We propose a novel algorithm for offline reinforcement learning using optimal transport. Typically, in offline reinforcement learning, the data is provided by various experts and some of them can be sub-optimal. To extract an efficient policy, it is necessary to \emph{stitch} the best behaviors from the dataset. To address this problem, we rethink offline reinforcement learning as an optimal transportation problem. And based on this, we present an algorithm that aims to find a policy that maps states to a \emph{partial} distribution of the best expert actions for each given state. We evaluate the performance of our algorithm on continuous control problems from the D4RL suite and demonstrate improvements over existing methods.

Despite recent impressive results of generative adversarial networks on text-to-image generation, the generation of complex scenes with multiple objects in the complicated background remains challenging; moreover, end-to-end text-toimage generation still suffers from poor image quality. In this work, we propose a sequential algorithm of text-to-image generation, which allows synthesizing high-quality images (more than 1024x1024 pixels). The proposed approach consists of location inference, key objects extraction, image search, layout generation, and image harmonization stages. We compare the suggested approach with state-of-the-art image generation model DALL-E with text-to-image mapping. Our approach demonstrates the effectiveness and visual plausibility of the generated images based on golden section layouts.

Episodic memory lets reinforcement learning algorithms remember and exploit promising experience from the past to improve agent performance. Previous works on memory mechanisms show benefits of using episodic-based data structures for discrete action problems in terms of sample-efficiency. The application of episodic memory for continuous control with a large action space is not trivial. Our study aims to answer the question: can episodic memory be used to improve agent's performance in continuous control? Our proposed algorithm combines episodic memory with Actor-Critic architecture by modifying critic's objective. We further improve performance by introducing episodic-based replay buffer prioritization. We evaluate our algorithm on OpenAI gym domains and show greater sample-efficiency compared with the state-of-the art model-free off-policy algorithms.

In this technical demonstration, we showcase the World's first personality-driven marketing content generation platform, called SoMin.ai. The platform combines deep multi-view personality profiling framework and style generative adversarial networks facilitating the automatic creation of content that appeals to different human personality types. The platform can be used for enhancement of the social networking user experience as well as for content marketing routines. Guided by the MBTI personality type, automatically derived from a user social network content, SoMin.ai generates new social media content based on the preferences of other users with a similar personality type aiming at enhancing the user experience on social networking venues as well diversifying the efforts of marketers when crafting new content for digital marketing campaigns. The real-time user feedback to the platform via the platform's GUI fine-tunes the content generation model and the evaluation results demonstrate the promising performance of the proposed multi-view personality profiling framework when being applied in the content generation scenario. By leveraging content generation at a large scale, marketers will be able to execute more effective digital marketing campaigns at a lower cost.

When taking photos of historical buildings and landmarks, one can often encounter more modern and less attractive objects blocking the view (poles, electricity cables, road signs, and others). Photographers strive to take the unobstructed shot, without random objects popping up in the image. However, they avoid deleting unwanted objects with inpainting or exemplar-based methods, because it can introduce notable artefacts. We propose a new algorithm for removing large static objects such as road signs, sitting people, and parked cars from a photograph keeping its originality and unique details. We do not use artificial patterns to fill covered regions, only two shots taken from different angles. Usually, removing long thin objects such as road sign poles cause image deformations, but our approach avoids this. For comparison, we created a dataset from “Caltech Buildings” and “Kaggle Architecture” Datasets and added road signs, cars, and other objects to photos. We compared our approach with state-of-the-art methods such as Deep Image Prior, Gated Convolution, and the Region Filling by block sampling. The real photographs of historical building demonstrate the effectiveness of our algorithm. Code and example images are available on GitHub1.

Nowadays, video games play a very important role in human life and no longer purely associated with escapism or entertainment. In fact, gaming has become an essential part of our daily routines, which give rise to the exponential growth of various online game platforms. By participating in such platforms, individuals generate a multitude of game data points, which, for example, can be further used for automatic user profiling and recommendation applications. However, the literature on automatic learning from the game data is relatively sparse, which had inspired us to tackle the problem of player profiling in this first preliminary study. Specifically, in this work, we approach the task of player gender prediction based on various types of game data. Our initial experimental results inspire further research on user profiling in the game domain.

Automated text recognition is used in autonomous driving systems, search engines, document analysis, and many other applications. There are many techniques to extract text information from scanned documents, but text recognition from arbitrary images is a much harder task. Recently suggested deep learning approaches have demonstrated highquality results, but they require a huge amount of data to achieve them. The process of collecting and labelling training data to train a deep learning network is costly. In this paper, we suggest an approach for automatic dataset generation for text recognition for arbitrary languages. We use a generative adversarial network structure, which is adapted to generate readable and clear text looking naturally on the image background. We evaluate our approach using SegLink and Textboxes++ text localization models, which were trained on examples generated by SynthText and by variations of our method. The comparison showed the superiority of our method on a subset of the ICDAR 2017 dataset for English and Arabic languages.

Deep neural networks help solving different images related tasks very efficiently, though their cost is high whereas a lot of data are required for training. While there is a great demand to build neural network models for optical character detection and recognition for different languages, such as, for mobile real-time applications, datasets collecting and labeling are quite expensive. In this paper, we propose the fully automated approach for synthetic images with text generation based on deep learning and projective geometry methods. For evaluation, we trained two neural networks on the dataset generated by our algorithm. Our approach enables to decrease the false negative rate on real images from SVT and SVT-50 datasets in comparison with training on SynthText dataset, giving ~1% of F1-measure increasing.

The smart grid is envisioned as a reconfigurable energy exchange network that is resilient to failures. An expected feature of the future smart grid is optimal power distribution from energy producers to consumers, also referred to as network operation planning. This entails allocating finite energy resources to customers in order to optimally satisfy all customer demands, subject to constraints on the topology of the graph. We model this problem as the Capacitated Spanning Forest Problem (CSF), namely the optimization problem of creating a spanning forest with a capacity constraint on each tree limiting its total weight. We present a new heuristic algorithm for solving CSF based on computing the minimum-cost maximum flow on the graph. Our algorithm outperforms state of the art approaches with respect to solution quality and running time.

The exponential growth of online social networks has inspired us to tackle the problem of individual user attributes inference from the Big Data perspective. It is well known that various social media networks exhibit different aspects of user interactions, and thus represent users from diverse points of view. In this preliminary study, we make the first step towards solving the significant problem of personality profiling from multiple social networks. Specifically, we tackle the task of relationship prediction, which is closely related to our desired problem. Experimental results show that the incorporation of multi-source data helps to achieve better prediction performance as compared to single-source baselines.

Venue category recommendation is an essential application for the tourism and advertisement industries, wherein it may suggest attractive localities within close proximity to users' current location. Considering that many adults use more than three social networks simultaneously, it is reasonable to leverage on this rapidly growing multi-source social media data to boost venue recommendation performance. Another approach to achieve higher recommendation results is to utilize group knowledge, which is able to diversify recommendation output. Taking into account these two aspects, we introduce a novel cross-network collaborative recommendation framework C3R, which utilizes both individual and group knowledge, while being trained on data from multiple social media sources. Group knowledge is derived based on new cross-source user community detection approach, which utilizes both inter-source relationship and the ability of sources to complement each other. To fully utilize multi-source multi-view data, we process user-generated content by employing state-of-the-art text, image, and location processing techniques. Our experimental results demonstrate the superiority of our multi-source framework over state-of-the-art baselines and different data source combinations. In addition, we suggest a new approach for automatic construction of inter-network relationship graph based on the data, which eliminates the necessity of having pre-defined domain knowledge.