Rui Wang

Chuanfu Shen, Chao Fan, Wei Wu et al.

Video-based gait recognition has achieved impressive results in constrained scenarios. However, visual cameras neglect human 3D structure information, which limits the feasibility of gait recognition in the 3D wild world. Instead of extracting gait features from images, this work explores precise 3D gait features from point clouds and proposes a simple yet efficient 3D gait recognition framework, termed LidarGait. Our proposed approach projects sparse point clouds into depth maps to learn the representations with 3D geometry information, which outperforms existing point-wise and camera-based methods by a significant margin. Due to the lack of point cloud datasets, we built the first large-scale LiDAR-based gait recognition dataset, SUSTech1K, collected by a LiDAR sensor and an RGB camera. The dataset contains 25,239 sequences from 1,050 subjects and covers many variations, including visibility, views, occlusions, clothing, carrying, and scenes. Extensive experiments show that (1) 3D structure information serves as a significant feature for gait recognition. (2) LidarGait outperforms existing point-based and silhouette-based methods by a significant margin, while it also offers stable cross-view results. (3) The LiDAR sensor is superior to the RGB camera for gait recognition in the outdoor environment. The source code and dataset have been made available at https://lidargait.github.io.

Rui Wang, Chuanfu Shen, Manuel J. Marin-Jimenez et al.

Current gait recognition research mainly focuses on identifying pedestrians captured by the same type of sensor, neglecting the fact that individuals may be captured by different sensors in order to adapt to various environments. A more practical approach should involve cross-modality matching across different sensors. Hence, this paper focuses on investigating the problem of cross-modality gait recognition, with the objective of accurately identifying pedestrians across diverse vision sensors. We present CrossGait inspired by the feature alignment strategy, capable of cross retrieving diverse data modalities. Specifically, we investigate the cross-modality recognition task by initially extracting features within each modality and subsequently aligning these features across modalities. To further enhance the cross-modality performance, we propose a Prototypical Modality-shared Attention Module that learns modality-shared features from two modality-specific features. Additionally, we design a Cross-modality Feature Adapter that transforms the learned modality-specific features into a unified feature space. Extensive experiments conducted on the SUSTech1K dataset demonstrate the effectiveness of CrossGait: (1) it exhibits promising cross-modality ability in retrieving pedestrians across various modalities from different sensors in diverse scenes, and (2) CrossGait not only learns modality-shared features for cross-modality gait recognition but also maintains modality-specific features for single-modality recognition.

Jinyun Zhou, Rui Wang, Xu Liu et al.

We present a learning-based planner that aims to robustly drive a vehicle by mimicking human drivers' driving behavior. We leverage a mid-to-mid approach that allows us to manipulate the input to our imitation learning network freely. With that in mind, we propose a novel feedback synthesizer for data augmentation. It allows our agent to gain more driving experience in various previously unseen environments that are likely to encounter, thus improving overall performance. This is in contrast to prior works that rely purely on random synthesizers. Furthermore, rather than completely commit to imitating, we introduce task losses that penalize undesirable behaviors, such as collision, off-road, and so on. Unlike prior works, this is done by introducing a differentiable vehicle rasterizer that directly converts the waypoints output by the network into images. This effectively avoids the usage of heavyweight ConvLSTM networks, therefore, yields a faster model inference time. About the network architecture, we exploit an attention mechanism that allows the network to reason critical objects in the scene and produce better interpretable attention heatmaps. To further enhance the safety and robustness of the network, we add an optional optimization-based post-processing planner improving the driving comfort. We comprehensively validate our method's effectiveness in different scenarios that are specifically created for evaluating self-driving vehicles. Results demonstrate that our learning-based planner achieves high intelligence and can handle complex situations. Detailed ablation and visualization analysis are included to further demonstrate each of our proposed modules' effectiveness in our method.

Rui Wang, Min Chen, Nadra Guizani et al.

Future advances in deep learning and its impact on the development of artificial intelligence (AI) in all fields depends heavily on data size and computational power. Sacrificing massive computing resources in exchange for better precision rates of the network model is recognized by many researchers. This leads to huge computing consumption and satisfactory results are not always expected when computing resources are limited. Therefore, it is necessary to find a balance between resources and model performance to achieve satisfactory results. This article proposes a self-adaptive quality of experience (QoE) framework, DeepNetQoE, to guide the training of deep networks. A self-adaptive QoE model is set up that relates the model's accuracy with the computing resources required for training which will allow the experience value of the model to improve. To maximize the experience value when computer resources are limited, a resource allocation model and solutions need to be established. In addition, we carry out experiments based on four network models to analyze the experience values with respect to the crowd counting example. Experimental results show that the proposed DeepNetQoE is capable of adaptively obtaining a high experience value according to user needs and therefore guiding users to determine the computational resources allocated to the network models.