Search

Adnexal torsion is a spontaneous rotation of the ovary and sometimes the fallopian tube around its axis which can interfere with arterial supply and lead to ischemia It is a rare complication of an ovarian cyst, which can occur at any age, from the fetal period to adulthood. The mature cystic teratoma accounts for 20% of all ovarian tumors and is seen especially in young girls and therefore is most often benign. It's a surgical emergency. We report here two cases of adnexal torsion operated at the level of the pediatric surgery unit of the Hospital of Mali The two girls are 14 and 13 years old, nulligest and normoregulated with recurrent abdominal pain admitted for acute pelvic pain. On palpation, an abdomino-pelvic mass of a firm and painful consistency is noted. An abdominopelvic ultrasound was performed in both cases and revealed torsion of the left adnexa on the left ovarian cyst in the first and on the right in the second. The surgical procedure performed was manual detorsion and cystectomy in both cases. The anatomopathological examination concluded with a dermoid cyst In the two girls and their postoperative course was simple.

The objective of our study was to assess levels of knowledge about Human Papillomavirus, attitudes and acceptability of vaccination. This was a cross-sectional, descriptive and analytical study conducted at the Nabil Choucair and Philippe Maguilen Senghor Health Centers during the period from January 1 to May 30, 2019 (5 months). The parameters studied in these health workers were age, education, ethnicity, occupation, marital status, knowledge of human papillomavirus, and knowledge and acceptability of cervical cancer vaccination. Data collection was done with Epi info version 7 and data analysis with Spss (Statistical Package for the social sciences) version 21. In our series, 95 health workers were enrolled. The average age of the health workers was 30.9 years, with extremes from 21 to 57 years, and the majority were doctors (65.3%). In this study 92.6% of the agents knew about HPV. The acceptability of taking the HPV vaccine was noted in only 47.4% of the agents.

The goal of this paper is to bypass the need for labelled examples in few-shot video understanding at run time. While proven effective, in many practical video settings even labelling a few examples appears unrealistic. This is especially true as the level of details in spatio-temporal video understanding and with it, the complexity of annotations continues to increase. Rather than performing few-shot learning with a human oracle to provide a few densely labelled support videos, we propose to automatically learn to find appropriate support videos given a query. We call this self-shot learning and we outline a simple self-supervised learning method to generate an embedding space well-suited for unsupervised retrieval of relevant samples. To showcase this novel setting, we tackle, for the first time, video instance segmentation in a self-shot (and few-shot) setting, where the goal is to segment instances at the pixel-level across the spatial and temporal domains. We provide strong baseline performances that utilize a novel transformer-based model and show that self-shot learning can even surpass few-shot and can be positively combined for further performance gains. Experiments on new benchmarks show that our approach achieves strong performance, is competitive to oracle support in some settings, scales to large unlabelled video collections, and can be combined in a semi-supervised setting. Code: https://github.com/PengWan-Yang/self-shot

Multi-modal retrieval is an important problem for many applications, such as recommendation and search. Current benchmarks and even datasets are often manually constructed and consist of mostly clean samples where all modalities are well-correlated with the content. Thus, current video-text retrieval literature largely focuses on video titles or audio transcripts, while ignoring user comments, since users often tend to discuss topics only vaguely related to the video. Despite the ubiquity of user comments online, there is currently no multi-modal representation learning datasets that includes comments. In this paper, we a) introduce a new dataset of videos, titles and comments; b) present an attention-based mechanism that allows the model to learn from sometimes irrelevant data such as comments; c) show that by using comments, our method is able to learn better, more contextualised, representations for image, video and audio representations. Project page: https://unitaryai.github.io/vtc-paper., Accepted paper at the European Conference on Computer Vision (ECCV) 2022

This paper aims to accelerate video stream processing, such as object detection and semantic segmentation, by leveraging the temporal redundancies that exist between video frames. Instead of propagating and warping features using motion alignment, such as optical flow, we propose a novel knowledge distillation schema coined as Delta Distillation. In our proposal, the student learns the variations in the teacher’s intermediate features over time. We demonstrate that these temporal variations can be effectively distilled due to the temporal redundancies within video frames. During inference, both teacher and student cooperate for providing predictions: the former by providing initial representations extracted only on the key-frame, and the latter by iteratively estimating and applying deltas for the successive frames. Moreover, we consider various design choices to learn optimal student architectures including an end-to-end learnable architecture search. By extensive experiments on a wide range of architectures, including the most efficient ones, we demonstrate that delta distillation sets a new state of the art in terms of accuracy vs. efficiency trade-off for semantic segmentation and object detection in videos. Finally, we show that, as a by-product, delta distillation improves the temporal consistency of the teacher model.

Despite the recent success of video self-supervised learning models, there is much still to be understood about their generalization capability. In this paper, we investigate how sensitive video self-supervised learning is to the current conventional benchmark and whether methods generalize beyond the canonical evaluation setting. We do this across four different factors of sensitivity: domain, samples, actions and task. Our study which encompasses over 500 experiments on 7 video datasets, 9 self-supervised methods and 6 video understanding tasks, reveals that current benchmarks in video self-supervised learning are not good indicators of generalization along these sensitivity factors. Further, we find that self-supervised methods considerably lag behind vanilla supervised pre-training, especially when domain shift is large and the amount of available downstream samples are low. From our analysis we distill the SEVERE-benchmark, a subset of our experiments, and discuss its implication for evaluating the generalizability of representations obtained by existing and future self-supervised video learning methods. Code is available at https://github.com/fmthoker/SEVERE-BENCHMARK.

In recent years, neural implicit representations have made remarkable progress in modeling of 3D shapes with arbitrary topology. In this work, we address two key limitations of such representations, in failing to capture local 3D geometric fine details, and to learn from and generalize to shapes with unseen 3D transformations. To this end, we introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details and guaranteed robustness to various groups of geometric transformations, through local $k$-NN graph embeddings with sparse point set observations at multiple resolutions. Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 (IoU) on the ShapeNet reconstruction task. We also show that our equivariant implicit function can be extended to other types of similarity transformations and generalizes to unseen translations and scaling., Comment: Video: https://youtu.be/W7goOzZP2Kc

The standard approach to contrastive learning is to maximize the agreement between different views of the data. The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects. The supervisory signal comes from maximizing the total similarity over positive pairs, while the negative pairs are needed to avoid collapse. In this work, we note that the approach of considering individual pairs cannot account for both intra-set and inter-set similarities when the sets are formed from the views of the data. It thus limits the information content of the supervisory signal available to train representations. We propose to go beyond contrasting individual pairs of objects by focusing on contrasting objects as sets. For this, we use combinatorial quadratic assignment theory designed to evaluate set and graph similarities and derive set-contrastive objective as a regularizer for contrastive learning methods. We conduct experiments and demonstrate that our method improves learned representations for the tasks of metric learning and self-supervised classification.