Search

The parity anomalous semimetal is a topological state of matter characterized by its semi-metallic nature and a quantum Hall conductance of one-half $e^{2}/h$ ($e$ is the elementary charge and $h$ is the Planck constant). Here we investigate the topological phase transition driven by disorder in a semi-magnetic structure of topological insulator, and narrow-gap weak topological insulator film. We demonstrate that strong disorder not only leads to a topological transition from the parity anomalous semimetal to a diffusive metal with non-quantized anomalous Hall conductance, but also induces the topological phase in a trivial insulating phase. Our calculations of the local density of states provide clear picture for the formation of a single gapless Dirac fermion, which emerges as the disorder strength increases. The half quantized Hall effect is attributed to the existence of the gapless Dirac cone. Our findings of disorder-induced parity anomalous semimetal and diffusive metal significantly advance our understanding of the disorder-driven topological phase transition in magnetic topological insulators, opening up new avenues for further exploration in the field of quantum materials., Comment: 6 pages, 4 figures

Dynamic jumping on high platforms and over gaps differentiates legged robots from wheeled counterparts. Compared to walking on rough terrains, dynamic locomotion on abrupt surfaces requires fusing proprioceptive and exteroceptive perception for explosive movements. In this paper, we propose SF-TIM (Simple Framework combining Terrain Imagination and Measurement), a single-policy method that enhances quadrupedal robot jumping agility, while preserving their fundamental blind walking capabilities. In addition, we introduce a terrain-guided reward design specifically to assist quadrupedal robots in high jumping, improving their performance in this task. To narrow the simulation-to-reality gap in quadrupedal robot learning, we introduce a stable and high-speed elevation map generation framework, enabling zero-shot simulation-to-reality transfer of locomotion ability. Our algorithm has been deployed and validated on both the small-/large-size quadrupedal robots, demonstrating its effectiveness in real-world applications: the robot has successfully traversed various high platforms and gaps, showing the robustness of our proposed approach. A demo video has been made available at https://flysoaryun.github.io/SF-TIM., Comment: A demo video has been made available at https://flysoaryun.github.io/SF-TIM

Reed-Solomon (RS) codes are widely used to correct errors in storage systems. Finding the error locator polynomial is one of the key steps in the error correction procedure of RS codes. Modular Approach (MA) is an effective algorithm for solving the Welch-Berlekamp (WB) key-equation problem to find the error locator polynomial that needs $2t$ steps, where $t$ is the error correction capability. In this paper, we first present a new MA algorithm that only requires $2e$ steps and then propose two fast decoding algorithms for RS codes based on our MA algorithm, where $e$ is the number of errors and $e\leq t$. We propose Improved-Frequency Domain Modular Approach (I-FDMA) algorithm that needs $2e$ steps to solve the error locator polynomial and present our first decoding algorithm based on the I-FDMA algorithm. We show that, compared with the existing methods based on MA algorithms, our I-FDMA algorithm can effectively reduce the decoding complexity of RS codes when $e

The interaction between boron and hydrogen at grain boundaries has been investigated experimentally and numerically in boron-doped and boron-free martensitic steels using thermal desorption spectrometry (TDS) and ab initio calculations. The calculations show that boron, which mostly segregates into prior austenite grain boundaries (PAGBs), repels hydrogen. This behavior has also been observed using TDS measurements, with the disappearance of one peak when boron is incorporated into the microstructure. Additionally, the microstructure of both boron-doped and boron-free steels has been studied through electron backscattered diffraction, electron channeling contrast imaging, synchrotron X-ray measurements, and atom probe tomography. While both steels have a similar grain size, grain boundary distribution, and dislocation densities, pronounced boron segregation into PAGBs is observed for boron-doped steels. Therefore, the equilibrium hydrogen concentration in different trapping sites has been evaluated using the Langmuir-McLean approximation. This thermodynamic model shows that the distribution of hydrogen is identical for all traps when the total hydrogen concentration is low for boron-free steel. However, when it increases, traps of the lowest segregation energies (mostly PAGBs) are firstly saturated, which promotes failure initiation at this defect type. This finding partially explains why PAGBs are the weakest microstructure feature when martensitic steels are exposed to hydrogen-containing environments., Comment: Pre-printed version, also submitted to hal science: https://hal.science/hal-04631250

Panoramic images can broaden the Field of View (FoV), occlusion-aware prediction can deepen the understanding of the scene, and domain adaptation can transfer across viewing domains. In this work, we introduce a novel task, Occlusion-Aware Seamless Segmentation (OASS), which simultaneously tackles all these three challenges. For benchmarking OASS, we establish a new human-annotated dataset for Blending Panoramic Amodal Seamless Segmentation, i.e., BlendPASS. Besides, we propose the first solution UnmaskFormer, aiming at unmasking the narrow FoV, occlusions, and domain gaps all at once. Specifically, UnmaskFormer includes the crucial designs of Unmasking Attention (UA) and Amodal-oriented Mix (AoMix). Our method achieves state-of-the-art performance on the BlendPASS dataset, reaching a remarkable mAPQ of 26.58% and mIoU of 43.66%. On public panoramic semantic segmentation datasets, i.e., SynPASS and DensePASS, our method outperforms previous methods and obtains 45.34% and 48.08% in mIoU, respectively. The fresh BlendPASS dataset and our source code are available at https://github.com/yihong-97/OASS., Comment: Accepted to ECCV 2024. The fresh dataset and source code are available at https://github.com/yihong-97/OASS

Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis and recovering them well-founded is the goal of speech error correction. In this paper, we propose a non-autoregressive speech error correction method. A Confidence Module measures the uncertainty of each word of the N-best ASR hypotheses as the reference to find the wrong word position. Besides, the acoustic feature from the ASR encoder is also used to provide the correct pronunciation references. N-best candidates from ASR are aligned using the edit path, to confirm each other and recover some missing character errors. Furthermore, the cross-attention mechanism fuses the information between error correction references and the ASR hypothesis. The experimental results show that both the acoustic and confidence references help with error correction. The proposed system reduces the error rate by 21% compared with the ASR model.

The complexity of financial data, characterized by its variability and low signal-to-noise ratio, necessitates advanced methods in quantitative investment that prioritize both performance and interpretability.Transitioning from early manual extraction to genetic programming, the most advanced approach in the alpha factor mining domain currently employs reinforcement learning to mine a set of combination factors with fixed weights. However, the performance of resultant alpha factors exhibits inconsistency, and the inflexibility of fixed factor weights proves insufficient in adapting to the dynamic nature of financial markets. To address this issue, this paper proposes a two-stage formulaic alpha generating framework AlphaForge, for alpha factor mining and factor combination. This framework employs a generative-predictive neural network to generate factors, leveraging the robust spatial exploration capabilities inherent in deep learning while concurrently preserving diversity. The combination model within the framework incorporates the temporal performance of factors for selection and dynamically adjusts the weights assigned to each component alpha factor. Experiments conducted on real-world datasets demonstrate that our proposed model outperforms contemporary benchmarks in formulaic alpha factor mining. Furthermore, our model exhibits a notable enhancement in portfolio returns within the realm of quantitative investment and real money investment., Comment: 10 pages, 3 figures

In offline Imitation Learning (IL), one of the main challenges is the \textit{covariate shift} between the expert observations and the actual distribution encountered by the agent, because it is difficult to determine what action an agent should take when outside the state distribution of the expert demonstrations. Recently, the model-free solutions introduce the supplementary data and identify the latent expert-similar samples to augment the reliable samples during learning. Model-based solutions build forward dynamic models with conservatism quantification and then generate additional trajectories in the neighborhood of expert demonstrations. However, without reward supervision, these methods are often over-conservative in the out-of-expert-support regions, because only in states close to expert-observed states can there be a preferred action enabling policy optimization. To encourage more exploration on expert-unobserved states, we propose a novel model-based framework, called offline Imitation Learning with Self-paced Reverse Augmentation (SRA). Specifically, we build a reverse dynamic model from the offline demonstrations, which can efficiently generate trajectories leading to the expert-observed states in a self-paced style. Then, we use the subsequent reinforcement learning method to learn from the augmented trajectories and transit from expert-unobserved states to expert-observed states. This framework not only explores the expert-unobserved states but also guides maximizing long-term returns on these states, ultimately enabling generalization beyond the expert data. Empirical results show that our proposal could effectively mitigate the covariate shift and achieve the state-of-the-art performance on the offline imitation learning benchmarks. Project website: \url{https://www.lamda.nju.edu.cn/shaojj/KDD24_SRA/}., Comment: Accepted by KDD2024

Chern insulators are topologically non-trivial states of matter characterized by incompressible bulk and chiral edge states. Incorporating topological Chern bands with strong electronic correlations provides a versatile playground for studying emergent quantum phenomena. In this study, we resolve the correlated Chern insulators (CCIs) in magic-angle twisted bilayer graphene (MATBG) through Rydberg exciton sensing spectroscopy, and unveil their direct link with the zero-field cascade features in the electronic compressibility. The compressibility minima in the cascade are found to deviate substantially from nearby integer fillings (by $\Delta\nu$) and coincide with the onsets of CCIs in doping densities, yielding a quasi-universal relation $B_c$=$\Phi_0\Delta\nu/C$ (onset magnetic field $B_c$, magnetic flux quantum $\Phi_0$ and Chern number $C$). We suggest these onsets lie on the intersection where the integer filling of localized "f-orbitals" and Chern bands are simultaneously reached. Our findings update the field-dependent phase diagram of MATBG and directly support the topological heavy fermion model., Comment: 24 pages, 4 figures, supplementary material

Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or benchmark in a fully supervised manner. While the dense occupancy grids need point-wise semantic annotations, which incur expensive and tedious labeling costs. In this paper, we build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. In particular, we propose a simple yet effective approach called Scribble2Scene, which bridges the gap between the sparse scribble annotations and fully-supervision. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance. Experiments on SemanticKITTI demonstrate that Scribble2Scene achieves competitive performance against the fully-supervised counterparts, showing 99% performance of the fully-supervised models with only 13.5% voxels labeled. Both annotations of ScribbleSC and our full implementation are available at https://github.com/songw-zju/Scribble2Scene., Comment: Accepted by IJCAI2024

Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the barrier of feature redundancy when constructing vectorized High-Definition (HD) maps. In this paper, we revisit the temporal fusion of vectorized HD maps, focusing on temporal instance consistency and temporal map consistency learning. To improve the representation of instances in single-frame maps, we introduce a novel method, DTCLMapper. This approach uses a dual-stream temporal consistency learning module that combines instance embedding with geometry maps. In the instance embedding component, our approach integrates temporal Instance Consistency Learning (ICL), ensuring consistency from vector points and instance features aggregated from points. A vectorized points pre-selection module is employed to enhance the regression efficiency of vector points from each instance. Then aggregated instance features obtained from the vectorized points preselection module are grounded in contrastive learning to realize temporal consistency, where positive and negative samples are selected based on position and semantic information. The geometry mapping component introduces Map Consistency Learning (MCL) designed with self-supervised learning. The MCL enhances the generalization capability of our consistent learning approach by concentrating on the global location and distribution constraints of the instances. Extensive experiments on well-recognized benchmarks indicate that the proposed DTCLMapper achieves state-of-the-art performance in vectorized mapping tasks, reaching 61.9% and 65.1% mAP scores on the nuScenes and Argoverse datasets, respectively. The source code is available at https://github.com/lynn-yu/DTCLMapper., Comment: Accepted to IEEE Transactions on Intelligent Transportation Systems (T-ITS). The source code is available at https://github.com/lynn-yu/DTCLMapper

Maximum distance separable (MDS) codes facilitate the achievement of elevated levels of fault tolerance in storage systems while incurring minimal redundancy overhead. Reed-Solomon (RS) codes are typical MDS codes with the sub-packetization level being one, however, they require large repair bandwidth defined as the total amount of symbols downloaded from other surviving nodes during single-node failure/repair. In this paper, we present the {\em set transformation}, which can transform any MDS code into set transformed code such that (i) the sub-packetization level is flexible and ranges from 2 to $(n-k)^{\lfloor\frac{n}{n-k}\rfloor}$ in which $n$ is the number of nodes and $k$ is the number of data nodes, (ii) the new code is MDS code, (iii) the new code has lower repair bandwidth for any single-node failure. We show that our set transformed codes have both lower repair bandwidth and lower field size than the existing related MDS array codes, such as elastic transformed codes \cite{10228984}. Specifically, our set transformed codes have $2\%-6.6\%$ repair bandwidth reduction compared with elastic transformed codes \cite{10228984} for the evaluated typical parameters.

In this paper, we plan to show an eigenvalue algorithm for block Hessenberg matrices by using the idea of non-commutative integrable systems and matrix-valued orthogonal polynomials. We introduce adjacent families of matrix-valued $\theta$-deformed bi-orthogonal polynomials, and derive corresponding discrete non-commutative hungry Toda lattice from discrete spectral transformations for polynomials. It is shown that this discrete system can be used as a pre-precessing algorithm for block Hessenberg matrices. Besides, some convergence analysis and numerical examples of this algorithm are presented., Comment: 24 pages, 2 figures. Comments are welcome

LiDAR-based Moving Object Segmentation (MOS) aims to locate and segment moving objects in point clouds of the current scan using motion information from previous scans. Despite the promising results achieved by previous MOS methods, several key issues, such as the weak coupling of temporal and spatial information, still need further study. In this paper, we propose a novel LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model, termed MambaMOS. Firstly, we develop a novel embedding module, the Time Clue Bootstrapping Embedding (TCBE), to enhance the coupling of temporal and spatial information in point clouds and alleviate the issue of overlooked temporal clues. Secondly, we introduce the Motion-aware State Space Model (MSSM) to endow the model with the capacity to understand the temporal correlations of the same object across different time steps. Specifically, MSSM emphasizes the motion states of the same object at different time steps through two distinct temporal modeling and correlation steps. We utilize an improved state space model to represent these motion differences, significantly modeling the motion states. Finally, extensive experiments on the SemanticKITTI-MOS and KITTI-Road benchmarks demonstrate that the proposed MambaMOS achieves state-of-the-art performance. The source code is publicly available at https://github.com/Terminal-K/MambaMOS., Comment: Accepted to ACM MM 2024. The source code is publicly available at https://github.com/Terminal-K/MambaMOS

To solve the Unmanned Aerial Vehicle (UAV) path planning problem, a meta-heuristic optimization algorithm called competitive game optimizer (CGO) is proposed. In the CGO model, three phases of exploration and exploitation, and candidate replacement, are established, corresponding to the player's search for supplies and combat, and the movement toward a safe zone. In the algorithm exploration phase, Levy flight is introduced to improve the global convergence of the algorithm. The encounter probability which adaptively changes with the number of iterations is also introduced in the CGO. The balance between exploration and exploitation of solution space of optimization problem is realized, and each step is described and modeled mathematically. The performance of the CGO was evaluated on a set of 41 test functions taken from CEC2017 and CEC2022. It was then compared with eight widely recognized meta-heuristic optimization algorithms. The simulation results demonstrate that the proposed algorithm successfully achieves a balanced trade-off between exploration and exploitation, showcasing remarkable advantages when compared to seven classical algorithms. In addition, in order to further verify the effectiveness of the CGO, the CGO is applied to 8 practical engineering design problems and UAV path planning, and the results show that the CGO has strong performance in dealing with these practical optimization problems, and has a good application prospect.

We demonstrate that Debye shielding cannot be employed to constrain the cosmological abundance of magnetic monopoles, contrary to what is stated in the previous literature. Current model-independent bounds on the monopole abundance are then revisited for unit Dirac magnetic charge. We find that the Andromeda Parker bound can be employed to set an upper limit on the monopole flux at the level of $F_M\lesssim 5.3\times 10^{-19}\,\text{cm}^{-2}\text{s}^{-1}\text{sr}^{-1}$ for a monopole mass $10^{13}\,\text{GeV}/c^2\lesssim m\lesssim 10^{16}\,\text{GeV}/c^2$, which is more stringent than the MACRO direct search limit by two orders of magnitude. This translates into stringent constraints on the monopole density parameter $\Omega_M$ at the level of $10^{-7}-10^{-4}$ depending on the mass. For larger monopole masses the scenarios in which magnetic monopoles account for all or the majority of dark matter are disfavored., Comment: 26 pages, 2 figures. Explanations added regarding the fluid approximation. Matching the journal version

Quantum algorithms offer significant speed-ups over their classical counterparts in various applications. In this paper, we develop quantum algorithms for the Kalman filter widely used in classical control engineering using the block encoding method. The entire calculation process is achieved by performing matrix operations on Hamiltonians based on the block encoding framework, including addition, multiplication, and inversion, which can be completed in a unified framework compared to previous quantum algorithms for solving control problems. We demonstrate that the quantum algorithm exponentially accelerates the computation of the Kalman filter compared to traditional methods. The time complexity can be reduced from $O(n^3)$ to $O(\kappa poly\log(n/\epsilon)\log(1/\epsilon'))$, where $n$ represents the matrix dimension, $\kappa$ denotes the condition number for the matrix to be inverted, $\epsilon$ indicates desired precision in block encoding, $\epsilon'$ signifies desired precision in matrix inversion. This paper provides a comprehensive quantum solution for implementing the Kalman filter and serves as an attempt to broaden the scope of quantum computation applications. Finally, we present an illustrative example implemented in Qiskit (a Python-based open-source toolkit) as a proof-of-concept., Comment: 23 pages, 20 figures, 3 tables

In this paper, we mainly consider a combinatoric explanation for block Pfaffians in terms of non-intersecting paths, as a generalization of results obtained by Stembridge. As applications, we demonstrate how are generating functions of non-intersecting paths related to skew orthogonal polynomials and their deformations, including a new concept called multiple partial-skew orthogonal polynomials., Comment: 22 pages, 4 figures

Relying on paired synthetic data, existing learning-based Computational Aberration Correction (CAC) methods are confronted with the intricate and multifaceted synthetic-to-real domain gap, which leads to suboptimal performance in real-world applications. In this paper, in contrast to improving the simulation pipeline, we deliver a novel insight into real-world CAC from the perspective of Unsupervised Domain Adaptation (UDA). By incorporating readily accessible unpaired real-world data into training, we formalize the Domain Adaptive CAC (DACAC) task, and then introduce a comprehensive Real-world aberrated images (Realab) dataset to benchmark it. The setup task presents a formidable challenge due to the intricacy of understanding the target aberration domain. To this intent, we propose a novel Quntized Domain-Mixing Representation (QDMR) framework as a potent solution to the issue. QDMR adapts the CAC model to the target domain from three key aspects: (1) reconstructing aberrated images of both domains by a VQGAN to learn a Domain-Mixing Codebook (DMC) which characterizes the degradation-aware priors; (2) modulating the deep features in CAC model with DMC to transfer the target domain knowledge; and (3) leveraging the trained VQGAN to generate pseudo target aberrated images from the source ones for convincing target domain supervision. Extensive experiments on both synthetic and real-world benchmarks reveal that the models with QDMR consistently surpass the competitive methods in mitigating the synthetic-to-real gap, which produces visually pleasant real-world CAC results with fewer artifacts. Codes and datasets will be made publicly available., Comment: Codes and datasets will be made publicly available at https://github.com/zju-jiangqi/QDMR

Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation, continuity across varying viewpoints, and single-view occlusion. Our paper introduces OccFiner, a novel offboard framework designed to enhance the accuracy of vision-based occupancy predictions. OccFiner operates in two hybrid phases: 1) a multi-to-multi local propagation network that implicitly aligns and processes multiple local frames for correcting onboard model errors and consistently enhancing occupancy accuracy across all distances. 2) the region-centric global propagation, focuses on refining labels using explicit multi-view geometry and integrating sensor bias, especially to increase the accuracy of distant occupied voxels. Extensive experiments demonstrate that OccFiner improves both geometric and semantic accuracy across various types of coarse occupancy, setting a new state-of-the-art performance on the SemanticKITTI dataset. Notably, OccFiner elevates vision-based SSC models to a level even surpassing that of LiDAR-based onboard SSC models. Furthermore, OccFiner is the first to achieve automatic annotation of SSC in a purely vision-based approach. Quantitative experiments prove that OccFiner successfully facilitates occupancy data loop-closure in autonomous driving. Additionally, we quantitatively and qualitatively validate the superiority of the offboard approach on city-level SSC static maps. The source code will be made publicly available at https://github.com/MasterHow/OccFiner., Comment: The source code will be made publicly available at https://github.com/MasterHow/OccFiner

Adapting an automatic speech recognition (ASR) system to unseen noise environments is crucial. Integrating adapters into neural networks has emerged as a potent technique for transfer learning. This study thoroughly investigates adapter-based ASR adaptation in noisy environments. We conducted experiments using the CHiME--4 dataset. The results show that inserting the adapter in the shallow layer yields superior effectiveness, and there is no significant difference between adapting solely within the shallow layer and adapting across all layers. The simulated data helps the system to improve its performance under real noise conditions. Nonetheless, when the amount of data is the same, the real data is more effective than the simulated data. Multi-condition training is still useful for adapter training. Furthermore, integrating adapters into speech enhancement-based ASR systems yields substantial improvements.

Electron-phonon coupling in magic-angle twisted bilayer graphene is an important but difficult topic. We propose a scheme to simplify and understand this problem. Weighted by the coupling strength with the low-energy heavy electrons ($f$ orbitals), several moir\'{e} optical phonons are singled out which strongly couple to the flat bands. These modes have localized envelopes in the moir\'{e} scale, while in the atomic scale they inherit the monolayer oscillations like the Kekul\'{e} pattern. They flip the flavor of $f$ orbitals, helping stabilize some symmetry-breaking orders. Such electron-phonon couplings are incorporated into an effective extended Holstein model, where both phonons and electrons are written as moir\'{e} scale basis. We hope this model will inspire some insights guiding further studies about the superconductivity and other correlated effects in this system.

3D human pose estimation captures the human joint points in three-dimensional space while keeping the depth information and physical structure. That is essential for applications that require precise pose information, such as human-computer interaction, scene understanding, and rehabilitation training. Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content. Given the remarkable self-attention mechanism of transformers, capable of capturing the spatial-temporal correlation from multi-view video datasets, we propose a multi-stage framework for 3D sequence-to-sequence (seq2seq) human pose detection. Firstly, the spatial module represents the human pose feature by intra-image content, while the frame-image relation module extracts temporal relationships and 3D spatial positional relationship features between the multi-perspective images. Secondly, the self-attention mechanism is adopted to eliminate the interference from non-human body parts and reduce computing resources. Our method is evaluated on Human3.6M, a popular 3D human pose detection dataset. Experimental results demonstrate that our approach achieves state-of-the-art performance on this dataset. The source code will be available at https://github.com/WUJINHUAN/3D-human-pose., Comment: Accepted to IJCNN 2024. The source code will be available at https://github.com/WUJINHUAN/3D-human-pose

Human pose estimation is a fundamental and appealing task in computer vision. Traditional frame-based cameras and videos are commonly applied, yet, they become less reliable in scenarios under high dynamic range or heavy motion blur. In contrast, event cameras offer a robust solution for navigating these challenging contexts. Predominant methodologies incorporate event cameras into learning frameworks by accumulating events into event frames. However, such methods tend to marginalize the intrinsic asynchronous and high temporal resolution characteristics of events. This disregard leads to a loss in essential temporal dimension data, crucial for discerning distinct actions. To address this issue and to unlock the 3D potential of event information, we introduce two 3D event representations: the Rasterized Event Point Cloud (RasEPC) and the Decoupled Event Voxel (DEV). The RasEPC collates events within concise temporal slices at identical positions, preserving 3D attributes with statistical cues and markedly mitigating memory and computational demands. Meanwhile, the DEV representation discretizes events into voxels and projects them across three orthogonal planes, utilizing decoupled event attention to retrieve 3D cues from the 2D planes. Furthermore, we develop and release EV-3DPW, a synthetic event-based dataset crafted to facilitate training and quantitative analysis in outdoor scenes. On the public real-world DHP19 dataset, our event point cloud technique excels in real-time mobile predictions, while the decoupled event voxel method achieves the highest accuracy. Experiments on EV-3DPW demonstrate that the robustness of our proposed 3D representation methods compared to traditional RGB images and event frame techniques under the same backbones. Our code and dataset have been made publicly available at https://github.com/MasterHow/EventPointPose., Comment: Extended version of arXiv:2206.04511. The code and dataset are available at https://github.com/MasterHow/EventPointPose

Roadside camera-driven 3D object detection is a crucial task in intelligent transportation systems, which extends the perception range beyond the limitations of vision-centric vehicles and enhances road safety. While previous studies have limitations in using only depth or height information, we find both depth and height matter and they are in fact complementary. The depth feature encompasses precise geometric cues, whereas the height feature is primarily focused on distinguishing between various categories of height intervals, essentially providing semantic context. This insight motivates the development of Complementary-BEV (CoBEV), a novel end-to-end monocular 3D object detection framework that integrates depth and height to construct robust BEV representations. In essence, CoBEV estimates each pixel's depth and height distribution and lifts the camera features into 3D space for lateral fusion using the newly proposed two-stage complementary feature selection (CFS) module. A BEV feature distillation framework is also seamlessly integrated to further enhance the detection accuracy from the prior knowledge of the fusion-modal CoBEV teacher. We conduct extensive experiments on the public 3D detection benchmarks of roadside camera-based DAIR-V2X-I and Rope3D, as well as the private Supremind-Road dataset, demonstrating that CoBEV not only achieves the accuracy of the new state-of-the-art, but also significantly advances the robustness of previous methods in challenging long-distance scenarios and noisy camera disturbance, and enhances generalization by a large margin in heterologous settings with drastic changes in scene and camera parameters. For the first time, the vehicle AP score of a camera model reaches 80% on DAIR-V2X-I in terms of easy mode. The source code will be made publicly available at https://github.com/MasterHow/CoBEV., Comment: The source code will be made publicly available at https://github.com/MasterHow/CoBEV

We investigate the integrability of the non-commutative leapfrog map in this paper. Firstly, we derive the explicit formula for the non-commutative leapfrog map and corresponding discrete zero-curvature equation by employing the concept of non-commutative cross-ratio. Then we revisit this discrete map, as well as its continuous limit, from the perspective of non-commutative Laurent bi-orthogonal polynomials. Finally, the Poisson structure for this discrete non-commutative map is formulated with the help of a non-commutative network. We aim to enhance our understanding of the integrability properties of the non-commutative leapfrog map and its related mathematical structures through these analysis and constructions., Comment: 32 pages. Comments are welcome