When a recurrent neural network (RNN) language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in the RNN – conditioning the language model by ‘injecting’ image features – or in a layer following the RNN – conditioning the language model by ‘merging’ image features. While both options are attested in the literature, there is as yet no systematic comparison between the two. In this paper, we empirically show that it is not especially detrimental to performance whether one architecture is used or another. The merge architecture does have practical advantages, as conditioning by merging allows the RNN’s hidden state vector to shrink in size by up to four times. Our results suggest that the visual and linguistic modalities for caption generation need not be jointly encoded by the RNN as that yields large, memory-intensive models with few tangible advantages in performance; rather, the multimodal integration should be delayed to a subsequent stage.

Propagation Phase Contrast Synchrotron Microtomography (PPC-SRμCT) is the gold standard for non-invasive and non-destructive access to internal structures of archaeological remains. In this analysis, the virtual specimen needs to be segmented to separate different parts or materials, a process that normally requires considerable human effort. In the Automated SEgmentation of Microtomography Imaging (ASEMI) project, we developed a tool to automatically segment these volumetric images, using manually segmented samples to tune and train a machine learning model. For a set of four specimens of ancient Egyptian animal mummies we achieve an overall accuracy of 94–98% when compared with manually segmented slices, approaching the results of off-the-shelf commercial software using deep learning (97–99%) at much lower complexity. A qualitative analysis of the segmented output shows that our results are close in terms of usability to those from deep learning, justifying the use of these techniques.

Sepideh Mollanorozy, Marc Tanti, Malvina Nissim. Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP. 2023.

In this paper, we explore the generation of face images conditioned on a textual description, as well as the capabilities of the models in editing a machine-generated image on the basis of additional text prompts. We leverage open source state-of-the-art face image generators, StyleGAN models and couple these with the open source multimodal embedding space, CLIP, in an optimisation loop using the method in StyleCLIP to set up our experimental system. We make use of automatic metrics and human ratings to evaluate the results and, in addition, obtain insight into how much automatic metrics are correlated with human ratings. We found compelling evidence that both the text-to-image and editing models based on StyleGAN2 stand out as the better options. In addition, the automatic evaluation metrics are only weakly correlated with human ratings.

Résumé The main function of the Defense Health Service is to preserve the health of the projected forces. In this context, a Defense health watch duty was defined and entrusted to the Health observation Unit of the French Forces Institute of Tropical Medicine. To complete this mission, three documentation databases were created and broadcasted. Their updating, depending on innovation detection, requires a process of documentary awareness in six phases : definition of the topics to be supervised, selection of the documentary sources, gathering, analysis, reformatting and diffusion of the documents. The various phases are described and the process is evaluated in this article. The definition of the topics to be supervised shows its essential character to avoid the documents out-of-subject. The sources are selected on criteria of volumetry and cover. The gathering is automated by the tools of « push type » and RSS Feed (Really Simple Syndication). The innovation and the validity of the documents are evaluated according to a grid of definite reading. The documents are analyzed statistically by bibliometric tools. Formatted documents are finally spread via the owner network and by email. This process of documentary awareness, structured and organized, involves, for its users, an obvious saving of time. It allows an improvement in quantity and quality of the number of disseminated relevant information. However, it doesn’t yet allow to quantify in real time the number of users to the device.

Alcohol use disorders (AUD) is a major public health concern. General practitioners (GP) must play a key role in identifying this disorder and offering appropriate interventions. The authors conducted a survey among French GP in the Provence – Alpes – Côte-d’Azur (PACA) region to better understand their practices regarding AUD. Random sampling was used to enrol 101 GP in a 15-minute survey. A Computer-Assisted Telephone Interview exploring demographic and professional characteristics was conducted using a questionnaire. One third (31.7%) of the participants systematically addressed alcohol use with their patients whereas six (5.9%) never addressed it. Logistic regression analyses showed that after adjustment for the number of AUD patients followed up (odds ratio [OR] = 1.92; 95% confidence interval [CI] [1.19, 3.08]) and GP interest in addiction medicine (5.41 [2.17, 13.40]), GP who systematically screened patients for AUD were more likely to accept controlled drinking as a therapeutic goal (5.41 [2.17, 13.33]), and to perceive patient denial of AUD as a major barrier to care (1.39 [0.60, 3.22]). GP providing care for AUD were more likely to monitor tobacco cessation (9.08 [2.60, 31.64]) and to prescribe opioid maintenance treatment (7.35 [2.52, 21.41]). Alcohol screening is insufficient in general practice in France. Providing updated guidelines is essential to foster experience in this field among GP.