With the popularity of electric vehicles (EVs) and the gradual maturity of the technology of bidirectional power transfer between EVs and the grid, EVs as a mobile energy storage device to achieve peak shaving and valley filling of the grid has become a hot point. Hence, we are committed to exploring the use of EVs to achieve spatial and temporal energy supply redistribution via V2G and G2V. We propose a multi-type bidirectional power transfer network and minimize the system cost by determining facility siting and pricing, which can be modeled as a bi-level optimization problem. In lower-level, a transportation and power coupled network is constructed considering the bidirectional interaction between EVs and the grid. We propose a new user equilibrium to explain the equilibrium state under bidirectional interaction, construct the optimal power flow model under the equilibrium state, use variational inequality to solve the minimum travel cost, and obtain the locational marginal price by solving the Lagrange duality variable of the active power. In upper-level, we propose the government’s construction of multi-type charging facilities siting planning to minimize transportation system cost and facilities operation costs. For experimental analysis, we consider various interactive scenarios of EVs and the grid and use three comparative models to verify the effectiveness of the proposed model. Results show that considering coupled network will effectively reduce the grid load and system cost. Notably, to provide more useful inspiration, we also have made a sensitivity analysis on the change of bidirectional transfer power and service price.

Grasp planning with high-performance and efficiency in unstructured environments is a critical problem that intelligent robots need to solve urgently to complete picking tasks. To solve this problem, a quantized grasp quality generative neural network is proposed to generate pixel-level grasps. A light-weight convolutional neural network is first used to generate initial grasp configurations. Aiming at the degradation of grasping performance caused by the light-weight design, a decoupled grasp quality network is designed to generate a pixel-wise grasp quality. To improve the robustness and generalization of the model, an adaptive filtering method is proposed to filter the grasp configurations. Then, an ellipse fitting-based grasp pose optimization method is proposed to obtain the final grasp configuration. On the public Cornell dataset, the state-of-the-art grasp accuracy of 98.9% and the efficiency of 15 ms are achieved, with approximately 564× fewer parameters compared to comparable performance. In the grasping experiments on the robotic platform, grasp success rates of 99% and 93.4% can be achieved in single object and cluttered scenes, respectively. Finally, the model is deployed on an embedded artificial intelligence (AI) computing device to verify its practicality.

Depth information can benefit various computer vision tasks on both images and videos. However, depth maps may suffer from invalid values in many pixels, and also large holes. To improve such data, we propose a joint self-supervised and reference-guided learning approach for depth inpainting. For the self-supervised learning strategy, we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge information. This module alternately learns a convolutional dictionary and sparse coding from a corrupted depth map. Then, both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map, which is effectively smoothed using local contextual information. The reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth values. We thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large holes. In summary, our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent information. Experimental results show that the proposed approach works well for both invalid value restoration and large hole inpainting.

Cross-domain weakly supervised object detection aims to adapt object-level knowledge from a fully labeled source domain dataset (i.e., with object bounding boxes) to train object detectors for target domains that are weakly labeled (i.e., with image-level tags). Instead of domain-level distribution matching, as popularly adopted in the literature, we propose to learn pixel-wise cross-domain correspondences for more precise knowledge transfer. It is realized through a novel cross-domain co-attention scheme trained as region competition. In this scheme, the cross-domain correspondence module seeks for informative features on the target domain image, which if warped to the source domain image, could best explain its annotations. Meanwhile, a collaborative mask generator competes to mask out the relevant target image region to make the remaining features uninformative. Such competitive learning strives to correlate the full foreground in cross-domain image pairs, revealing the accurate object extent in target domain. To alleviate the ambiguity of inter-domain correspondence learning, a domain-cycle consistency regularizer is further proposed to leverage the more reliable intra-domain correspondence. The proposed approach achieves consistent improvements over existing approaches by a considerable margin, demonstrated by the experiments on various datasets.

Large convolutional neural network models have recently demonstrated impressive performance on video attention prediction. Conventionally, these models are with intensive computation and large memory. To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net. The network is constructed based on depth-wise convolutions and takes low-resolution images as input. However, this straight-forward acceleration method will decrease performance dramatically. To this end, we propose a coupled knowledge distillation strategy to augment and train the network effectively. With this strategy, the model can further automatically discover and emphasize implicit useful cues contained in the data. Both spatial and temporal knowledge learned by the high-resolution complex teacher networks also can be distilled and transferred into the proposed low-resolution light-weight spatiotemporal network. Experimental results show that the performance of our model is comparable to 11 state-of-the-art models in video attention prediction, while it costs only 0.68 MB memory footprint, runs about 10,106 FPS on GPU and 404 FPS on CPU, which is 206 times faster than previous models.

As an emerging vision platform, a drone can look from many abnormal viewpoints which brings many new challenges into the classic vision task of video saliency prediction. To investigate these challenges, this paper proposes a large-scale video dataset for aerial saliency prediction, which consists of ground-truth salient object regions of 1,000 aerial videos, annotated by 24 subjects. To the best of our knowledge, it is the first large-scale video dataset that focuses on visual saliency prediction on drones. Based on this dataset, we propose a Model-guided Multi-path Network (MM-Net) that serves as a baseline model for aerial video saliency prediction. Inspired by the annotation process in eye-tracking experiments, MM-Net adopts multiple information paths, each of which is initialized under the guidance of a classic saliency model. After that, the visual saliency knowledge encoded in the most representative paths is selected and aggregated to improve the capability of MM-Net in predicting spatial saliency in aerial scenarios. Finally, these spatial predictions are adaptively combined with the temporal saliency predictions via a spatiotemporal optimization algorithm. Experimental results show that MM-Net outperforms ten state-of-the-art models in predicting aerial video saliency.

The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model. The knowledge of spatial and temporal saliency is first separately transferred from the two complex and redundant teachers to their simple and compact students, while the input scenes are also degraded from high-resolution to low-resolution to remove the probable data redundancy so as to greatly speed up the feature extraction process. After that, the desired spatiotemporal model is further trained by distilling and encoding the spatial and temporal saliency knowledge of two students into a unified network. In this manner, the inter-model redundancy can be removed for the effective estimation of dynamic saliency on aerial videos. Experimental results show that the proposed approach is comparable to 11 state-of-the-art models in estimating visual saliency on aerial videos, while its speed reaches up to 28,738 FPS and 1,490.5 FPS on the GPU and CPU platforms, respectively.

Attribute relation learning is important, but has been few studied. This paper proposes hybrid strategies for attribute relation acquisition from candidate attributes. The composition of candidate attributes is firstly analyzed and subdivided into three types: non-attribute vocabularies, invalid attribute, and valid attribute. Secondly, the HowNet-based filtering strategy is presented which filters out the non-attribute vocabularies and invalid attributes from the candidates using the knowledge of ldquois-ardquo relations and attribute-host relations described by attribute sememe in HowNet. Thirdly, the pruning strategy based on domain concept tree is proposed to further perfect the associations between a concept and its candidate attributes. We define some pruning rules through which some redundant, unreliable, even wrong attributes can be discarded from candidates and some lost attributes can be recalled. Our results about attribute relation learning show the efficiency of our hybrid strategies.