Search

Traditional machine learning sequence models, such as RNN and LSTM, can solve sequential data problems with the use of internal memory states. However, the neuron units and weights are shared at each time step to reduce computational costs, limiting their ability to learn time-varying relationships between model inputs and outputs. In this context, this paper proposes two methods to characterize the dynamic relationships in real-world sequential data, namely, the internal time-varying sequence model (ITV model) and the external time-varying sequence model (ETV model). Our methods were designed with an automated basis expansion module to adapt internal or external parameters at each time step without requiring high computational complexity. Extensive experiments performed on synthetic and real-world data demonstrated superior prediction and classification results to conventional sequence models. Our proposed ETV model is particularly effective at handling long sequence data. [ABSTRACT FROM AUTHOR]

Cross modal retrieval can retrieve images through a text query and vice versa. In recent years, cross modal retrieval has attracted extensive attention. The purpose of most now available cross modal retrieval methods is to find a common subspace and maximize the different modal correlation. To generate specific representations consistent with cross modal tasks, this paper proposes a novel cross modal retrieval framework, which integrates feature learning and latent space embedding. In detail, we proposed a deep CNN and a shallow CNN to extract the feature of the samples. The deep CNN is used to extract the representation of images, and the shallow CNN uses a multi‐dimensional kernel to extract multi‐level semantic representation of text. Meanwhile, we enhance the semantic manifold by constructing cross modal ranking and within‐modal discriminant loss to improve the division of semantic representation. Moreover, the most representative samples are selected by using online sampling strategy, so that the approach can be implemented on a large‐scale data. This approach not only increases the discriminative ability among different categories, but also maximizes the relativity between different modalities. Experiments on three real word datasets show that the proposed method is superior to the popular methods. [ABSTRACT FROM AUTHOR]

Incremental Learning is a particular form of machine learning that enables a model to be modified incrementally, when new data becomes available. In this way, the model can adapt to the new data without the lengthy and time-consuming process required for complete model re-training. However, existing incremental learning methods face two significant problems: 1) noise in the classification sample data, 2) poor accuracy of modern classification algorithms when applied to modern classification problems. In order to deal with these issues, this paper proposes an integrated classification model, known as a Pre-trained Truncated Gradient Confidence-weighted (Pt-TGCW) model. Since the pre-trained model can extract and transform image information into a feature vector, the integrated model also shows its advantages in the field of image classification. Experimental results on ten datasets demonstrate that the proposed method outperform the original counterparts. [ABSTRACT FROM AUTHOR]

Hashing is an efficient method for nearest neighbor search in large-scale data space by embedding high-dimensional feature descriptors into a similarity preserving Hamming space with a low dimension. However, large-scale high-speed retrieval through binary code has a certain degree of reduction in retrieval accuracy compared to traditional retrieval methods. We have noticed that multi-view methods can well preserve the diverse characteristics of data. Therefore, we try to introduce the multi-view deep neural network into the hash learning field, and design an efficient and innovative retrieval model, which has achieved a significant improvement in retrieval performance. In this paper, we propose a supervised multi-view hash model which can enhance the multi-view information through neural networks. This is a completely new hash learning method that combines multi-view and deep learning methods. The proposed method utilizes an effective view stability evaluation method to actively explore the relationship among views, which will affect the optimization direction of the entire network. We have also designed a variety of multi-data fusion methods in the Hamming space to preserve the advantages of both convolution and multi-view. In order to avoid excessive computing resources on the enhancement procedure during retrieval, we set up a separate structure called memory network which participates in training together. The proposed method is systematically evaluated on the CIFAR-10, NUS-WIDE and MS-COCO datasets, and the results show that our method significantly outperforms the state-of-the-art single-view and multi-view hashing methods. [ABSTRACT FROM AUTHOR]

Correlation filter (CF) is a critical technique to improve accuracy and speed in the field of visual object tracking. Despite being studied extensively, most existing CF methods suffer from failing to make the most of the inherent spatial-temporal prior of videos. To address this limitation, as consecutive frames are eminently resemble in most videos, we investigate a novel scheme to predict targets’ future state by exploiting previous observations. Specifically, in this paper, we propose a prediction based CF tracking framework by learning the spatial-temporal similarity of consecutive frames for sample managing, template regularization, and training response pre-weighting. We model the learning problem theoretically as a novel objective and provide effective optimization algorithms to solve the learning task. In addition, we implement two CF trackers with different features. Extensive experiments are conducted on three popular benchmarks to validate our scheme. The encouraging results demonstrate that the proposed scheme can significantly boost the accuracy of CF tracking, and the two trackers achieve competitive performances against state-of-the-art trackers. We finally present a comprehensive analysis on the efficacy of our proposed method and the efficiency of our trackers to facilitate real-world visual tracking applications. [ABSTRACT FROM AUTHOR]

Image content analysis is an important surround perception modality of intelligent vehicles. In order to efficiently recognize the on-road environment based on image content analysis from the large-scale scene database, relevant images retrieval becomes one of the fundamental problems. To improve the efficiency of calculating similarities between images, hashing techniques have received increasing attentions. For most existing hash methods, the suboptimal binary codes are generated, as the hand-crafted feature representation is not optimally compatible with the binary codes. In this paper, a one-stage supervised deep hashing framework (SDHP) is proposed to learn high-quality binary codes. A deep convolutional neural network is implemented, and we enforce the learned codes to meet the following criterions: 1) similar images should be encoded into similar binary codes, and vice versa; 2) the quantization loss from Euclidean space to Hamming space should be minimized; and 3) the learned codes should be evenly distributed. The method is further extended into SDHP+ to improve the discriminative power of binary codes. Extensive experimental comparisons with state-of-the-art hashing algorithms are conducted on CIFAR-10 and NUS-WIDE, the MAP of SDHP reaches to 87.67% and 77.48% with 48 b, respectively, and the MAP of SDHP+ reaches to 91.16%, 81.08% with 12 b, 48 b on CIFAR-10 and NUS-WIDE, respectively. It illustrates that the proposed method can obviously improve the search accuracy. [ABSTRACT FROM PUBLISHER]

Large scale image understanding is a challenging but significant task to comprehend image contents on the internet. The de-facto standard methods based on machine learning or computer vision still suffer from a phenomenon of visual polysemia and concept polymorphism (VPCP). To resolve the VPCP, semantic dictionary has been proposed to characterize the membership distribution between visual appearances and semantic concepts. In this paper, we propose an online semantic dictionary learning algorithm on the base of both locality sensitive hashing (LSH) and stochastic approximations, which can scale up to large scale datasets with millions of training samples and speedup the efficiency of follow-up processing. With the help of the LSH-based semantic dictionary, we develop an extension of the spatial pyramid matching (SPM) kernel method by generalizing the dictionary as a basic semantic description. The efficiency of our approach is validated in the experiments of web-scale semantic image search and image classification on the ImageNet dataset and Caltech-256 dataset. [ABSTRACT FROM AUTHOR]

Compared with deadzone hard-decision quantization (HDQ), rate-distortion optimized quantization (RDOQ) in HEVC brings non-negligible coding gain, however consumes considerable computations caused by exhaustive search over multiple candidates to determine optimal output level. Benefiting from efficient prediction in HEVC, transform blocks are frequently quantized to all zero, especially in small-size blocks. It is worthwhile to detect all zero block (AZB) for transform blocks to bypass subsequent computation-intensive RDOQ. Traditional thresholding based AZB detection algorithms are well-suited for deadzone quantized blocks, however miss partial optimal results in RDOQ and suffer from more or less accuracy degradation in RDOQ. This paper proposes a novel multi-stage AZB detection algorithm for RDOQ blocks with good tradeoff between complexity and accuracy. At the first stage, genuine all zero blocks (G_AZB) which are quantized to all zero both in HDQ and RDOQ are prejudged by comparison with conservative threshold determined by mathematical derivation for deadzone HDQ. At the second stage, an adaptive threshold model is built using adaptive deadzone offset by simulating the behavior patterns existing in RDOQ, aiming to further detect the pseudo AZB (P_AZB) which are quantized to all zero in RDOQ however not all zero in HDQ. At the final stage, machine learning based detection is proposed to classify the remaining "cunning" all zero blocks using eight distinguished RDO-related features, by which subtle working mechanism in RDOQ is leveraged. The experimental results demonstrate that the proposed algorithm achieves up to 7.471% total coding computation saving with 0.064% BD-RATE increment compared with RDOQ on average. Moreover, the average FNR and FPR detection accuracies are 6.3% and 6.5% respectively. [ABSTRACT FROM AUTHOR]