Yan Chen

Abolfazl Razi, Xiwen Chen, Huayu Li et al.

This paper explores Deep Learning (DL) methods that are used or have the potential to be used for traffic video analysis, emphasizing driving safety for both Autonomous Vehicles (AVs) and human-operated vehicles. We present a typical processing pipeline, which can be used to understand and interpret traffic videos by extracting operational safety metrics and providing general hints and guidelines to improve traffic safety. This processing framework includes several steps, including video enhancement, video stabilization, semantic and incident segmentation, object detection and classification, trajectory extraction, speed estimation, event analysis, modeling and anomaly detection. Our main goal is to guide traffic analysts to develop their own custom-built processing frameworks by selecting the best choices for each step and offering new designs for the lacking modules by providing a comparative analysis of the most successful conventional and DL-based algorithms proposed for each step. We also review existing open-source tools and public datasets that can help train DL models. To be more specific, we review exemplary traffic problems and mentioned requires steps for each problem. Besides, we investigate connections to the closely related research areas of drivers' cognition evaluation, Crowd-sourcing-based monitoring systems, Edge Computing in roadside infrastructures, Automated Driving Systems (ADS)-equipped vehicles, and highlight the missing gaps. Finally, we review commercial implementations of traffic monitoring systems, their future outlook, and open problems and remaining challenges for widespread use of such systems.

Wenbin An, Feng Tian, Jiahao Nie et al.

Knowledge-based Visual Question Answering (KVQA) requires both image and world knowledge to answer questions. Current methods first retrieve knowledge from the image and external knowledge base with the original complex question, then generate answers with Large Language Models (LLMs). However, since the original question contains complex elements that require knowledge from different sources, acquiring different kinds of knowledge in a coupled manner may confuse models and hinder them from retrieving precise knowledge. Furthermore, the ``forward-only'' answering process fails to explicitly capture the knowledge needs of LLMs, which can further hurt answering quality. To cope with the above limitations, we propose DKA: Disentangled Knowledge Acquisition from LLM feedback, a training-free framework that disentangles knowledge acquisition to avoid confusion and uses LLM's feedback to specify the required knowledge. Specifically, DKA requires LLMs to specify what knowledge they need to answer the question and decompose the original complex question into two simple sub-questions: Image-based sub-question and Knowledge-based sub-question. Then we use the two sub-questions to retrieve knowledge from the image and knowledge base, respectively. In this way, two knowledge acquisition models can focus on the content that corresponds to them and avoid disturbance of irrelevant elements in the original complex question, which can help to provide more precise knowledge and better align the knowledge needs of LLMs to yield correct answers. Experiments on benchmark datasets show that DKA significantly outperforms SOTA models. To facilitate future research, our data and code are available at \url{https://github.com/Lackel/DKA}.

Haoyuan Li, Hao Jiang, Tao Jin et al.

Product Retrieval (PR) and Grounding (PG), aiming to seek image and object-level products respectively according to a textual query, have attracted great interest recently for better shopping experience. Owing to the lack of relevant datasets, we collect two large-scale benchmark datasets from Taobao Mall and Live domains with about 474k and 101k image-query pairs for PR, and manually annotate the object bounding boxes in each image for PG. As annotating boxes is expensive and time-consuming, we attempt to transfer knowledge from annotated domain to unannotated for PG to achieve un-supervised Domain Adaptation (PG-DA). We propose a {\bf D}omain {\bf A}daptive Produc{\bf t} S{\bf e}eker ({\bf DATE}) framework, regarding PR and PG as Product Seeking problem at different levels, to assist the query {\bf date} the product. Concretely, we first design a semantics-aggregated feature extractor for each modality to obtain concentrated and comprehensive features for following efficient retrieval and fine-grained grounding tasks. Then, we present two cooperative seekers to simultaneously search the image for PR and localize the product for PG. Besides, we devise a domain aligner for PG-DA to alleviate uni-modal marginal and multi-modal conditional distribution shift between source and target domains, and design a pseudo box generator to dynamically select reliable instances and generate bounding boxes for further knowledge transfer. Extensive experiments show that our DATE achieves satisfactory performance in fully-supervised PR, PG and un-supervised PG-DA. Our desensitized datasets will be publicly available here\footnote{\url{https://github.com/Taobao-live/Product-Seeking}}.

Cong Yu, Dongheng Zhang, Zhi Wu et al.

This paper introduces a novel framework, i.e., RFPose-OT, to enable the 3D human pose estimation from Radio Frequency (RF) signals. Different from existing methods that predict human poses from RF signals on the signal level directly, we consider the structure difference between the RF signals and the human poses, propose to transform the RF signals to the pose domain on the feature level based on Optimal Transport (OT) theory, and generate human poses from the transformed features. To evaluate RFPose-OT, we build a radio system and a multi-view camera system to acquire the RF signal data and the ground-truth human poses. The experimental results in basic indoor environment, occlusion indoor environment, and outdoor environment, all demonstrate that RFPose-OT can predict 3D human poses with higher precision than the state-of-the-art methods.

Haochen Han, Qinghua Zheng, Minnan Luo et al.

Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the model. Although various multi-modal learning methods have been proposed and offer remarkable recognition results, almost all of these methods rely on high-quality manual annotations and assume that modalities among multi-modal data provide semantically relevant information. Unfortunately, the widely used video datasets are usually coarse-annotated or collected from the Internet. Thus, it inevitably contains a portion of noisy labels and noisy correspondence. To address this challenge, we use the audio-visual action recognition task as a proxy and propose a noise-tolerant learning framework to find anti-interference model parameters against both noisy labels and noisy correspondence. Specifically, our method consists of two phases that aim to rectify noise by the inherent correlation between modalities. First, a noise-tolerant contrastive training phase is performed to make the model immune to the possible noisy-labeled data. To alleviate the influence of noisy correspondence, we propose a cross-modal noise estimation component to adjust the consistency between different modalities. As the noisy correspondence existed at the instance level, we further propose a category-level contrastive loss to reduce its interference. Second, in the hybrid-supervised training phase, we calculate the distance metric among features to obtain corrected labels, which are used as complementary supervision to guide the training. Extensive experiments on a wide range of noisy levels demonstrate that our method significantly improves the robustness of the action recognition model and surpasses the baselines by a clear margin.

Zichen Yu, Changyong Shu, Jiajun Deng et al.

Given the capability of mitigating the long-tail deficiencies and intricate-shaped absence prevalent in 3D object detection, occupancy prediction has become a pivotal component in autonomous driving systems. However, the procession of three-dimensional voxel-level representations inevitably introduces large overhead in both memory and computation, obstructing the deployment of to-date occupancy prediction approaches. In contrast to the trend of making the model larger and more complicated, we argue that a desirable framework should be deployment-friendly to diverse chips while maintaining high precision. To this end, we propose a plug-and-play paradigm, namely FlashOCC, to consolidate rapid and memory-efficient occupancy prediction while maintaining high precision. Particularly, our FlashOCC makes two improvements based on the contemporary voxel-level occupancy prediction approaches. Firstly, the features are kept in the BEV, enabling the employment of efficient 2D convolutional layers for feature extraction. Secondly, a channel-to-height transformation is introduced to lift the output logits from the BEV into the 3D space. We apply the FlashOCC to diverse occupancy prediction baselines on the challenging Occ3D-nuScenes benchmarks and conduct extensive experiments to validate the effectiveness. The results substantiate the superiority of our plug-and-play paradigm over previous state-of-the-art methods in terms of precision, runtime efficiency, and memory costs, demonstrating its potential for deployment. The code will be made available.

Yan Chen, Tao Li

We study Nash equilibria learning of a general-sum stochastic game with an unknown transition probability density function. Agents take actions at the current environment state and their joint action influences the transition of the environment state and their immediate rewards. Each agent only observes the environment state and its own immediate reward and is unknown about the actions or immediate rewards of others. We introduce the concepts of weighted asymptotic Nash equilibrium with probability 1 and in probability. For the case with exact pseudo gradients, we design a two-loop algorithm by the equivalence of Nash equilibrium and variational inequality problems. In the outer loop, we sequentially update a constructed strongly monotone variational inequality by updating a proximal parameter while employing a single-call extra-gradient algorithm in the inner loop for solving the constructed variational inequality. We show that if the associated Minty variational inequality has a solution, then the designed algorithm converges to the k^{1/2}-weighted asymptotic Nash equilibrium. Further, for the case with unknown pseudo gradients, we propose a decentralized algorithm, where the G(PO)MDP gradient estimator of the pseudo gradient is provided by Monte-Carlo simulations. The convergence to the k^{1/4} -weighted asymptotic Nash equilibrium in probability is achieved.

Zichen Yu, Changyong Shu, Qianpu Sun et al.

Panoptic occupancy poses a novel challenge by aiming to integrate instance occupancy and semantic occupancy within a unified framework. However, there is still a lack of efficient solutions for panoptic occupancy. In this paper, we propose Panoptic-FlashOcc, a straightforward yet robust 2D feature framework that enables realtime panoptic occupancy. Building upon the lightweight design of FlashOcc, our approach simultaneously learns semantic occupancy and class-aware instance clustering in a single network, these outputs are jointly incorporated through panoptic occupancy procession for panoptic occupancy. This approach effectively addresses the drawbacks of high memory and computation requirements associated with three-dimensional voxel-level representations. With its straightforward and efficient design that facilitates easy deployment, Panoptic-FlashOcc demonstrates remarkable achievements in panoptic occupancy prediction. On the Occ3D-nuScenes benchmark, it achieves exceptional performance, with 38.5 RayIoU and 29.1 mIoU for semantic occupancy, operating at a rapid speed of 43.9 FPS. Furthermore, it attains a notable score of 16.0 RayPQ for panoptic occupancy, accompanied by a fast inference speed of 30.2 FPS. These results surpass the performance of existing methodologies in terms of both speed and accuracy. The source code and trained models can be found at the following github repository: https://github.com/Yzichen/FlashOCC.

Yafeng Yan, Shuyao He, Zhou Yu et al.

Aiming at the limitations of traditional medical decision system in processing large-scale heterogeneous medical data and realizing highly personalized recommendation, this paper introduces a personalized medical decision algorithm utilizing graph neural network (GNN). This research innovatively integrates graph neural network technology into the medical and health field, aiming to build a high-precision representation model of patient health status by mining the complex association between patients' clinical characteristics, genetic information, living habits. In this study, medical data is preprocessed to transform it into a graph structure, where nodes represent different data entities (such as patients, diseases, genes, etc.) and edges represent interactions or relationships between entities. The core of the algorithm is to design a novel multi-scale fusion mechanism, combining the historical medical records, physiological indicators and genetic characteristics of patients, to dynamically adjust the attention allocation strategy of the graph neural network, so as to achieve highly customized analysis of individual cases. In the experimental part, this study selected several publicly available medical data sets for validation, and the results showed that compared with traditional machine learning methods and a single graph neural network model, the proposed personalized medical decision algorithm showed significantly superior performance in terms of disease prediction accuracy, treatment effect evaluation and patient risk stratification.

Yunhui Liang, Jianwen Gan, Yan Chen et al.

High-dimensional data is commonly encountered in numerous data analysis tasks. Feature selection techniques aim to identify the most representative features from the original high-dimensional data. Due to the absence of class label information, it is significantly more challenging to select appropriate features in unsupervised learning scenarios compared to supervised ones. Traditional unsupervised feature selection methods typically score the features of samples based on certain criteria, treating samples indiscriminately. However, these approaches fail to fully capture the internal structure of the data. The importance of different samples should vary, and there is a dual relationship between the weight of samples and features that will influence each other. Therefore, an unsupervised feature selection algorithm based on dual manifold re-ranking (DMRR) is proposed in this paper. Different similarity matrices are constructed to depict the manifold structures among samples, between samples and features, and among features themselves. Then, manifold re-ranking is performed by combining the initial scores of samples and features. By comparing DMRR with three original unsupervised feature selection algorithms and two unsupervised feature selection post-processing algorithms, experimental results confirm that the importance information of different samples and the dual relationship between sample and feature are beneficial for achieving better feature selection.

Yunhui Liang, Jianwen Gan, Yan Chen et al.

Aiming at the problem that existing methods could not fully capture the intrinsic structure of data without considering the higher-order neighborhood information of the data, we proposed an unsupervised feature selection algorithm based on graph filtering and self-representation. Firstly,a higher-order graph filter was applied to the data to obtain its smooth representation,and a regularizer was designed to combine the higher-order graph information for the self-representation matrix learning to capture the intrinsic structure of the data. Secondly,l2,1 norm was used to reconstruct the error term and feature selection matrix to enhance the robustness and row sparsity of the model to select the discriminant features. Finally, an iterative algorithm was applied to effectively solve the proposed objective function and simulation experiments were carried out to verify the effectiveness of the proposed algorithm.

Zhi Wu, Dongheng Zhang, Chunyang Xie et al.

Human silhouette segmentation, which is originally defined in computer vision, has achieved promising results for understanding human activities. However, the physical limitation makes existing systems based on optical cameras suffer from severe performance degradation under low illumination, smoke, and/or opaque obstruction conditions. To overcome such limitations, in this paper, we propose to utilize the radio signals, which can traverse obstacles and are unaffected by the lighting conditions to achieve silhouette segmentation. The proposed RFMask framework is composed of three modules. It first transforms RF signals captured by millimeter wave radar on two planes into spatial domain and suppress interference with the signal processing module. Then, it locates human reflections on RF frames and extract features from surrounding signals with human detection module. Finally, the extracted features from RF frames are aggregated with an attention based mask generation module. To verify our proposed framework, we collect a dataset containing 804,760 radio frames and 402,380 camera frames with human activities under various scenes. Experimental results show that the proposed framework can achieve impressive human silhouette segmentation even under the challenging scenarios(such as low light and occlusion scenarios) where traditional optical-camera-based methods fail. To the best of our knowledge, this is the first investigation towards segmenting human silhouette based on millimeter wave signals. We hope that our work can serve as a baseline and inspire further research that perform vision tasks with radio signals. The dataset and codes will be made in public.

Tiantian Zhu, Jinkai Yu, Tieming Chen et al.

Advanced Persistent Threat (APT) attack usually refers to the form of long-term, covert and sustained attack on specific targets, with an adversary using advanced attack techniques to destroy the key facilities of an organization. APT attacks have caused serious security threats and massive financial loss worldwide. Academics and industry thereby have proposed a series of solutions to detect APT attacks, such as dynamic/static code analysis, traffic detection, sandbox technology, endpoint detection and response (EDR), etc. However, existing defenses are failed to accurately and effectively defend against the current APT attacks that exhibit strong persistent, stealthy, diverse and dynamic characteristics due to the weak data source integrity, large data processing overhead and poor real-time performance in the process of real-world scenarios. To overcome these difficulties, in this paper we propose APTSHIELD, a stable, efficient and real-time APT detection system for Linux hosts. In the aspect of data collection, audit is selected to stably collect kernel data of the operating system so as to carry out a complete portrait of the attack based on comprehensive analysis and comparison of existing logging tools; In the aspect of data processing, redundant semantics skipping and non-viable node pruning are adopted to reduce the amount of data, so as to reduce the overhead of the detection system; In the aspect of attack detection, an APT attack detection framework based on ATT\&CK model is designed to carry out real-time attack response and alarm through the transfer and aggregation of labels. Experimental results on both laboratory and Darpa Engagement show that our system can effectively detect web vulnerability attacks, file-less attacks and remote access trojan attacks, and has a low false positive rate, which adds far more value than the existing frontier work.

Chengrun Qiu, Dongheng Zhang, Yang Hu et al.

In this paper, we propose a radio-assisted human detection framework by incorporating radio information into the state-of-the-art detection methods, including anchor-based onestage detectors and two-stage detectors. We extract the radio localization and identifer information from the radio signals to assist the human detection, due to which the problem of false positives and false negatives can be greatly alleviated. For both detectors, we use the confidence score revision based on the radio localization to improve the detection performance. For two-stage detection methods, we propose to utilize the region proposals generated from radio localization rather than relying on region proposal network (RPN). Moreover, with the radio identifier information, a non-max suppression method with the radio localization constraint has also been proposed to further suppress the false detections and reduce miss detections. Experiments on the simulative Microsoft COCO dataset and Caltech pedestrian datasets show that the mean average precision (mAP) and the miss rate of the state-of-the-art detection methods can be improved with the aid of radio information. Finally, we conduct experiments in real-world scenarios to demonstrate the feasibility of our proposed method in practice.

Cong Yu, Zhi Wu, Dongheng Zhang et al.

This paper demonstrates human synthesis based on the Radio Frequency (RF) signals, which leverages the fact that RF signals can record human movements with the signal reflections off the human body. Different from existing RF sensing works that can only perceive humans roughly, this paper aims to generate fine-grained optical human images by introducing a novel cross-modal RFGAN model. Specifically, we first build a radio system equipped with horizontal and vertical antenna arrays to transceive RF signals. Since the reflected RF signals are processed as obscure signal projection heatmaps on the horizontal and vertical planes, we design a RF-Extractor with RNN in RFGAN for RF heatmap encoding and combining to obtain the human activity information. Then we inject the information extracted by the RF-Extractor and RNN as the condition into GAN using the proposed RF-based adaptive normalizations. Finally, we train the whole model in an end-to-end manner. To evaluate our proposed model, we create two cross-modal datasets (RF-Walk & RF-Activity) that contain thousands of optical human activity frames and corresponding RF signals. Experimental results show that the RFGAN can generate target human activity frames using RF signals. To the best of our knowledge, this is the first work to generate optical images based on RF signals.

Bin-Bin Zhang, Dongheng Zhang, Yadong Li et al.

Human gesture recognition with Radio Frequency (RF) signals has attained acclaim due to the omnipresence, privacy protection, and broad coverage nature of RF signals. These gesture recognition systems rely on neural networks trained with a large number of labeled data. However, the recognition model trained with data under certain conditions would suffer from significant performance degradation when applied in practical deployment, which limits the application of gesture recognition systems. In this paper, we propose an unsupervised domain adaptation framework for RF-based gesture recognition aiming to enhance the performance of the recognition model in new conditions by making effective use of the unlabeled data from new conditions. We first propose pseudo-labeling and consistency regularization to utilize unlabeled data for model training and eliminate the feature discrepancies in different domains. Then we propose a confidence constraint loss to enhance the effectiveness of pseudo-labeling, and design two corresponding data augmentation methods based on the characteristic of the RF signals to strengthen the performance of the consistency regularization, which can make the framework more effective and robust. Furthermore, we propose a cross-match loss to integrate the pseudo-labeling and consistency regularization, which makes the whole framework simple yet effective. Extensive experiments demonstrate that the proposed framework could achieve 4.35% and 2.25% accuracy improvement comparing with the state-of-the-art methods on public WiFi dataset and millimeter wave (mmWave) radar dataset, respectively.

Yadong Li, Dongheng Zhang, Jinbo Chen et al.

Human gesture recognition using millimeter-wave (mmWave) signals provides attractive applications including smart home and in-car interfaces. While existing works achieve promising performance under controlled settings, practical applications are still limited due to the need of intensive data collection, extra training efforts when adapting to new domains, and poor performance for real-time recognition. In this paper, we propose DI-Gesture, a domain-independent and real-time mmWave gesture recognition system. Specifically, we first derive signal variations corresponding to human gestures with spatial-temporal processing. To enhance the robustness of the system and reduce data collecting efforts, we design a data augmentation framework for mmWave signals based on correlations between signal patterns and gesture variations. Furthermore, a spatial-temporal gesture segmentation algorithm is employed for real-time recognition. Extensive experimental results show DI-Gesture achieves an average accuracy of 97.92\%, 99.18\%, and 98.76\% for new users, environments, and locations, respectively. We also evaluate DI-Gesture in challenging scenarios like real-time recognition and sensing at extreme angles, all of which demonstrate the superior robustness and effectiveness of our system.

Ruixu Geng, Yang Hu, Yan Chen

As an emerging technology that has attracted huge attention, non-line-of-sight (NLOS) imaging can reconstruct hidden objects by analyzing the diffuse reflection on a relay surface, with broad application prospects in the fields of autonomous driving, medical imaging, and defense. Despite the challenges of low signal-to-noise ratio (SNR) and high ill-posedness, NLOS imaging has been developed rapidly in recent years. Most current NLOS imaging technologies use conventional physical models, constructing imaging models through active or passive illumination and using reconstruction algorithms to restore hidden scenes. Moreover, deep learning algorithms for NLOS imaging have also received much attention recently. This paper presents a comprehensive overview of both conventional and deep learning-based NLOS imaging techniques. Besides, we also survey new proposed NLOS scenes, and discuss the challenges and prospects of existing technologies. Such a survey can help readers have an overview of different types of NLOS imaging, thus expediting the development of seeing around corners.

Yan Chen, Jimmy Ren, Xuanye Cheng et al.

Time-of-Flight (ToF) cameras require active illumination to obtain depth information thus the power of illumination directly affects the performance of ToF cameras. Traditional ToF imaging algorithms is very sensitive to illumination and the depth accuracy degenerates rapidly with the power of it. Therefore, the design of a power efficient ToF camera always creates a painful dilemma for the illumination and the performance trade-off. In this paper, we show that despite the weak signals in many areas under extreme short exposure setting, these signals as a whole can be well utilized through a learning process which directly translates the weak and noisy ToF camera raw to depth map. This creates an opportunity to tackle the aforementioned dilemma and make a very power efficient ToF camera possible. To enable the learning, we collect a comprehensive dataset under a variety of scenes and photographic conditions by a specialized ToF camera. Experiments show that our method is able to robustly process ToF camera raw with the exposure time of one order of magnitude shorter than that used in conventional ToF cameras. In addition to evaluating our approach both quantitatively and qualitatively, we also discuss its implication to designing the next generation power efficient ToF cameras. We will make our dataset and code publicly available.

Michael Hay, Ashwin Machanavajjhala, Gerome Miklau et al.

Differential privacy has become the dominant standard in the research community for strong privacy protection. There has been a flood of research into query answering algorithms that meet this standard. Algorithms are becoming increasingly complex, and in particular, the performance of many emerging algorithms is {\em data dependent}, meaning the distribution of the noise added to query answers may change depending on the input data. Theoretical analysis typically only considers the worst case, making empirical study of average case performance increasingly important. In this paper we propose a set of evaluation principles which we argue are essential for sound evaluation. Based on these principles we propose DPBench, a novel evaluation framework for standardized evaluation of privacy algorithms. We then apply our benchmark to evaluate algorithms for answering 1- and 2-dimensional range queries. The result is a thorough empirical study of 15 published algorithms on a total of 27 datasets that offers new insights into algorithm behavior---in particular the influence of dataset scale and shape---and a more complete characterization of the state of the art. Our methodology is able to resolve inconsistencies in prior empirical studies and place algorithm performance in context through comparison to simple baselines. Finally, we pose open research questions which we hope will guide future algorithm design.