There has been extensive research on visual localization and odometry for autonomous robots and virtual reality during the past decades. Traditionally, this problem has been solved with the help of expensive sensors, such as light detection and ranging (LiDAR). Nowadays, the focus of the leading research in this field is on robust localization using more economic sensors, such as cameras and inertial measurement units. Consequently, geometric visual localization methods have become more accurate over time. However, these methods still suffer from significant loss and divergence in challenging environments, such as a room full of moving people. Scientists started using deep neural networks (DNNs) to mitigate this problem. The main idea behind using DNNs is to better understand challenging aspects of the data and overcome complex conditions such as the movement of a dynamic object in front of the camera that covers the full view of the camera, extreme lighting conditions, and the high speed of the camera. Prior end-to-end DNN methods did overcome some of these challenges. However, no general and robust framework is available to overcome all challenges together. In this article, we have combined geometric and DNN-based methods to have the generality and speed of geometric SLAM frameworks and overcome most of these challenging conditions with the help of DNNs and deliver the most robust framework so far. To do so, we have designed a framework based on VINS-Mono and shown that it can achieve state-of-the-art results on TUM-Dynamic, TUM-VI, ADVIO, and EuRoC datasets compared to geometric and end-to-end DNN-based simultaneous localization and mappings. Our proposed framework can also achieve outstanding results on extreme simulated cases resembling the aforementioned challenges.

Abstract With significant advances in vision and natural language processing, the generation of image captions becomes a need. Mathews, Xie, and He extended a new model to generate styled captions by separating semantics and style. In continuation of their work, here, a new captioning model is developed, including an image encoder to extract the features, a mixture of recurrent networks to embed the set of extracted features to a group of words, and a sentence generator that combines the obtained words as a stylized sentence. This Mixture of Recurrent Experts (MoRE) system uses a new training algorithm that derives singular value decomposition from weighting matrices of Recurrent Neural Networks (RNNs) to increase the diversity of captions. Each decomposition step depends on a distinctive factor based on the number of RNNs in MoRE. The used sentence generator gives a stylized language corpus without paired images. Besides, the styled and diverse captions are extracted without training on a densely labeled or styled dataset. MoRE on the COCO dataset generated diverse and stylized image captions without the necessity of extra‐labeling and improved descriptions in terms of content accuracy.

We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relations between individual persons in image or video. It learns to produce an intermediate spatial representation (activity map) based on individual and group activities. A multi-stage refinement component is responsible for decreasing the incorrect predictions in the activity map. Finally, an aggregation component uses the refined information to recognize group activities. Experimental results demonstrate the constructive contribution of the information extracted and represented in the form of the activity map. CRM shows advantages over state-of-the-art models on Volleyball and Collective Activity datasets.

In this paper, a new variant of the PSO algorithm called dynamic niching particle swarm optimizer (DNPSO) is proposed. Similar to basic PSO, DNPSO is a global optimization algorithm in which the main population of the particles is divided into some sub-swarms and a group of free particles. A new sub-swarm forming algorithm is proposed. This new form of sub-swarm creation, combined with free particles which implement a cognition-only model of PSO, brings about a great balance between exploration and exploitation characteristics of the standard PSO. DNPSO is tested with some well-known and widely used benchmark functions and the results are compared with several PSO-based multi-modal optimization methods. The results show that in all cases, DNPSO provides the best solutions.

In our previous work, we proposed DNPSO (Dynamic Niching Particle Swarm Optimizer) and evaluated its performance in static multi-modal functions. DNPSO is a multiswarm technique in which the main swarm is divided into some sub-swarms and a number of free particles. Due to the dynamic creation and deletion of sub-swarms, DNPSO is able to provide a good performance both in static multi-modal and dynamic optimization problems. In this paper, the performance of DNPSO is investigated using two different dynamic function generators. Experimental results for three different dynamic environments show that DNPSO is a suitable algorithm for these types of problems and can completely outperform PSO.