Traffic flow analysis largely depends on accurate predictions of microscopic speed. Due to the complexity and stochastic of real-world driving environments, traditional model-driven methods face significant challenges. In recent years, data-driven methods that combine advanced intelligent algorithms have emerged to address the issue of vehicle speed prediction. However, most existing studies primarily focus on the static spatiotemporal relationships between vehicles, with only a few exploring dynamic spatiotemporal correlations. In this study, a new graph structure, named the vehicle generalized-dynamic graph, is constructed to characterize the vehicle trajectory, emphasizing the spatial and temporal evolution of vehicles. In the spatial dimension, we employ the potential field theory to compute the field strength of vehicles in different motion states, enhancing the description of interdependencies among vehicles. In the temporal dimension, the movements of each vehicle at different time points are interrelated. Furthermore, we propose a novel neural network architecture, named the dynamic edge graph convolutional network (DEGCN), to address the vehicle speed prediction problem. The DEGCN model is evaluated through experiments on three real-world vehicle trajectory datasets. The experimental results demonstrate that the proposed model outperforms other baseline models in terms of prediction performance. Additionally, various ablation studies are conducted to evaluate the effectiveness of different components, the potential field theory, and the vehicle generalized-dynamic graph structure.

Speech recognition is becoming prevalent in daily life. However, due to the similar semantic context of the entities and the overlap of Chinese pronunciation, the pronoun homophone, especially “他/她/它 (he/she/it)”, (their pronunciation is “Tā”) is usually recognized incorrectly. It poses a challenge to automatically correct them during the post-processing of Chinese speech recognition. In this paper, we propose three models to address the common confusion issues in this domain, tailored to various application scenarios. We implement the language model, the LSTM model with semantic features, and the rule-based assisted Ngram model, enabling our models to adapt to a wide range of requirements, from high-precision to low-resource offline devices. The extensive experiments show that our models achieve the highest recognition rate for “Tā” correction with improvements from 70% in the popular voice input methods up to 90%. Further ablation analysis underscores the effectiveness of our models in enhancing recognition accuracy. Therefore, our models improve the overall experience of Chinese speech recognition of “Tā” and reduce the burden of manual transcription corrections.

The accurate prediction of traffic conditions is essential for effective and efficient traffic management and control. The dynamic and complex nature of traffic data, characterized by intricate temporal and spatial features, presents significant challenges to accurate traffic forecasting. While previous studies have developed various models with advanced algorithms, they often fail to fully capture the holistic spatio-temporal features and the dynamically evolving correlations within traffic networks. Additionally, these studies often overlook the potential of adjacency matrices learned from real-time traffic data to more accurately represent the interconnectivity of nodes within road network. To address these gaps, this study introduces the Generalized Dynamic Spatio-Temporal Graph Convolutional Network (GDSTGCN), a novel prediction model tailored for traffic data. First, this model builds a learning-based generalized dynamic graph structure, which incorporates both spatial and temporal connections and evolves with real-time traffic data. Then, a generalized dynamic graph convolution, integrated with graph diffusion, is crafted to operate on the designed generalized dynamic graph structure. This plays a critical role in holistically capturing local and global spatio-temporal traffic dependencies. Moreover, the generalized dynamic graph convolution is incorporated with Temporal convolution and other essential components, forming a cohesive framework that enables effective and efficient traffic flow predictions. To validate the performance of the GDSTGCN model, we conducted extensive experiments using four real-world road network datasets. The results demonstrate that our model outperforms existing state-of-the-art GCN-based models and traditional baseline methods.

This paper describes a fast and accurate semantic image segmentation approach that encodes not only segmentation-specified features but also high-order context compatibilities and boundary guidance constraints. We introduce a structured patch prediction technique to make a trade-off between classification discriminability and boundary sensibility for features. Both label and feature contexts are embedded to ensure recognition accuracy and compatibility, while the complexity of the high order cliques is reduced by a distance-aware sampling and pooling strategy. The proposed joint model also employs a guidance CRF to further enhance the segmentation performance. The message passing step is augmented with the guided filtering which enables an efficient and joint training of the whole system in an end-to-end fashion. Our proposed joint model outperforms the state-of-art on Pascal VOC 2012 and Cityscapes, with mIoU(%) of 82.5 and 79.2 respectively. It also reaches a leading performance on ADE20K, which is the dataset of the scene parsing track in ILSVRC 2016. The code is available at https://github.com/FalongShen/SegModel.

This paper describes a patchwork assembly algorithm for depth image super-resolution. An input low resolution depth image is disassembled into parts by matching similar regions on a set of high resolution training images, and a super-resolution image is then assembled using these corresponding matched counterparts. We convert the super resolution problem into a Markov Random Field (MRF) labeling problem, and propose a unified formulation embedding (1) the consistency between the resolution enhanced image and the original input, (2) the similarity of disassembled parts with the corresponding regions on training images, (3) the depth smoothness in local neighborhoods, (4) the additional geometric constraints from self-similar structures in the scene, and (5) the boundary coincidence between the resolution enhanced depth image and an optional aligned high resolution intensity image. Experimental results on both synthetic and real-world data demonstrate that the proposed algorithm is capable of recovering high quality depth images with X4 resolution enhancement along each coordinate direction, and that it outperforms state-of-the-arts [14] in both qualitative and quantitative evaluations.

This paper describes a multiple view based approach for building modeling via a novel multi-box grammar, which represents an occlusion relationship among the projections of a set of buildings sharing a common Manhattan World coordinate system. We formulate the building modeling problem as an energy minimization to combine the constraints from the multi-box grammar with (1) the semantic labeling information from appearance models, (2) the directional information w.r.t the vanishing points in each single view, and (3) the planar homography correspondence among multiple views. We further propose a two-step coarse-to-fine approach to achieve the optimal solution. First we employ super-pixels and a simplified edition of the grammar to reduce the searching space, and obtain an initial layout to accelerate the convergence speed. At the second stage, the scene model is refined to achieve pixel-level accuracy by minimizing the energy using Random Walk. Experiments on street view images demonstrate the capability of our method in reconstructing multiple buildings at different distances, and also the robustness in handling occlusion.

In this paper, we propose a new data structure for approximate nearest neighbor search. This structure augments the neighborhood graph with a bridge graph. We propose to exploit Cartesian concatenation to produce a large set of vectors, called bridge vectors, from several small sets of subvectors. Each bridge vector is connected with a few reference vectors near to it, forming a bridge graph. Our approach finds nearest neighbors by simultaneously traversing the neighborhood graph and the bridge graph in the best-first strategy. The success of our approach stems from two factors: the exact nearest neighbor search over a large number of bridge vectors can be done quickly, and the reference vectors connected to a bridge (reference) vector near the query are also likely to be near the query. Experimental results on searching over large scale datasets (SIFT, GISTand HOG) show that our approach outperforms state-of-the-art ANN search algorithms in terms of efficiency and accuracy. The combination of our approach with the IVFADC system [18] also shows superior performance over the BIGANN dataset of 1 billion SIFT features compared with the best previously published result.

The k-NN graph has played a central role in increasingly popular data-driven techniques for various learning and vision tasks; yet, finding an efficient and effective way to construct k-NN graphs remains a challenge, especially for large-scale high-dimensional data. In this paper, we propose a new approach to construct approximate k-NN graphs with emphasis in: efficiency and accuracy. We hierarchically and randomly divide the data points into subsets and build an exact neighborhood graph over each subset, achieving a base approximate neighborhood graph; we then repeat this process for several times to generate multiple neighborhood graphs, which are combined to yield a more accurate approximate neighborhood graph. Furthermore, we propose a neighborhood propagation scheme to further enhance the accuracy. We show both theoretical and empirical accuracy and efficiency of our approach to k-NN graph construction and demonstrate significant speed-up in dealing with large scale visual data.

Over-segments (i.e. superpixels) have been commonly used as supporting regions for feature vectors and primitives to reduce computational complexity in various image analysis tasks. In this paper, we describe a structuresensitive over-segmentation technique by exploiting Lloyd's algorithm with a geodesic distance. It generates smaller superpixels to achieve lower under-segmentation in structure-dense regions with high intensity or color variation, and produces larger segments to increase computational efficiency in structure-sparse regions with homogeneous appearance. We adopt geometric flows to compute the geodesic distances amongst pixels, and in the segmentation procedure, the density of over-segments is automatically adjusted according to an energy functional that embeds color homogeneity, structure density and compactness constraints. Comparative experiments with the Berkeley database show that the proposed algorithm outperforms prior arts while offering a comparable computational efficiency with fast methods, such as TurboPixels.