Search

The key parameter for describing frictional strength at the onset of sliding is the static friction coefficient. Yet, how the static friction coefficient at the macroscale emerges from contacting asperities at the microscale is still an open problem. Here, we present friction experiments in which the normal load was varied over more than three orders of magnitude, so that a transition from a single asperity contact at low loads to multi-asperity contacts at high loads was achieved. We find a remarkable drop in static friction coefficient with increasing normal load. Using a simple stick-slip transition model we identify the presence of pre-sliding and subcritical contact points as the cause of smaller static friction coefficient at increased normal loads. Our measurements and model bridge the gap between friction behavior commonly observed in atomic force microscopy (AFM) experiments at microscopic forces, and industrially relevant multi-asperity contact interfaces loaded with macroscopic forces., Comment: 9 pages, 7 figures

The creation of increasingly vivid 3D virtual digital humans has become a hot topic in recent years. Currently, most speech-driven work focuses on training models to learn the relationship between phonemes and visemes to achieve more realistic lips. However, they fail to capture the correlations between emotions and facial expressions effectively. To solve this problem, we propose a new model, termed EmoFace. EmoFace employs a novel Mesh Attention mechanism, which helps to learn potential feature dependencies between mesh vertices in time and space. We also adopt, for the first time to our knowledge, an effective self-growing training scheme that combines teacher-forcing and scheduled sampling in a 3D face animation task. Additionally, since EmoFace is an autoregressive model, there is no requirement that the first frame of the training data must be a silent frame, which greatly reduces the data limitations and contributes to solve the current dilemma of insufficient datasets. Comprehensive quantitative and qualitative evaluations on our proposed high-quality reconstructed 3D emotional facial animation dataset, 3D-RAVDESS ($5.0343\times 10^{-5}$mm for LVE and $1.0196\times 10^{-5}$mm for EVE), and publicly available dataset VOCASET ($2.8669\times 10^{-5}$mm for LVE and $0.4664\times 10^{-5}$mm for EVE), demonstrate that our algorithm achieves state-of-the-art performance.

Speech-driven talking head generation is an important but challenging task for many downstream applications such as augmented reality. Existing methods have achieved remarkable performance by utilizing autoregressive models or diffusion models. However, most still suffer from modality inconsistencies, specifically the misalignment between audio and mesh modalities, which causes inconsistencies in motion diversity and lip-sync accuracy. To address this issue, this paper introduces GLDiTalker, a novel speech-driven 3D facial animation model that employs a Graph Latent Diffusion Transformer. The core idea behind GLDiTalker is that the audio-mesh modality misalignment can be resolved by diffusing the signal in a latent quantilized spatial-temporal space. To achieve this, GLDiTalker builds upon a quantilized space-time diffusion training pipeline, which consists of a Graph Enhanced Quantilized Space Learning Stage and a Space-Time Powered Latent Diffusion Stage. The first stage ensures lip-sync accuracy, while the second stage enhances motion diversity. Together, these stages enable GLDiTalker to generate temporally and spatially stable, realistic models. Extensive evaluations on several widely used benchmarks demonstrate that our method achieves superior performance compared to existing methods., Comment: 9 pages, 5 figures

3D visual grounding aims to identify objects in 3D point cloud scenes that match specific natural language descriptions. This requires the model to not only focus on the target object itself but also to consider the surrounding environment to determine whether the descriptions are met. Most previous works attempt to accomplish both tasks within the same module, which can easily lead to a distraction of attention. To this end, we propose PD-APE, a dual-branch decoding framework that separately decodes target object attributes and surrounding layouts. Specifically, in the target object branch, the decoder processes text tokens that describe features of the target object (e.g., category and color), guiding the queries to pay attention to the target object itself. In the surrounding branch, the queries align with other text tokens that carry surrounding environment information, making the attention maps accurately capture the layout described in the text. Benefiting from the proposed dual-branch design, the queries are allowed to focus on points relevant to each branch's specific objective. Moreover, we design an adaptive position encoding method for each branch respectively. In the target object branch, the position encoding relies on the relative positions between seed points and predicted 3D boxes. In the surrounding branch, the attention map is additionally guided by the confidence between visual and text features, enabling the queries to focus on points that have valuable layout information. Extensive experiments demonstrate that we surpass the state-of-the-art on two widely adopted 3D visual grounding datasets, ScanRefer and Nr3D.

Semi-supervised learning aims to leverage numerous unlabeled data to improve the model performance. Current semi-supervised 3D object detection methods typically use a teacher to generate pseudo labels for a student, and the quality of the pseudo labels is essential for the final performance. In this paper, we propose PatchTeacher, which focuses on partial scene 3D object detection to provide high-quality pseudo labels for the student. Specifically, we divide a complete scene into a series of patches and feed them to our PatchTeacher sequentially. PatchTeacher leverages the low memory consumption advantage of partial scene detection to process point clouds with a high-resolution voxelization, which can minimize the information loss of quantization and extract more fine-grained features. However, it is non-trivial to train a detector on fractions of the scene. Therefore, we introduce three key techniques, i.e., Patch Normalizer, Quadrant Align, and Fovea Selection, to improve the performance of PatchTeacher. Moreover, we devise PillarMix, a strong data augmentation strategy that mixes truncated pillars from different LiDAR scans to generate diverse training samples and thus help the model learn more general representation. Extensive experiments conducted on Waymo and ONCE datasets verify the effectiveness and superiority of our method and we achieve new state-of-the-art results, surpassing existing methods by a large margin. Codes are available at https://github.com/LittlePey/PTPM., Comment: Accepted by AAAI 2024

Significant advancements in video diffusion models have brought substantial progress to the field of text-to-video (T2V) synthesis. However, existing T2V synthesis model struggle to accurately generate complex motion dynamics, leading to a reduction in video realism. One possible solution is to collect massive data and train the model on it, but this would be extremely expensive. To alleviate this problem, in this paper, we reformulate the typical T2V generation process as a search-based generation pipeline. Instead of scaling up the model training, we employ existing videos as the motion prior database. Specifically, we divide T2V generation process into two steps: (i) For a given prompt input, we search existing text-video datasets to find videos with text labels that closely match the prompt motions. We propose a tailored search algorithm that emphasizes object motion features. (ii) Retrieved videos are processed and distilled into motion priors to fine-tune a pre-trained base T2V model, followed by generating desired videos using input prompt. By utilizing the priors gleaned from the searched videos, we enhance the realism of the generated videos' motion. All operations can be finished on a single NVIDIA RTX 4090 GPU. We validate our method against state-of-the-art T2V models across diverse prompt inputs. The code will be public.

In order to solve the problem of stable jumping of micro robot, we design a special mechanism: elastic passive joint (EPJ). EPJ can assist in achieving smooth jumping through the opening-closing process when the robot jumps. First, we introduce the composition and operation principle of EPJ, and perform a dynamic modeling of the robot's jumping process. Then, in order to verify the effectiveness of EPJ in controlling the robot's smooth jump, we design a simulation experiment based on MATLAB. Through comparative experiments, it was proved that EPJ can greatly adjust the angular velocity of the robot and increase the jump distance of the robot. Finally, we analyze each parameter in EPJ and performs parameter optimization. After optimization, EPJ achieves a completely flip-free jump of the robot, laying an important foundation for improving the mobility of micro-robot.

A comprehensive theoretical approach to describe the electron-ion radiative recombination in the presence of intense, short laser pulses, which accounts for nondipole corrections is presented. It is based on the relativistic Coulomb-Volkov solution describing an electron in a combined Coulomb potential and a laser field, which is systematically expanded in powers of $1/c$. Thus, it allows us to trace the origin of nondipole effects observed in the spectrum of emitted radiation. Hence, as we demonstrate for high-frequency pulses assisting the process, a significant extension of the cutoff and asymmetry in angular distributions of the emitted radiation can be attributed to the electron recoil off the laser pulse. In addition, we investigate a possibility of enhancing the efficiency of the generated high-energy radiation by chirping the pulse., Comment: 15 pages, 6 figures

It is well-known that Excess-of-Loss reinsurance has more marketability than Stop-Loss reinsurance, though Stop-Loss reinsurance is the most prominent setting discussed in the optimal (re)insurance design literature. We point out that optimal reinsurance policy under Stop-Loss leads to a zero insolvency probability, which motivates our paper. We provide a remedy to this peculiar property of the optimal Stop-Loss reinsurance contract by investigating the optimal Excess-of-Loss reinsurance contract instead. We also provide estimators for the optimal Excess-of-Loss and Stop-Loss contracts and investigate their statistical properties under many premium principle assumptions and various risk preferences, which according to our knowledge, have never been investigated in the literature. Simulated data and real-life data are used to illustrate our main theoretical findings.

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, this selection process inevitably introduces unreliable 3D boxes, in which 3D points cannot be definitively assigned as foreground or background. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. To resolve this problem, in this paper, we propose a novel pseudo label refinery framework. Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy. This strategy involves either removing all points within an unreliable box or replacing it with a high-confidence box. Moreover, the point numbers of instances in high-beam datasets are considerably higher than those in low-beam datasets, also degrading the quality of pseudo labels during the training process. We alleviate this issue by generating additional proposals and aligning RoI features across different domains. Experimental results demonstrate that our method effectively enhances the quality of pseudo labels and consistently surpasses the state-of-the-art methods on six autonomous driving benchmarks. Code will be available at https://github.com/Zhanwei-Z/PERE., Comment: Accepted by CVPR2024

From $\sim$ 5000 deg$^{2}$ of the combination of the Beijing-Arizona Sky Survey (BASS) and Mayall $z$-band Legacy Survey (MzLS) which is also the northern sky region of the Dark Energy Spectroscopic Instrument (DESI) Legacy Imaging Surveys, we selected a sample of 31,825 candidates of low surface brightness galaxies (LSBGs) with the mean effective surface brightness 24.2 $< \bar{\mu}_{\rm eff,g} <$ 28.8 mag arcsec$^{\rm -2}$ and the half-light radius 2.5$^{\prime\prime}$ $< r_{\rm eff} <$ 20$^{\prime\prime}$ based on the released photometric catalogue and the machine learning model. The distribution of the LSBGs is of bimodality in the $g$ - $r$ color, indicating the two distinct populations of the blue ($g$ - $r <$ 0.60) and the red ($g$ - $r >$ 0.60) LSBGs. The blue LSBGs appear spiral, disk or irregular while the red LSBGs are spheroidal or ellipitcal and spatially clustered. This trend shows that the color has a strong correlation with galaxy morphology for LSBGs. In the spatial distribution, the blue LSBGs are more uniformly distributed while the red ones are highly clustered, indicating that red LSBGs preferentially populated denser environment than the blue LSBGs. Besides, both populations have consistent distribution of ellipticity (median $\epsilon\sim$ 0.3), half-light radius (median $r_{\rm eff} \sim$ 4$^{\prime\prime}$), and Sersic index (median $n$ = 1), implying the dominance of the full sample by the round and disk galaxies. This sample has definitely extended the studies of LSBGs to a regime of lower surface brightness, fainter magnitude, and broader other properties than the previously SDSS-based samples., Comment: 20 pages, 11 figures, 1 table, accepted by Research in Astronomy and Astrophysics

Customization generation techniques have significantly advanced the synthesis of specific concepts across varied contexts. Multi-concept customization emerges as the challenging task within this domain. Existing approaches often rely on training a fusion matrix of multiple Low-Rank Adaptations (LoRAs) to merge various concepts into a single image. However, we identify this straightforward method faces two major challenges: 1) concept confusion, where the model struggles to preserve distinct individual characteristics, and 2) concept vanishing, where the model fails to generate the intended subjects. To address these issues, we introduce LoRA-Composer, a training-free framework designed for seamlessly integrating multiple LoRAs, thereby enhancing the harmony among different concepts within generated images. LoRA-Composer addresses concept vanishing through concept injection constraints, enhancing concept visibility via an expanded cross-attention mechanism. To combat concept confusion, concept isolation constraints are introduced, refining the self-attention computation. Furthermore, latent re-initialization is proposed to effectively stimulate concept-specific latent within designated regions. Our extensive testing showcases a notable enhancement in LoRA-Composer's performance compared to standard baselines, especially when eliminating the image-based conditions like canny edge or pose estimations. Code is released at \url{https://github.com/Young98CN/LoRA_Composer}, Comment: project page: https://github.com/Young98CN/LoRA_Composer

In this paper, we introduce a novel benchmark, dubbed VastTrack, towards facilitating the development of more general visual tracking via encompassing abundant classes and videos. VastTrack possesses several attractive properties: (1) Vast Object Category. In particular, it covers target objects from 2,115 classes, largely surpassing object categories of existing popular benchmarks (e.g., GOT-10k with 563 classes and LaSOT with 70 categories). With such vast object classes, we expect to learn more general object tracking. (2) Larger scale. Compared with current benchmarks, VastTrack offers 50,610 sequences with 4.2 million frames, which makes it to date the largest benchmark regarding the number of videos, and thus could benefit training even more powerful visual trackers in the deep learning era. (3) Rich Annotation. Besides conventional bounding box annotations, VastTrack also provides linguistic descriptions for the videos. The rich annotations of VastTrack enables development of both the vision-only and the vision-language tracking. To ensure precise annotation, all videos are manually labeled with multiple rounds of careful inspection and refinement. To understand performance of existing trackers and to provide baselines for future comparison, we extensively assess 25 representative trackers. The results, not surprisingly, show significant drops compared to those on current datasets due to lack of abundant categories and videos from diverse scenarios for training, and more efforts are required to improve general tracking. Our VastTrack and all the evaluation results will be made publicly available https://github.com/HengLan/VastTrack., Comment: Tech. report

We investigate the anomalous photo-induced band renormalization in correlated materials, exemplified by the case of Ta$_2$NiSe$_5$. The manifestation of this anomaly is characterized by the alternating direction of band shift in response to changes in the laser parameters or electron momentum. We attribute the phenomena to the band inversion of the material and the selective excitation of a high-lying flat band, leading to the competition between the Hartree shift and the order collapse. These findings are based on {\it ab initio} determined effective model for Ta$_2$NiSe$_5$, in which we incorporate high-lying states and the time-dependent GW simulation to follow the non-equilibrium dynamics induced by the laser. Our findings reveal the sensitivity of the non-equilibrium electronic dynamics to the band structure and laser protocols, providing valuable guidance for the selection of suitable materials and lasers in the engineering of band structures.

Prompt learning has demonstrated impressive efficacy in the fine-tuning of multimodal large models to a wide range of downstream tasks. Nonetheless, applying existing prompt learning methods for the diagnosis of neurological disorder still suffers from two issues: (i) existing methods typically treat all patches equally, despite the fact that only a small number of patches in neuroimaging are relevant to the disease, and (ii) they ignore the structural information inherent in the brain connection network which is crucial for understanding and diagnosing neurological disorders. To tackle these issues, we introduce a novel prompt learning model by learning graph prompts during the fine-tuning process of multimodal large models for diagnosing neurological disorders. Specifically, we first leverage GPT-4 to obtain relevant disease concepts and compute semantic similarity between these concepts and all patches. Secondly, we reduce the weight of irrelevant patches according to the semantic similarity between each patch and disease-related concepts. Moreover, we construct a graph among tokens based on these concepts and employ a graph convolutional network layer to extract the structural information of the graph, which is used to prompt the pre-trained multimodal large models for diagnosing neurological disorders. Extensive experiments demonstrate that our method achieves superior performance for neurological disorder diagnosis compared with state-of-the-art methods and validated by clinicians.

Multi-camera perception tasks have gained significant attention in the field of autonomous driving. However, existing frameworks based on Lift-Splat-Shoot (LSS) in the multi-camera setting cannot produce suitable dense 3D features due to the projection nature and uncontrollable densification process. To resolve this problem, we propose to regulate intermediate dense 3D features with the help of volume rendering. Specifically, we employ volume rendering to process the dense 3D features to obtain corresponding 2D features (e.g., depth maps, semantic maps), which are supervised by associated labels in the training. This manner regulates the generation of dense 3D features on the feature level, providing appropriate dense and unified features for multiple perception tasks. Therefore, our approach is termed Vampire, stands for "Volume rendering As Multi-camera Perception Intermediate feature REgulator". Experimental results on the Occ3D and nuScenes datasets demonstrate that Vampire facilitates fine-grained and appropriate extraction of dense 3D features, and is competitive with existing SOTA methods across diverse downstream perception tasks like 3D occupancy prediction, LiDAR segmentation and 3D objection detection, while utilizing moderate GPU resources. We provide a video demonstration in the supplementary materials and Codes are available at github.com/cskkxjk/Vampire., Comment: Accepted by AAAI 2024

Diffusion models have exhibited impressive prowess in the text-to-image task. Recent methods add image-level structure controls, e.g., edge and depth maps, to manipulate the generation process together with text prompts to obtain desired images. This controlling process is globally operated on the entire image, which limits the flexibility of control regions. In this paper, we explore a novel and practical task setting: local control. It focuses on controlling specific local region according to user-defined image conditions, while the remaining regions are only conditioned by the original text prompt. However, it is non-trivial to achieve local conditional controlling. The naive manner of directly adding local conditions may lead to the local control dominance problem, which forces the model to focus on the controlled region and neglect object generation in other regions. To mitigate this problem, we propose Regional Discriminate Loss to update the noised latents, aiming at enhanced object generation in non-control regions. Furthermore, the proposed Focused Token Response suppresses weaker attention scores which lack the strongest response to enhance object distinction and reduce duplication. Lastly, we adopt Feature Mask Constraint to reduce quality degradation in images caused by information differences across the local control region. All proposed strategies are operated at the inference stage. Extensive experiments demonstrate that our method can synthesize high-quality images aligned with the text prompt under local control conditions.

Recent one-shot video tuning methods, which fine-tune the network on a specific video based on pre-trained text-to-image models (e.g., Stable Diffusion), are popular in the community because of the flexibility. However, these methods often produce videos marred by incoherence and inconsistency. To address these limitations, this paper introduces a simple yet effective noise constraint across video frames. This constraint aims to regulate noise predictions across their temporal neighbors, resulting in smooth latents. It can be simply included as a loss term during the training phase. By applying the loss to existing one-shot video tuning methods, we significantly improve the overall consistency and smoothness of the generated videos. Furthermore, we argue that current video evaluation metrics inadequately capture smoothness. To address this, we introduce a novel metric that considers detailed features and their temporal dynamics. Experimental results validate the effectiveness of our approach in producing smoother videos on various one-shot video tuning baselines. The source codes and video demos are available at \href{https://github.com/SPengLiang/SmoothVideo}{https://github.com/SPengLiang/SmoothVideo}.

In the field of monocular 3D detection, it is common practice to utilize scene geometric clues to enhance the detector's performance. However, many existing works adopt these clues explicitly such as estimating a depth map and back-projecting it into 3D space. This explicit methodology induces sparsity in 3D representations due to the increased dimensionality from 2D to 3D, and leads to substantial information loss, especially for distant and occluded objects. To alleviate this issue, we propose MonoNeRD, a novel detection framework that can infer dense 3D geometry and occupancy. Specifically, we model scenes with Signed Distance Functions (SDF), facilitating the production of dense 3D representations. We treat these representations as Neural Radiance Fields (NeRF) and then employ volume rendering to recover RGB images and depth maps. To the best of our knowledge, this work is the first to introduce volume rendering for M3D, and demonstrates the potential of implicit reconstruction for image-based 3D perception. Extensive experiments conducted on the KITTI-3D benchmark and Waymo Open Dataset demonstrate the effectiveness of MonoNeRD. Codes are available at https://github.com/cskkxjk/MonoNeRD., Comment: Accepted by ICCV 2023

Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks by exploring both complementary information and consistent information among multiple graphs. However, previous methods usually overlook the issues in practical applications, i.e., the out-of-sample issue and the noise issue. To address the above issues, in this paper, we propose an effective and efficient UMGL method to explore both complementary and consistent information. To do this, our method employs multiple MLP encoders rather than graph convolutional network (GCN) to conduct representation learning with two constraints, i.e., preserving the local graph structure among nodes to handle the out-of-sample issue, and maximizing the correlation of multiple node representations to handle the noise issue. Comprehensive experiments demonstrate that our proposed method achieves superior effectiveness and efficiency over the comparison methods and effectively tackles those two issues. Code is available at https://github.com/LarryUESTC/CoCoMG.

Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical applications. Existing depth estimation systems, however, suffer inevitably from real-world corruptions and perturbations and are struggled to provide reliable depth predictions under such cases. In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation. This challenge was developed based on the newly established KITTI-C and NYUDepth2-C benchmarks. We hosted two stand-alone tracks, with an emphasis on robust self-supervised and robust fully-supervised depth estimation, respectively. Out of more than two hundred participants, nine unique and top-performing solutions have appeared, with novel designs ranging from the following aspects: spatial- and frequency-domain augmentations, masked image modeling, image restoration and super-resolution, adversarial training, diffusion-based noise suppression, vision-language pre-training, learned model ensembling, and hierarchical feature enhancement. Extensive experimental analyses along with insightful observations are drawn to better understand the rationale behind each design. We hope this challenge could lay a solid foundation for future research on robust and reliable depth estimation and beyond. The datasets, competition toolkit, workshop recordings, and source code from the winning teams are publicly available on the challenge website., Comment: Technical Report; 65 pages, 34 figures, 24 tables; Code at https://github.com/ldkong1205/RoboDepth

Meeting online is becoming the new normal. Creating an immersive experience for online meetings is a necessity towards more diverse and seamless environments. Efficient photorealistic rendering of human 3D dynamics is the core of immersive meetings. Current popular applications achieve real-time conferencing but fall short in delivering photorealistic human dynamics, either due to limited 2D space or the use of avatars that lack realistic interactions between participants. Recent advances in neural rendering, such as the Neural Radiance Field (NeRF), offer the potential for greater realism in metaverse meetings. However, the slow rendering speed of NeRF poses challenges for real-time conferencing. We envision a pipeline for a future extended reality metaverse conferencing system that leverages monocular video acquisition and free-viewpoint synthesis to enhance data and hardware efficiency. Towards an immersive conferencing experience, we explore an accelerated NeRF-based free-viewpoint synthesis algorithm for rendering photorealistic human dynamics more efficiently. We show that our algorithm achieves comparable rendering quality while performing training and inference 44.5% and 213% faster than state-of-the-art methods, respectively. Our exploration provides a design basis for constructing metaverse conferencing systems that can handle complex application scenarios, including dynamic scene relighting with customized themes and multi-user conferencing that harmonizes real-world people into an extended world., Comment: Accepted to CVPR 2023 ECV Workshop

In the absence of an authoritative statement about a rumor, people may expose the truth behind such rumor through their responses on social media. Most rumor detection methods aggregate the information of all the responses and have made great progress. However, due to the different backgrounds of users, the responses have different relevance for discovering th suspicious points hidden in a rumor claim. The methods that focus on all the responding tweets would dilute the effect of the critical ones. Moreover, for a multi-modal rumor claim, the focus of a user may be on several words in the text or an object in the image, so the different modalities should be considered to select the relevant responses and verify the claim. In this paper, we propose a novel multi-modal rumor detection model, termed Focal Reasoning Model (FoRM), to filter out the irrelevant responses and further conduct fine-grained reasoning with the multi-modal claim and corresponding responses. Concretely, there are two main components in our FoRM: the coarse-grained selection and the fine-grained reasoning. The coarse-grained selection component leverages the post-level features of the responses to verify the claim and learns a relevant score of each response. Based on the relevant scores, the most relevant responses are reserved as the critical ones to the further reasoning. In the fine-grained reasoning component, we design a relation attention module to explore the fine-grained relations, i.e., token-to-token and token-to-object relations, between the reserved responses and the multi-modal claim for finding out the valuable clues. Extensive experiments have been conducted on two real-world datasets, and the results demonstrate that our proposed model outperforms all the baselines., Comment: Submitted to TKDE

Monocular 3D detection is a challenging task due to the lack of accurate 3D information. Existing approaches typically rely on geometry constraints and dense depth estimates to facilitate the learning, but often fail to fully exploit the benefits of three-dimensional feature extraction in frustum and 3D space. In this paper, we propose \textbf{OccupancyM3D}, a method of learning occupancy for monocular 3D detection. It directly learns occupancy in frustum and 3D space, leading to more discriminative and informative 3D features and representations. Specifically, by using synchronized raw sparse LiDAR point clouds, we define the space status and generate voxel-based occupancy labels. We formulate occupancy prediction as a simple classification problem and design associated occupancy losses. Resulting occupancy estimates are employed to enhance original frustum/3D features. As a result, experiments on KITTI and Waymo open datasets demonstrate that the proposed method achieves a new state of the art and surpasses other methods by a significant margin. Codes and pre-trained models will be available at \url{https://github.com/SPengLiang/OccupancyM3D}.

In non-life insurance, it is essential to understand the serial dynamics and dependence structure of the longitudinal insurance data before using them. Existing actuarial literature primarily focuses on modeling, which typically assumes a lack of serial dynamics and a pre-specified dependence structure of claims across multiple years. To fill in the research gap, we develop two diagnostic tests, namely the serial dynamic test and correlation test, to assess the appropriateness of these assumptions and provide justifiable modeling directions. The tests involve the following ingredients: i) computing the change of the cross-sectional estimated parameters under a logistic regression model and the empirical residual correlations of the claim occurrence indicators across time, which serve as the indications to detect serial dynamics; ii) quantifying estimation uncertainty using the randomly weighted bootstrap approach; iii) developing asymptotic theories to construct proper test statistics. The proposed tests are examined by simulated data and applied to two non-life insurance datasets, revealing that the two datasets behave differently.

Motion prediction is essential for safe and efficient autonomous driving. However, the inexplicability and uncertainty of complex artificial intelligence models may lead to unpredictable failures of the motion prediction module, which may mislead the system to make unsafe decisions. Therefore, it is necessary to develop methods to guarantee reliable autonomous driving, where failure detection is a potential direction. Uncertainty estimates can be used to quantify the degree of confidence a model has in its predictions and may be valuable for failure detection. We propose a framework of failure detection for motion prediction from the uncertainty perspective, considering both motion uncertainty and model uncertainty, and formulate various uncertainty scores according to different prediction stages. The proposed approach is evaluated based on different motion prediction algorithms, uncertainty estimation methods, uncertainty scores, etc., and the results show that uncertainty is promising for failure detection for motion prediction but should be used with caution., Comment: Accepted by 2023 IEEE International Conference on Robotics and Automation (ICRA 2023)

Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of fully-supervised methods to augment labeled and unlabeled data, which is sub-optimal. In this paper, we design a data augmentation method for semi-supervised learning, which we call Semi-Sampling. Specifically, we use ground truth labels and pseudo labels to crop gt samples and pseudo samples on labeled frames and unlabeled frames, respectively. Then we can generate a gt sample database and a pseudo sample database. When training a teacher-student semi-supervised framework, we randomly select gt samples and pseudo samples to both labeled frames and unlabeled frames, making a strong data augmentation for them. Our semi-sampling can be regarded as an extension of gt-sampling to semi-supervised learning. Our method is simple but effective. We consistently improve state-of-the-art methods on ScanNet, SUN-RGBD, and KITTI benchmarks by large margins. For example, when training using only 10% labeled data on ScanNet, we achieve 3.1 mAP and 6.4 mAP improvement upon 3DIoUMatch in terms of mAP@0.25 and mAP@0.5. When training using only 1% labeled data on KITTI, we boost 3DIoUMatch by 3.5 mAP, 6.7 mAP and 14.1 mAP on car, pedestrian and cyclist classes. Codes will be made publicly available at https://github.com/LittlePey/Semi-Sampling.

Autonomous driving confronts great challenges in complex traffic scenarios, where the risk of Safety of the Intended Functionality (SOTIF) can be triggered by the dynamic operational environment and system insufficiencies. The SOTIF risk is reflected not only intuitively in the collision risk with objects outside the autonomous vehicles (AVs), but also inherently in the performance limitation risk of the implemented algorithms themselves. How to minimize the SOTIF risk for autonomous driving is currently a critical, difficult, and unresolved issue. Therefore, this paper proposes the "Self-Surveillance and Self-Adaption System" as a systematic approach to online minimize the SOTIF risk, which aims to provide a systematic solution for monitoring, quantification, and mitigation of inherent and external risks. The core of this system is the risk monitoring of the implemented artificial intelligence algorithms within the AV. As a demonstration of the Self-Surveillance and Self-Adaption System, the risk monitoring of the perception algorithm, i.e., YOLOv5 is highlighted. Moreover, the inherent perception algorithm risk and external collision risk are jointly quantified via SOTIF entropy, which is then propagated downstream to the decision-making module and mitigated. Finally, several challenging scenarios are demonstrated, and the Hardware-in-the-Loop experiments are conducted to verify the efficiency and effectiveness of the system. The results demonstrate that the Self-Surveillance and Self-Adaption System enables dependable online monitoring, quantification, and mitigation of SOTIF risk in real-time critical traffic environments., Comment: 16 pages, 10 figures, 2 tables, submitted to IEEE TITS

Perception algorithms in autonomous driving systems confront great challenges in long-tail traffic scenarios, where the problems of Safety of the Intended Functionality (SOTIF) could be triggered by the algorithm performance insufficiencies and dynamic operational environment. However, such scenarios are not systematically included in current open-source datasets, and this paper fills the gap accordingly. Based on the analysis and enumeration of trigger conditions, a high-quality diverse dataset is released, including various long-tail traffic scenarios collected from multiple resources. Considering the development of probabilistic object detection (POD), this dataset marks trigger sources that may cause perception SOTIF problems in the scenarios as key objects. In addition, an evaluation protocol is suggested to verify the effectiveness of POD algorithms in identifying the key objects via uncertainty. The dataset never stops expanding, and the first batch of open-source data includes 1126 frames with an average of 2.27 key objects and 2.47 normal objects in each frame. To demonstrate how to use this dataset for SOTIF research, this paper further quantifies the perception SOTIF entropy to confirm whether a scenario is unknown and unsafe for a perception system. The experimental results show that the quantified entropy can effectively and efficiently reflect the failure of the perception algorithm., Comment: 7 pages, 5 figures, 4 tables, submitted to 2023 ICRA