing. It has been recognized in recent years that resting state activity is implicated in a wide variety of brain function. While certain networks of brain areas have different levels of activation at rest and during a task, there is nevertheless significant similarity between activations in the two cases. This suggests that recordings of resting state activity can be used as a source of unlabeled data to augment discriminative regression techniques in a semi-supervised setting. We evaluate this setting empirically yielding three main results: (i) regression tends to be improved by the use of Laplacian regularization even when no additional unlabeled data are available, (ii) resting state data may have a similar marginal distribution to that recorded during the execution of a visual processing task reinforcing the hypothesis that these conditions have similar types of activation, and (iii) this source of information can be broadly exploited to improve the robustness of empirical inference in fMRI studies, an inherently data poor domain.