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.
This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a profoundly different approach: we ask for annotations of the decision boundary. We achieve this using a deep generative model to create novel instances along a 1d line...
Syndrome coding is a very classical coding scheme in Physical layer security. It is necessary to design a efficient and secure code for syndrome coding to guarantee the security of the instant communications. In this paper, we apply two ways to construct random codes. By analysing on the effect of the parity check matrix on the average equivocation, we propose a method to generate the best random...
Automatic hand detection and accurate hand pose estimation from depth data in real system are challenging and vital tasks for human-computer interaction. In this paper, we introduce a Convolutional Neural Network (CNN) as Deep learning regression framework while employing an embedding denoising auto-encoder in the bottom layer of the network to learn latent representation of hand pose and account...
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)...
We develop the first approximate inference algorithm for 1-Best (and M-Best) decoding in bidirectional neural sequence models by extending Beam Search (BS) to reason about both forward and backward time dependencies. Beam Search (BS) is a widely used approximate inference algorithm for decoding sequences from unidirectional neural sequence models. Interestingly, approximate inference in bidirectional...
Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network...
Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information from the image to predict non-visual words such as the and of. Other words that may seem visual can often be predicted reliably just from the language model e...
Neural image/video captioning models can generate accurate descriptions, but their internal process of mapping regions to words is a black box and therefore difficult to explain. Top-down neural saliency methods can find important regions given a high-level semantic task such as object classification, but cannot use a natural language sentence as the top-down input for the task. In this paper, we...
Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems. However, it is challenging to reason about what a DNN actually does due to its opaque or black-box nature. To address this issue,...
Recent advances in video understanding are enabling incredible developments in video search, summarization, automatic captioning and human computer interaction. Attention mechanisms are a powerful way to steer focus onto different sections of the video. Existing mechanisms are driven by prior training probabilities and require input instances of identical temporal duration. We introduce an intuitive...
In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models. The proposed model naturally decomposes the problem of video captioning into vision and language segments, dealing with them as key-value pairs. More specifically, we learn a semantic embedding (v) corresponding to each frame (k) in the video,...
In order to defend adversarial attacks in computer vision models, the conventional approach arises on actively incorporate such samples into the training datasets. Nonetheless, the manual production of adversarial samples is painful and labor intensive. Here we propose a novel generative model: Convolutional Autoencoder Model to add unsupervised adversarial training, i.e., the production of adversarial...
Neural modelers in the domain of robot navigation, e.g. within the fields of neurorobotics and neuromorphic engineering, can benefit from a wealth of inspiration from neuroscientific research in the hippocampal formation — cell types such as place cells and grid cells provide a window into the inner workings of high-level cognitive processing, and have spawned many interesting computational models...
A central goal of neuroscience is to understand how the responses of populations of neurons and the connectivity patterns between groups of neurons allow brains to perform computations. The Neural Engineering Framework (NEF) is a promising approach to designing neural models that perform a wide range of computations. Emerging principles of efficient coding and divisive normalization from neuroscience...
This paper presents an adaptive clipping technique with optimized syntax in the video coding Joint Exploratory Model (JEM), which exploits the signal characteristics of the video sequence. The component-wise clipping bounds are coded for each slice. Two encoding methods leveraging the efficiency of the proposed technique are then described. The first one consists in modeling the errors induced by...
In this paper, we show that tensor compression techniques based on randomization and partial observations are very useful for spatial audio object coding. In this application, we aim at transmitting several audio signals called objects from a coder to a decoder. A common strategy is to transmit only the downmix of the objects along some small information permitting reconstruction at the decoder. In...
Deep neural network has obtained significant accuracy improvement in many large vocabulary continuous speech recognition (LVCSR) tasks. Recently, it was shown that even better performance can be obtained by modeling a larger number of more discriminative senones. However, as the neural network becomes larger, the number of parameters increases greatly, resulting in greater computation cost and slower...
Bayesian network is a probability, which is based on a probabilistic inference network of graphical and Bayesian formula is the basis of the probability of network. The paper analyzes general Semantic pixel naming and the implementation process and concept of Bayesian per pixel segmentation (BPPS). On this basis, author presents a novel deep learning framework for clustering and information mining...
The results of research and application of fuzzy logic on the control systems in the «atypical» (not in technical) area are offered. This is an estimation of testing diagnosis results within control system of education quality. To increase the accuracy and reliability of estimation of results of a given study in competence-based format, it is possible to use approved approaches and methods from contiguous...
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.