The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Agent-based modeling is a paradigm of modeling dynamic systems of interacting agents that are individually governed by specified behavioral rules. Training a model of such agents to produce an emergent behavior by specification of the emergent (as opposed to agent) behavior is easier from a demonstration perspective. Without the involvement of manual behavior specification via code or reliance on...
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively...
We propose “Areas of Attention”, a novel attentionbased model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attentionbased approaches that associate image regions only to the RNN state, our method allows a direct association between caption...
In this study, we investigated the effects of mastering multiple scripts in handwritten character recognition by means of computational simulations. In particular, we trained a set of deep neural networks on two different datasets of handwritten characters: the HODA dataset, which is a collection of images of handwritten Persian digits, and the MNIST dataset, which contains Latin handwritten digits...
Most present methods of saliency detection emphasize too much on the local contrast while ignore the global feature of image. The detailed characteristics of the image can be reflected based on the local comparison of image. However, the overall saliency of the image cannot be reflected. In this paper, a saliency detection model combined local and global features was proposed. Firstly, a local feature...
The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen...
This paper introduces a probabilistic latent variable model to address unsupervised domain adaptation problems. Specifically, we tackle the task of categorization of visual input from different domains by learning projections from each domain to a latent (shared) space jointly with the classifier in the latent space, which simultaneously minimizes the domain disparity while maximizing the classifier's...
In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its...
Video image dataset is playing an essential role in design and evaluation of traffic vision methods. However, there is a longstanding difficulty that manually collecting and annotating large-scale diversified dataset from real scenes is time-consuming and prone to error. In 2016, we proposed the parallel vision methodology to tackle the issues of conventional vision computing approach in data collection,...
The contribution of this paper is to bridge the gap on understanding the mathematical structure and the computational implementation of a convolutional neural network (CNN) using a minimal model (Minimal CNN). The proposed minimal CNN is presented using a layering approach. This approach provides a concise and accessible understanding of the main mathematical operations of a CNN. Hence, it benefits...
Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks. Among these elements, character is the most basic one for various languages such as Western, Chinese, Japanese, mathematical expression and etc. It is natural and convenient to construct a common text detection engine based on character detectors. However, training character...
Area V5 or Middle Temporal (MT) area of the primate brain is said to be involved in visual motion perception. Physiological studies indicate that the neurons in MT respond selectively to the direction of moving stimuli. However in response to the complex stimuli containing multiple oriented components, a set of MT neurons are selective to the direction of the component motion whereas the other set...
CNNs have made an undeniable impact on computer vision through the ability to learn high-capacity models with large annotated training sets. One of their remarkable properties is the ability to transfer knowledge from a large source dataset to a (typically smaller) target dataset. This is usually accomplished through fine-tuning a fixed-size network on new target data. Indeed, virtually every contemporary...
This paper proposes a method for generative learning of hierarchical random field models. The resulting model, which we call the hierarchical sparse FRAME (Filters, Random field, And Maximum Entropy) model, is a generalization of the original sparse FRAME model by decomposing it into multiple parts that are allowed to shift their locations, scales and rotations, so that the resulting model becomes...
Unsupervised learning of visual similarities is of paramount importance to computer vision, particularly due to lacking training data for fine-grained similarities. Deep learning of similarities is often based on relationships between pairs or triplets of samples. Many of these relations are unreliable and mutually contradicting, implying inconsistencies when trained without supervision information...
Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space to a semantic embedding space (e.g. attribute space). However, such a projection function is only concerned with predicting the training seen class semantic representation (e.g. attribute prediction) or classification. When applied to test data, which in the context of ZSL contains different (unseen)...
Our paper presents a new approach for temporal detection of human actions in long, untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST), a new effective and efficient deep architecture for the generation of temporal action proposals. Our network can run continuously in a single stream over very long input video sequences, without the need to divide input into short...
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic subspace explained by training classes. Thus, the former is able to constrain the whole space but lacks the ability to model semantic correlations. The latter addresses...
Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified framework for the tasks of referring expression comprehension and generation. Our model is composed of three modules: speaker, listener, and reinforcer. The speaker generates referring expressions, the listener comprehends referring expressions, and the reinforcer...
We present a novel visual attention tracking technique based on Shared Attention modeling. By considering the viewer as a participant in the activity occurring in the scene, our model learns the loci of attention of the scene actors and use it to augment image salience. We go beyond image salience and instead of only computing the power of image regions to pull attention, we also consider the strength...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.