Abstract: Cross domain image retrieval is a challenging task that implies matching images from one domain to their pairs from another domain. In this paper we focus on fashion image retrieval, which involves matching an image of a fashion item taken by users, to the images of the same item taken in controlled condition, usually by professional photographer. When facing this problem, we have different products
in train and test time, and we use triplet loss to train the network. We stress the importance of proper training of simple architecture, as well as adapting general models to the specific task.

Abstract: Background:
Suicide risk assessment usually involves an interaction between doctors and patients. However, a significant number of people with mental disorders receive no treatment for their condition due to the limited access to mental health care facilities; the reduced availability of clinicians; the lack of awareness; and stigma, neglect, and discrimination surrounding mental disorders. In contrast, internet access and social media usage have increased significantly, providing experts and patients with a means of communication that may contribute to the development of methods to detect mental health issues among social media users.
Objective:
This paper aimed to describe an approach for the suicide risk assessment of Spanish-speaking users on social media. We aimed to explore behavioral, relational, and multimodal data extracted from multiple social platforms and develop machine learning models to detect users at risk.
Methods:
We characterized users based on their writings, posting patterns, relations with other users, and images posted. We also evaluated statistical and deep learning approaches to handle multimodal data for the detection of users with signs of suicidal ideation (suicidal ideation risk group). Our methods were evaluated over a dataset of 252 users annotated by clinicians. To evaluate the performance of our models, we distinguished 2 control groups: users who make use of suicide-related vocabulary (focused control group) and generic random users (generic control group).
Results:
We identified significant statistical differences between the textual and behavioral attributes of each of the control groups compared with the suicidal ideation risk group. At a 95% CI, when comparing the suicidal ideation risk group and the focused control group, the number of friends (P=.04) and median tweet length (P=.04) were significantly different. The median number of friends for a focused control user (median 578.5) was higher than that for a user at risk (median 372.0). Similarly, the median tweet length was higher for focused control users, with 16 words against 13 words of suicidal ideation risk users. Our findings also show that the combination of textual, visual, relational, and behavioral data outperforms the accuracy of using each modality separately. We defined text-based baseline models based on bag of words and word embeddings, which were outperformed by our models, obtaining an increase in accuracy of up to 8% when distinguishing users at risk from both types of control users.
Conclusions:
The types of attributes analyzed are significant for detecting users at risk, and their combination outperforms the results provided by generic, exclusively text-based baseline models. After evaluating the contribution of image-based predictive models, we believe that our results can be improved by enhancing the models based on textual and relational features. These methods can be extended and applied to different use cases related to other mental disorders.

Abstract: Approaches that use more than two consecutive video frames in the optical flow estimation have a long research history. However, almost all such methods utilize extra information for a pre-processing flow prediction or for a post-processing flow correction and filtering. In contrast, this paper differs from previously developed techniques. We propose a new algorithm for the likelihood function calculation (alternatively the matching cost volume) that is used in the maximum a posteriori estimation. We exploit the fact that in general, optical flow is locally constant in the sense of time and the likelihood function depends on both the previous and the future frame. Implementation of our idea increases the robustness of optical flow estimation. As a result, our method outperforms 9% over the DCFlow technique, which we use as prototype for our CNN based computation architecture, on the most challenging MPI-Sintel dataset for the non-occluded mask metric. Furthermore, our approach considerably increases the accuracy of the flow estimation for the matching cost processing, consequently outperforming the original DCFlow algorithm results up to 50% in occluded regions and up to 9% in non-occluded regions on the MPI-Sintel dataset. The experimental section shows that the proposed method achieves state-of-the-arts results especially on the MPI-Sintel dataset.

Abstract: Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g., due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might not align with the source domain classifier, still forms clear clusters. We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity. We observe that higher affinity should be assigned to reciprocal neighbors. To aggregate information with more context, we consider expanded neighborhoods with small affinity values. Furthermore, we consider the density around each target sample, which can alleviate the negative impact of potential outliers. In the experimental results we verify that the inherent structure of the target features is an important source of information for domain adaptation. We demonstrate that this local structure can be efficiently captured by considering the local neighbors, the reciprocal neighbors, and the expanded neighborhood. Finally, we achieve state-of-the-art performance on several 2D image and 3D point cloud recognition datasets.

Abstract: Image-to-image (I2I) translation has matured in recent years and is able to generate high-quality realistic images. However, despite current success, it still faces important challenges when applied to small domains. Existing methods use transfer learning for I2I translation, but they still require the learning of millions of parameters from scratch. This drawback severely limits its application on small domains. In this paper, we propose a new transfer learning for I2I translation (TransferI2I). We decouple our learning process into the image generation step and the I2I translation step. In the first step we propose two novel techniques: source-target initialization and self-initialization of the adaptor layer. The former finetunes the pretrained generative model (e.g., StyleGAN) on source and target data. The latter allows to initialize all non-pretrained network parameters without the need of any data. These techniques provide a better initialization for the I2I translation step. In addition, we introduce an auxiliary GAN that further facilitates the training of deep I2I systems even from small datasets. In extensive experiments on three datasets, (Animal faces, Birds, and Foods), we show that we outperform existing methods and that mFID improves on several datasets with over 25 points.

Abstract: Aesthetic image analysis is essential for improving the performance of multimedia image retrieval systems, especially from a repository of social media and multimedia content stored on mobile devices. This paper presents a novel method for classifying aesthetic natural scene images by studying the naturalness of image content using statistical features, and reading text in the images using semantic features. Unlike existing methods that focus only on image quality with human information, the proposed approach focuses on image features as well as text-based semantic features without human intervention to reduce the gap between subjectivity and objectivity in the classification. The aesthetic classes considered in this work are (i) Very Pleasant, (ii) Pleasant, (iii) Normal and (iv) Unpleasant. The naturalness is represented by features of focus, defocus, perceived brightness, perceived contrast, blurriness and noisiness, while semantics are represented by text recognition, description of the images and labels of images, profile pictures, and banner images. Furthermore, a deep learning model is proposed in a novel way to fuse statistical and semantic features for the classification of aesthetic natural scene images. Experiments on our own dataset and the standard datasets demonstrate that the proposed approach achieves 92.74%, 88.67% and 83.22% average classification rates on our own dataset, AVA dataset and CUHKPQ dataset, respectively. Furthermore, a comparative study of the proposed model with the existing methods shows that the proposed method is effective for the classification of aesthetic social media images.

Abstract: Transformer models have shown great success handling long-range interactions, making them a promising tool for modeling video. However, they lack inductive biases and scale quadratically with input length. These limitations are further exacerbated when dealing with the high dimensionality introduced by the temporal dimension. While there are surveys analyzing the advances of Transformers for vision, none focus on an in-depth analysis of video-specific designs. In this survey, we analyze the main contributions and trends of works leveraging Transformers to model video. Specifically, we delve into how videos are handled at the input level first. Then, we study the architectural changes made to deal with video more efficiently, reduce redundancy, re-introduce useful inductive biases, and capture long-term temporal dynamics. In addition, we provide an overview of different training regimes and explore effective self-supervised learning strategies for video. Finally, we conduct a performance comparison on the most common benchmark for Video Transformers (i.e., action classification), finding them to outperform 3D ConvNets even with less computational complexity.