Generative models in Autonomous Driving (AD) enable diverse scenario creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of the map modality. With tokenized modalities, our scene sequence generation framework autoregressively predicts each scene while managing computational demands through a two-stage approach. The Temporal AutoRegressive (TAR) component captures inter-frame dynamics for each modality, while the Ordered AutoRegressive (OAR) component aligns modalities within each scene by sequentially predicting tokens in a fixed order To maintain coherence between map and ego-action modalities, we introduce the Action-Aware Map Alignment (AMA) module, which applies a transformation based on the ego-action to maintain coherence between these two modalities. Our framework effectively generates complex, realistic driving scenes over extended sequences, ensuring multimodal consistency and offering fine-grained control over scene elements. Project page: https://yanhaowu.github.io/UMGen.

Contrastive Language-Image Pre-training (CLIP) excels in global alignment with language but exhibits limited sensitivity to spatial information, leading to strong performance in zero-shot classification tasks but underperformance in tasks requiring precise spatial understanding. Recent approaches have introduced Region-Language Alignment (RLA) to enhance CLIP's performance in dense multimodal tasks by aligning regional visual representations with corresponding text inputs. However, we find that CLIP ViTs fine-tuned with RLA suffer from notable loss in spatial awareness, which is crucial for dense prediction tasks. To address this, we propose the Spatial Correlation Distillation (SCD) framework, which preserves CLIP's inherent spatial structure and mitigates above degradation. To further enhance spatial correlations, we introduce a lightweight Refiner that extracts refined correlations directly from CLIP before feeding them into SCD, based on an intriguring finding that CLIP naturally capture high-quality dense features. Together, these components form a robust distillation framework that enables CLIP ViTs to integrate both visual-language and visual-centric improvements, achieving state-of-the-art results across various open-vocabulary dense prediction benchmarks.

With the development of machine vision and multimedia technology, posture detection and related algorithms have become widely used in the field of human posture recognition. Traditional video surveillance methods have the disadvantages of slow detection speed, low accuracy, interference from occlusions, and poor real-time performance. This paper proposes a real-time pose detection algorithm based on deep learning, which can effectively perform real-time tracking and detection of single and multiple individuals in different indoor and outdoor environments and at different distances. First, a corresponding pose recognition dataset for complex scenes was created based on the YOLO network. Then, the OpenPose method was used to detect key points of the human body. Finally, the Kalman filter multi-object tracking method was used to predict the state of human targets within the occluded area. Real-time detection of human postures (sitting, stand up, standing, sit down, walking, fall down, and lying down) is achieved with corresponding alarms to ensure the timely detection and processing of emergencies.

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object cor-relations. This can create a tendency for neural networks to exploit these strong dependencies, bypassing the individ-ual object patterns. To address this challenge, we introduce a novel self-supervised learning (SSL) strategy. Our approach leverages both object patterns and contextual cues to produce robust features. It begins with the formulation of an object-exchanging strategy, where pairs of objects with comparable sizes are exchanged across different scenes, effectively disentangling the strong contextual dependencies. Subsequently, we introduce a context-aware feature learning strategy, which encodes object patterns without relying on their specific context by aggregating object features across various scenes. Our extensive experiments demonstrate the superiority of our method over existing SSL techniques, further showing its better robustness to environmental changes. Moreover, we showcase the applicability of our approach by transferring pre-trained models to diverse point cloud datasets.11Our code is available at https:/lgithub.com/YanhaoWu/OESSL

Dense Self-Supervised Learning (SSL) creates positive pairs by building positive paired regions or points, thereby aiming to preserve local features, for example of individual objects. However, existing approaches tend to couple objects by leaking information from the neighboring contextual regions when the pairs have a limited overlap. In this paper, we first quantitatively identify and confirm the existence of such a coupling phenomenon. We then address it by developing a remarkably simple yet highly effective solution comprising a novel augmentation method, Region Collaborative Cutout (RCC), and a corresponding decoupling branch. Importantly, our design is versatile and can be seamlessly integrated into existing SSL frameworks, whether based on Convolutional Neural Networks (CNNs) or Vision Transformers (ViTs). We conduct extensive experiments, incorporating our solution into two CNN-based and two ViT-based methods, with results confirming the effectiveness of our approach. Moreover, we provide empirical evidence that our method significantly contributes to the disentanglement of feature representations among objects, both in quantitative and qualitative terms.

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing methods employ contrastive learning strategies and define positive pairs by performing various augmentation of point clusters in a single frame. As such, these methods do not exploit the temporal nature of LiDAR data. In this paper, we introduce an SSL strategy that leverages positive pairs in both the spatial and temporal domain. To this end, we design (i) a point-to-cluster learning strategy that aggregates spatial information to distinguish objects; and (ii) a cluster-to-cluster learning strategy based on unsupervised object tracking that exploits temporal correspondences. We demonstrate the benefits of our approach via extensive experiments performed by self-supervised training on two large-scale LiDAR datasets and transferring the resulting models to other point cloud segmentation benchmarks. Our results evidence that our method outperforms the state-of-the-art point cloud SSL methods.11Our code and pretrained models will be found at https://github.com/YanhaoWu/STSSL. Correspondence to Ke Wei.

As the fundamental frequency in the medium-frequency power system is 8 times 50Hz, the voltage drop has become such a problem as to affect the waveform quality of medium-frequency power supply. The medium-frequency Dynamic Voltage Restorer (DVR) can be used to eliminate the impact. In this paper, the DVR adopts the independently-controlled three H-bridge, and a precise model of one phase is established. Considering that the traditional PI control strategy cannot be applied to easily achieving a non-static error output and harmonics suppression, this paper adopts the PR controller capable of dealing with the zero steady-state error by controlling the AC signals directly. The simulation and experiment results show that the PR control strategy can effectively compensate the required voltage drop, function well in dynamic response and facilitate the adjustment of a wider bandwidth margin and that it is capable of selective compensation for low harmonic.

As the traditional methods cannot be effectively used to suppress harmonics in the 400Hz solid-static power supply, a special studying of harmonic analysis and suppression has been made in this paper. The analysis of the topological structure of 400 Hz solid-static power supply leads to the equation of PWM voltage, which makes it possible to summarize the laws of both the distribution of sideband harmonics and the transformation of total harmonic distortion (THD) in this kind of power supply. This paper presents a new design of LC filter for higher harmonics suppression and a novel multi-ply dual-loop proportional-resonant (MDLPR) controller for lower harmonics suppression. They are given experimented verification by means of prototype of 300 kVA 400Hz solid-static power supply which has been developed. The results show that the theoretical analysis is correct and that the method of sectional suppression is effective.