arXiv subjects

Mingzhe Guo

Publications and source records attributed to Mingzhe Guo.

At least 19 recordsLinked to original sources

arXiv2026

Towards robust multimodal 3D object detection via visual foundation models

Multimodal 3D object detection is fundamental to robust perception in autonomous driving because it integrates complementary information from LiDAR and camera sensors. However, existing methods often fail to maintain robustness under out-of-distribution (OOD) corruptions caused by sensor noise, adverse weather, and environmental changes. To address this problem, we propose RoboDistill, a robust and generalizable multimodal 3D object detection framework that leverages visual foundation models (VFMs), such as the Segment Anything Model (SAM). First, we introduce SAM-AD, a domain-specific pretraining strategy that fine-tunes SAM on autonomous-driving imagery to extract feature representations with rich semantic information. Second, we design the AD Feature Pyramid Network (AD-FPN) to refine and upsample SAM features at multiple scales for seamless fusion with LiDAR features. Third, we develop the Depth-Guided Wavelet Attention (DGWA) module, which suppresses high-frequency sensor noise while preserving critical contextual information. Finally, we introduce KD Fusion, in which the pretrained SAM-AD serves as a teacher that distills high-quality visual knowledge into a lightweight point-cloud network, thereby improving robustness under noisy conditions. Extensive experiments across 27 challenging OOD corruption settings show that RoboDistill generally delivers stronger or competitive detection performance and robustness relative to representative state-of-the-art methods. This work bridges the gap between VFMs and 3D object detection and advances robust multimodal perception for real-world autonomous-driving applications.

cs.CV↗

arXiv2026

Alfvénic Motions in a Stratified Open Flux Tube: Transition from Propagating to Locally Standing Motions and Implications for the Kelvin-Helmholtz Instability

Standing transverse waves in closed coronal structures have been widely studied as a possible route to energy dissipation, with resonant absorption transferring kink wave energy to localized Alfvénic motions and the Kelvin-Helmholtz instability (KHI) accelerating the formation of small dissipative scales. However, it remains unclear whether the same mechanism applies to the open corona, given the long-standing consensus that the KHI tends to be prohibited for propagating Alfvénic waves. Within the framework of magnetohydrodynamics (MHD), we perform three-dimensional MHD simulations of boundary-driven kink waves in a gravitationally stratified open flux tube extending from the chromosphere into the corona. We find that propagating waves in open magnetic structures can also drive the system toward a turbulent state, with KH vortices clearly identifiable across the flux tube. This occurs because resonant absorption transfers energy from the propagating kink waves to azimuthal Alfvénic motions near the tube boundary, and wave reflection off the gradient of the Alfvén speed subsequently enables these boundary motions to acquire a locally standing character. Our results provide a possible answer to the long-standing question of whether and how propagating waves in open magnetic structures can generate nonlinear turbulent fine structures despite their globally propagating nature.

astro-ph.SR↗

arXiv2026

High-Frequency Magnetohydrodynamic Waves with Substantial Energy in the Solar Polar Corona

The acceleration and heating of the fast solar wind remain long-standing challenges in space physics. One type of leading theoretical models requires high-frequency magnetohydrodynamic (MHD) waves to transport and dissipate sufficient energy in the corona. However, such high-frequency waves with energetically significant amplitudes have never been unambiguously observed, leaving a key gap between theories and observations. Using high-cadence, high-resolution extreme-ultraviolet imaging from Solar Orbiter's Extreme Ultraviolet Imager, we identify a previously hidden population of high-frequency MHD waves in coronal plumes of the solar polar region. An analysis of the detected propagating kink waves shows that over one-third have periods shorter than 100 s, a population largely undetected by earlier instruments. Power spectral analysis demonstrates that these high-frequency waves carry substantial energy flux, which are significantly underestimated in lower-cadence data. These results suggest that high-frequency MHD waves may contribute importantly to the energy budget of the solar polar corona and could play a role in solar wind acceleration, highlighting the value of high-resolution observations for probing energy transport in magnetized space and astrophysical plasmas.

astro-ph.SR↗

arXiv2026

Dual-Perspective Microwave and Hard X-ray Constraints of Asymmetric Nonthermal Loops in an X-class Flare

We report dual-perspective microwave and HXR observations of an X-class flare on 2024 May 15, taking advantage of the unique geometry of a front-side view from the Earth and a back-side perspective from the Solar Orbiter (SolO). Using spatially resolved imaging spectroscopy from Siberian Radioheliograph (SRH) together with Chashan Broadband Solar millimeter spectrometer (CBSmm) and STIX data, we identify a set of nonthermal flaring loops in an asymmetric magnetic field, with microwave sources located near the loop top and HXR sources associated with the southern footpoint. Compared with HXR, the microwave emission shows an opposite ascending trend, an increasing time lag in time profile, and a distinctive ``SHH'' spectral pattern, which we attribute to energy-dependent trapping and precipitation of energetic electrons in an asymmetric magnetic configuration. Flux pulsations and their spectral and polarization signatures are consistent with intermittent particle acceleration rather than MHD wave modulation. Microwave magnetic diagnostics, corroborated by non-linear force free field (NLFFF) extrapolation, provide key constraints on the three-dimensional magnetic configuration. The dual-perspective flux profile comparison and consistent QPP signatures across wavelengths together support a self-consistent picture of energy-dependent electron trapping, precipitation, and transport in these asymmetric loops.

astro-ph.SR↗

arXiv2026

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving

Most end-to-end autonomous driving methods rely on imitation learning from single expert demonstrations, often leading to conservative and homogeneous behaviors that limit generalization in complex real-world scenarios. In this work, we propose DIVER, an end-to-end driving framework that integrates reinforcement learning with diffusion-based generation to produce diverse and feasible trajectories. At the core of DIVER lies a reinforced diffusion-based generation mechanism. First, the model conditions on map elements and surrounding agents to generate multiple reference trajectories from a single ground-truth trajectory, alleviating the limitations of imitation learning that arise from relying solely on single expert demonstrations. Second, reinforcement learning is employed to guide the diffusion process, where reward-based supervision enforces safety and diversity constraints on the generated trajectories, thereby enhancing their practicality and generalization capability. Furthermore, to address the limitations of L2-based open-loop metrics in capturing trajectory diversity, we propose a novel Diversity metric to evaluate the diversity of multi-mode predictions.Extensive experiments on the closed-loop NAVSIM and Bench2Drive benchmarks, as well as the open-loop nuScenes dataset, demonstrate that DIVER significantly improves trajectory diversity, effectively addressing the mode collapse problem inherent in imitation learning.

cs.CV↗

arXiv2026

Propagating Kink Waves in Chromospheric Jet-like Structures and Coronal Plumelets

Coronal plumes and chromospheric jet-like structures are believed to be highly dynamic. We report the first direct observations of a propagating kink wave in a chromospheric jet-like structure and its associated plumelet structure in the upper corona of the solar polar region, using data from the High Resolution Imager (HRI) of the Extreme Ultraviolet Imager (EUI) on board Solar Orbiter (SO). The dark jet-like structure exhibits transverse oscillation during upward propagation, with a period of approximately 95s and a displacement of about 193km. The corresponding plumelet also displays transverse motion, with an oscillation period of around 99s and a displacement of about 315km. Given that both the dark jet-like structure and the plumelet share the same magnetic skeleton and have similar oscillation period, we suggest that these oscillations are the same transverse propagating wave originating in the chromosphere. This scenario is further supported by a 3D magnetohydrodynamic (MHD) simulation, in which both vertical and transverse perturbations were introduced in a stratified magnetic flux tube. The simulation successfully reproduces the upward propagation of a kink wave through both the chromospheric jet-like structure and the coronal plumelet. These results highlight the potential role of transverse waves in transferring energy from the lower solar atmosphere to the corona.

astro-ph.SR↗

arXiv2026

FlowAD: Ego-Scene Interactive Modeling for Autonomous Driving

Effective environment modeling is the foundation for autonomous driving, underpinning tasks from perception to planning. However, current paradigms often inadequately consider the feedback of ego motion to the observation, which leads to an incomplete understanding of the driving process and consequently limits the planning capability. To address this issue, we introduce a novel ego-scene interactive modeling paradigm. Inspired by human recognition, the paradigm represents ego-scene interaction as the scene flow relative to the ego-vehicle. This conceptualization allows for modeling ego-motion feedback within a feature learning pattern, advantageously utilizing existing log-replay datasets rather than relying on scenario simulations. We specifically propose FlowAD, a general flow-based framework for autonomous driving. Within it, an ego-guided scene partition first constructs basic flow units to quantify scene flow. The ego-vehicle's forward direction and steering velocity directly shape the partition, which reflects ego motion. Then, based on flow units, spatial and temporal flow predictions are performed to model dynamics of scene flow, encompassing both spatial displacement and temporal variation. The final task-aware enhancement exploits learned spatio-temporal flow dynamics to benefit diverse tasks through object and region-level strategies. We also propose a novel Frames before Correct Planning (FCP) metric to assess the scene understanding capability. Experiments in both open and closed-loop evaluations demonstrate FlowAD's generality and effectiveness across perception, end-to-end planning, and VLM analysis. Notably, FlowAD reduces 19% collision rate over SparseDrive with FCP improvements of 1.39 frames (60%) on nuScenes, and achieves an impressive driving score of 51.77 on Bench2Drive, proving the superiority. Code, model, and configurations will be released here.

cs.CV↗

arXiv2026

Three-dimensional kink modes in solar coronal slabs: group velocities and their implications for impulsively excited waves

Little attention has been paid to group velocities of three-dimensional (3D) MHD waves in solar coronal seismology. This study aims to present a rather comprehensive examination on the group velocities of trapped 3D kink modes in coronal slabs, emphasizing the connection of mode analysis to both mode characterization and impulsively excited 3D kink waves. We work in linear, ideal, pressureless MHD, and take the equilibrium slab to be symmetrically structured only in one transverse direction. The dispersion relation is numerically solved, with the results understood by making in-depth analytical progress. We address both the transverse fundamental and its first overtone. We develop a three-subgroup scheme for categorizing 3D kink modes on the plane spanned by the axial and out-of-plane wavenumbers. The group ($\vec{v}_{\rm gr}$) and phase velocities ($\vec{v}_{\rm ph}$) sit on the same side of the equilibrium magnetic field ($\vec{B}_0$) for the ``$\vec{B}_0$-same-side A'' and ``$\vec{B}_0$-same-side F'' subgroups, which are further discriminated by the directional similarity of $\vec{v}_{\rm gr}$ and $\vec{B}_0$. The ``$\vec{B}_0$-straddling'' subgroup is peculiar in that $\vec{v}_{\rm gr}$ and $\vec{v}_{\rm ph}$ lie astride $\vec{B}_0$, a feature that cannot be found for waves in unbounded uniform media in pressureless MHD. This ``$\vec{B}_0$-straddling'' subgroup pertains to both the fundamental and its overtones. We further place our results in the context of impulsive waves, employing the method of stationary phase to predict the large-time wavefront morphology in the plane of symmetry of the equilibrium slab. Wavefronts directed toward $\vec{B}_0$ derive exclusively from ``$\vec{B}_0$-straddling'' modes, and are confined to narrow sectors.

astro-ph.SR↗

arXiv2026

The Effect of Gravitational Stratification on Kink Oscillations in Curved Coronal Loops

Kink oscillation frequency is a key parameter for coronal seismology. It is still unclear how gravitational stratification affects the kink frequency in curved coronal loops. This work aims to investigate the effect of gravitational stratification on the frequency of kink oscillations in curved coronal loops and discuss their seismological potential. We conduct numerical computations within the ideal MHD framework to study different kink polarizations and harmonics in a curved, gravitationally stratified coronal loop. The oscillation frequencies derived from the Lagrangian displacement are compared with the WKB approximation. For the vertically polarized fundamental mode, the oscillation frequency deviates from the WKB approximation by about 18\% in the current numerical setup. Nevertheless, the oscillation frequency closely matches the local Alfvén frequency near the loop apex. On the other hand, the frequency of the horizontally polarized fundamental mode exhibits only a 7\% deviation in our current model from the WKB approximation and closely matches the local Alfvén frequency near one quarter of the loop. For the first overtones, the frequencies for both polarizations can be well described by the WKB approximation. The frequency of vertically polarized fundamental kink modes can be predicted by the local Alfvén frequency near the loop apex. In contrast, the WKB approximation remains highly reliable for estimating the frequency of horizontally polarized fundamental modes and first overtones, which is also well described by the local Alfvén frequency near one quarter of the loop. These results therefore pave the way for spatially dependent coronal seismology, enabling, e.g., the probing of magnetic field strength at different locations along a coronal loop.

astro-ph.SR↗

arXiv2024

Measurements of the solar coronal magnetic field based on coronal seismology with propagating Alfvenic waves: forward modeling

Recent observations have demonstrated the capability of mapping the solar coronal magnetic field using the technique of coronal seismology based on the ubiquitous propagating Alfvenic/kink waves through imaging spectroscopy. We established a magnetohydrodynamic (MHD) model of a gravitationally stratified open magnetic flux tube, exciting kink waves propagating upwards along the tube. Forward modeling was performed to synthesize the Fe XIII 1074.7 and 1079.8 nm spectral line profiles, which were then used to determine the wave phase speed, plasma density, and magnetic field with seismology method. A comparison between the seismologically inferred results and the corresponding input values verifies the reliability of the seismology method. In addition, we also identified some factors that could lead to errors during magnetic field measurements. Our results may serve as a valuable reference for current and future coronal magnetic field measurements based on observations of propagating kink waves.

astro-ph.SR↗

arXiv2024

Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation.

cs.CV↗

arXiv2024

Propagating Kink Waves in an Open Coronal Magnetic Flux Tube with Gravitational Stratification: Magnetohydrodynamic Simulation and Forward Modelling

Context. In the coronal open-field regions, such as coronal holes, there are many transverse waves propagating along magnetic flux tubes, generally interpreted as kink waves. Previous studies have highlighted their potential in coronal heating, solar wind acceleration, and seismological diagnostics of various physical parameters. Aims. This study aims to investigate propagating kink waves, considering both vertical and horizontal density inhomogeneity, using three-dimensional magnetohydrodynamic (MHD) simulations. Methods. We establish a 3D MHD model of a gravitationally stratified open flux tube, incorporating a velocity driver at the lower boundary to excite propagating kink waves. Forward modelling is conducted to synthesise observational signatures of the Fe ix 17.1 nm line. Results. It is found that resonant absorption and density stratification both affect the wave amplitude. When diagnosing the relative density profile with velocity amplitude, resonant damping needs to be properly considered to avoid possible underestimation. In addition, unlike standing modes, propagating waves are believed to be Kelvin-Helmholtz stable. In the presence of vertical stratification, however, phase mixing of transverse motions around the tube boundary can still induce small scales, partially dissipating wave energy and leading to a temperature increase, especially at higher altitudes. Moreover, forward modeling is conducted to synthesise observational signatures, revealing the promising potential of future coronal imaging spectrometers such as MUSE in resolving these wave-induced signatures. Also, the synthesised intensity signals exhibit apparent periodic variations, offering a potential method to indirectly observe propagating kink waves with current EUV imagers.

astro-ph.SR↗

arXiv2024

End-to-End Autonomous Driving without Costly Modularization and 3D Manual Annotation

We propose UAD, a method for vision-based end-to-end autonomous driving (E2EAD), achieving the best open-loop evaluation performance in nuScenes, meanwhile showing robust closed-loop driving quality in CARLA. Our motivation stems from the observation that current E2EAD models still mimic the modular architecture in typical driving stacks, with carefully designed supervised perception and prediction subtasks to provide environment information for oriented planning. Although achieving groundbreaking progress, such design has certain drawbacks: 1) preceding subtasks require massive high-quality 3D annotations as supervision, posing a significant impediment to scaling the training data; 2) each submodule entails substantial computation overhead in both training and inference. To this end, we propose UAD, an E2EAD framework with an unsupervised proxy to address all these issues. Firstly, we design a novel Angular Perception Pretext to eliminate the annotation requirement. The pretext models the driving scene by predicting the angular-wise spatial objectness and temporal dynamics, without manual annotation. Secondly, a self-supervised training strategy, which learns the consistency of the predicted trajectories under different augment views, is proposed to enhance the planning robustness in steering scenarios. Our UAD achieves 38.7% relative improvements over UniAD on the average collision rate in nuScenes and surpasses VAD for 41.32 points on the driving score in CARLA's Town05 Long benchmark. Moreover, the proposed method only consumes 44.3% training resources of UniAD and runs 3.4 times faster in inference. Our innovative design not only for the first time demonstrates unarguable performance advantages over supervised counterparts, but also enjoys unprecedented efficiency in data, training, and inference. Code and models will be released at https://github.com/KargoBot_Research/UAD.

cs.CV↗

arXiv2024

Kelvin-Helmholtz instability and heating in oscillating loops perturbed by power-law transverse wave drivers

Instabilities in oscillating loops are believed to be essential for dissipating the wave energy and heating the solar coronal plasma. Our aim is to study the development of the Kelvin-Helmholtz (KH) instability in an oscillating loop that is driven by random footpoint motions. Using the PLUTO code, we performed 3D simulations of a straight gravitationally stratified flux tube. The loop footpoints are embedded in chromospheric plasma, in the presence of thermal conduction and an artificially broadened transition region. Using drivers with a power-law spectrum, one with a red noise spectrum and one with the low-frequency part subtracted, we excited standing oscillations and the KH instability in our loops, after one-and-a-half periods of the oscillation. We see that our broadband drivers lead to fully deformed, turbulent loop cross-sections over the entire coronal part of the loop due to the spatially extended KH instability. The low RMS velocity of our driver without the low-frequency components supports the working hypothesis that the KH instability can easily manifest in oscillating coronal loops. We report for the first time in driven transverse oscillations of loops the apparent propagation of density perturbations due to the onset of the KH instability, from the apex towards the footpoints. Both drivers input sufficient energy to drive enthalpy and mass flux fluctuations along the loop, while also causing heating near the driven footpoint of the oscillating loop, which becomes more prominent when a low-frequency component is included in the velocity driver. Finally, our power-law driver with the low-frequency component provides a RMS input Poynting flux of the same order as the radiative losses of the quiet-Sun corona, giving us promising prospects for the contribution of decayless oscillations in coronal heating.

astro-ph.SR↗

arXiv2024

Horizontally and vertically polarized kink oscillations in curved solar coronal loops

Kink oscillations are frequently observed in coronal loops. This work aims to numerically clarify the influence of loop curvature on horizontally and vertically polarized kink oscillations. Working within the framework of ideal MHD, we conduct 3D simulations of axial fundamental kink oscillations in curved density-enhanced loops embedded in a potential magnetic field. Both horizontal and vertical polarizations are examined, and their oscillation frequencies are compared with WKB expectations. We discriminate two different density specifications. In the first (dubbed"uniform-density"), the density is axially uniform and varies continuously in the transverse direction toward a uniform ambient corona. Some further stratification is implemented in the second specification (dubbed"stratified"), allowing us to address the effect of evanescent barriers. Examining the oscillating profiles of the initially perturbed uniform-density loops, we found that the frequencies for both polarizations deviate from the WKB expectation by $\sim 10\%$. In the stratified loop, however, the frequency of the horizontal polarization deviates to a larger extent ($\sim 25\%$). We illustrate the lateral leakage of kink modes through wave tunnelling in 3D simulations, for the first time. Despite this, in both loops, the damping time-to-period ratios are similar and close to the analytical predictions for straight configurations under the thin-tube-thin-boundary (TTTB) assumption. The WKB expectation for straight configurations can reasonably describe the eigenfrequency of kink oscillations only in loops without an asymmetrical cross-loop density profile perpendicular to the oscillating direction. Lateral leakage via wave tunnelling is found to be less efficient than resonant absorption, meaning that the latter remains a robust damping mechanism for kink motions even when loop curvature is included.

astro-ph.SR↗

arXiv2024

Damped kink motions in a system of two solar coronal tubes with elliptic cross-sections

This study is motivated by observations of coordinated transverse displacements in neighboring solar active region loops, addressing specifically how the behavior of kink motions in straight two-tube equilibria is impacted by tube interactions and tube cross-sectional shapes.We work with linear, ideal, pressureless magnetohydrodynamics. Axially standing kink motions are examined as an initial value problem for transversely structured equilibria involving two identical, field-aligned, density-enhanced tubes with elliptic cross-sections (elliptic tubes). Continuously nonuniform layers are implemented around both tube boundaries. We numerically follow the system response to external velocity drivers, largely focusing on the quasi-mode stage of internal flows to derive the pertinent periods and damping times. The periods and damping times we derive for two-circular-tube setups justify available modal results found with the T-matrix approach. Regardless of cross-sectional shapes, our nonuniform layers feature the development of small-scale shears and energy accumulation around Alfven resonances, indicative of resonant absorption and phase-mixing. As with two-circular-tube systems, our configurational symmetries make it still possible to classify lower-order kink motions by the polarization and symmetric properties of the internal flows; hence such mode labels as $S_x$ and $A_x$. However, the periods and damping times for two-elliptic-tube setups further depend on cross-sectional aspect ratios, with $A_x$ motions occasionally damped less rapidly than $S_x$ motions. We find uncertainties up to $\sim 20\%$ ($\sim 50\%$) for the axial Alfven time (the inhomogeneity lengthscale) if the periods (damping times) computed for two-elliptic-tube setups are seismologically inverted with canonical theories for isolated circular tubes.

astro-ph.SR↗

arXiv2023

Modelling of transverse oscillations driven by p-modes in short coronal loops

Recent observations have revealed two types of decayless transverse oscillations in short coronalloops: one with short periods scaling with loop lengths, and the other with longer periods that exhibit a peak at around 5 min in the period distribution. To understand such a difference in period, we work in the framework of ideal MHD and model a short coronal loop embedded in an atmosphere with density stratification from the chromosphere to the corona. An inclined p-mode-like driver with a period of 5 min is launched at one loop footpoint. It is discovered that two types of decayless transverse oscillations can be excited in the loop. We interpret the 5 min periodicity as being directly driven by the footpoint driver, while the others, with periods of several tens of seconds, are regarded as kink eigenmodes of different harmonics. Therefore, our simulation shows that both types of decayless oscillations found in observations can be excited by p-modes in one short coronal loop. This study extends our understanding of ubiquitous decayless transverse oscillations in the corona. Furthermore, it suggests that p-modes could be an important energy source for coronal heating by driving decayless transverse oscillations.

astro-ph.SR↗

arXiv2023

Divert More Attention to Vision-Language Object Tracking

Multimodal vision-language (VL) learning has noticeably pushed the tendency toward generic intelligence owing to emerging large foundation models. However, tracking, as a fundamental vision problem, surprisingly enjoys less bonus from recent flourishing VL learning. We argue that the reasons are two-fold: the lack of large-scale vision-language annotated videos and ineffective vision-language interaction learning of current works. These nuisances motivate us to design more effective vision-language representation for tracking, meanwhile constructing a large database with language annotation for model learning. Particularly, in this paper, we first propose a general attribute annotation strategy to decorate videos in six popular tracking benchmarks, which contributes a large-scale vision-language tracking database with more than 23,000 videos. We then introduce a novel framework to improve tracking by learning a unified-adaptive VL representation, where the cores are the proposed asymmetric architecture search and modality mixer (ModaMixer). To further improve VL representation, we introduce a contrastive loss to align different modalities. To thoroughly evidence the effectiveness of our method, we integrate the proposed framework on three tracking methods with different designs, i.e., the CNN-based SiamCAR, the Transformer-based OSTrack, and the hybrid structure TransT. The experiments demonstrate that our framework can significantly improve all baselines on six benchmarks. Besides empirical results, we theoretically analyze our approach to show its rationality. By revealing the potential of VL representation, we expect the community to divert more attention to VL tracking and hope to open more possibilities for future tracking with diversified multimodal messages.

cs.CV↗