As a natural extension of the image synthesis task, video synthesis has attracted a lot of interest recently. Many image synthesis works utilize class labels or text as guidance. However, neither labels nor text can provide explicit temporal guidance, such as when an action starts or ends. To overcome this limitation, we introduce semantic video scene graphs as input for video synthesis, as they represent the spatial and temporal relationships between objects in the scene. Since video scene graphs are usually temporally discrete annotations, we propose a video scene graph (VSG) encoder that not only encodes the existing video scene graphs but also predicts the graph representations for unlabeled frames. The VSG encoder is pre-trained with different contrastive multi-modal losses. A semantic scene graph-to-video synthesis framework (SSGVS), based on the pre-trained VSG encoder, VQ-VAE, and auto-regressive Transformer, is proposed to synthesize a video given an initial scene image and a non-fixed number of semantic scene graphs. We evaluate SSGVS and other state-of-the-art video synthesis models on the Action Genome dataset and demonstrate the positive significance of video scene graphs in video synthesis. The source code will be released.

同一场景中的不同对象彼此之间或多或少相关，但是只有有限数量的这些关系值得注意。受到对象检测效果的DETR的启发，我们将场景图生成视为集合预测问题，并提出了具有编码器decoder架构的端到端场景图生成模型RELTR。关于视觉特征上下文的编码器原因是，解码器使用带有耦合主题和对象查询的不同类型的注意机制渗透了一组固定大小的三胞胎主题prodicate-object。我们设计了一套预测损失，以执行地面真相与预测三胞胎之间的匹配。与大多数现有场景图生成方法相反，Reltr是一种单阶段方法，它仅使用视觉外观直接预测一组关系，而无需结合实体并标记所有可能的谓词。视觉基因组和开放图像V6数据集的广泛实验证明了我们模型的出色性能和快速推断。

KL-regularized reinforcement learning from expert demonstrations has proved successful in improving the sample efficiency of deep reinforcement learning algorithms, allowing them to be applied to challenging physical real-world tasks. However, we show that KL-regularized reinforcement learning with behavioral reference policies derived from expert demonstrations can suffer from pathological training dynamics that can lead to slow, unstable, and suboptimal online learning. We show empirically that the pathology occurs for commonly chosen behavioral policy classes and demonstrate its impact on sample efficiency and online policy performance. Finally, we show that the pathology can be remedied by non-parametric behavioral reference policies and that this allows KL-regularized reinforcement learning to significantly outperform state-of-the-art approaches on a variety of challenging locomotion and dexterous hand manipulation tasks.

In this work, we propose a new approach that combines data from multiple sensors for reliable obstacle avoidance. The sensors include two depth cameras and a LiDAR arranged so that they can capture the whole 3D area in front of the robot and a 2D slide around it. To fuse the data from these sensors, we first use an external camera as a reference to combine data from two depth cameras. A projection technique is then introduced to convert the 3D point cloud data of the cameras to its 2D correspondence. An obstacle avoidance algorithm is then developed based on the dynamic window approach. A number of experiments have been conducted to evaluate our proposed approach. The results show that the robot can effectively avoid static and dynamic obstacles of different shapes and sizes in different environments.

Salient object detection (SOD) aims to determine the most visually attractive objects in an image. With the development of virtual reality technology, 360{\deg} omnidirectional image has been widely used, but the SOD task in 360{\deg} omnidirectional image is seldom studied due to its severe distortions and complex scenes. In this paper, we propose a Multi-Projection Fusion and Refinement Network (MPFR-Net) to detect the salient objects in 360{\deg} omnidirectional image. Different from the existing methods, the equirectangular projection image and four corresponding cube-unfolding images are embedded into the network simultaneously as inputs, where the cube-unfolding images not only provide supplementary information for equirectangular projection image, but also ensure the object integrity of the cube-map projection. In order to make full use of these two projection modes, a Dynamic Weighting Fusion (DWF) module is designed to adaptively integrate the features of different projections in a complementary and dynamic manner from the perspective of inter and intra features. Furthermore, in order to fully explore the way of interaction between encoder and decoder features, a Filtration and Refinement (FR) module is designed to suppress the redundant information between the feature itself and the feature. Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively.

Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders. Previous research has demonstrated that probabilistic statistical methods based on syntactic rules are particularly effective in constituency parsing, whereas syntactic rules are not used during the training of neural models in prior work probably due to their enormous computation requirements. In this paper, we first implement a fast CKY decoding procedure harnessing GPU acceleration, based on which we further derive a syntactic rule-based (rule-constrained) CKY decoding. In the experiments, our method obtains 95.89 and 92.52 F1 on the datasets of PTB and CTB respectively, which shows significant improvements compared with previous approaches. Besides, our parser achieves strong and competitive cross-domain performance in zero-shot settings.

This paper aims to improve the Warping Planer Object Detection Network (WPOD-Net) using feature engineering to increase accuracy. What problems are solved using the Warping Object Detection Network using feature engineering? More specifically, we think that it makes sense to add knowledge about edges in the image to enhance the information for determining the license plate contour of the original WPOD-Net model. The Sobel filter has been selected experimentally and acts as a Convolutional Neural Network layer, the edge information is combined with the old information of the original network to create the final embedding vector. The proposed model was compared with the original model on a set of data that we collected for evaluation. The results are evaluated through the Quadrilateral Intersection over Union value and demonstrate that the model has a significant improvement in performance.

Semantic communication (SemCom) and edge computing are two disruptive solutions to address emerging requirements of huge data communication, bandwidth efficiency and low latency data processing in Metaverse. However, edge computing resources are often provided by computing service providers and thus it is essential to design appealingly incentive mechanisms for the provision of limited resources. Deep learning (DL)- based auction has recently proposed as an incentive mechanism that maximizes the revenue while holding important economic properties, i.e., individual rationality and incentive compatibility. Therefore, in this work, we introduce the design of the DLbased auction for the computing resource allocation in SemComenabled Metaverse. First, we briefly introduce the fundamentals and challenges of Metaverse. Second, we present the preliminaries of SemCom and edge computing. Third, we review various incentive mechanisms for edge computing resource trading. Fourth, we present the design of the DL-based auction for edge resource allocation in SemCom-enabled Metaverse. Simulation results demonstrate that the DL-based auction improves the revenue while nearly satisfying the individual rationality and incentive compatibility constraints.

In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles. In practice, the ground plane is dynamically changed due to braking and unstable road surface. As a result, the vehicle pose, especially the pitch angle, is oscillating from subtle to obvious. Thus, estimating ground plane normal is meaningful since it can be encoded to improve the robustness of various autonomous driving tasks (e.g., 3D object detection, road surface reconstruction, and trajectory planning). Our proposed method only uses odometry as input and estimates accurate ground plane normal vectors in real time. Particularly, it fully utilizes the underlying connection between the ego pose odometry (ego-motion) and its nearby ground plane. Built on that, an Invariant Extended Kalman Filter (IEKF) is designed to estimate the normal vector in the sensor's coordinate. Thus, our proposed method is simple yet efficient and supports both camera- and inertial-based odometry algorithms. Its usability and the marked improvement of robustness are validated through multiple experiments on public datasets. For instance, we achieve state-of-the-art accuracy on KITTI dataset with the estimated vector error of 0.39{\deg}. Our code is available at github.com/manymuch/ground_normal_filter.

Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference. V2C is more challenging than conventional text-to-speech tasks as it additionally requires the generated speech to exactly match the varying emotions and speaking speed presented in the video. Unlike previous works, we propose a novel movie dubbing architecture to tackle these problems via hierarchical prosody modelling, which bridges the visual information to corresponding speech prosody from three aspects: lip, face, and scene. Specifically, we align lip movement to the speech duration, and convey facial expression to speech energy and pitch via attention mechanism based on valence and arousal representations inspired by recent psychology findings. Moreover, we design an emotion booster to capture the atmosphere from global video scenes. All these embeddings together are used to generate mel-spectrogram and then convert to speech waves via existing vocoder. Extensive experimental results on the Chem and V2C benchmark datasets demonstrate the favorable performance of the proposed method. The source code and trained models will be released to the public.