58 accepted papers
The research frontier in human pose prediction (HPP) is advancing toward continual test-time adaptation (TTA), where models must self-adapt to dynamic test distributions. To date, the homeostatic continual TTA remains the sole viable solution, which isolates the model parameters and update domain-se
Recent reinforcement-learning frameworks for visual perception policy usually incorporate intermediate reasoning chains expressed in natural language. Empirical observations indicate that such purely linguistic intermediate reasoning often reduces performance on perception tasks. We argue that the c…
Multi-modal fusion has emerged as a promising paradigm for accurate 3D object detection. However, performance degrades substantially when deployed in target domains different from training. In this work, focusing on dual-branch proposal-level detectors, we identify two factors that limit robust cros
Accurate short-term precipitation forecasting is critical for weather-sensitive decision-making in agriculture, transportation, and disaster response. Existing deep learning approaches often struggle to balance global structural consistency with local detail preservation, especially under complex me
Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods for generating such captions often rely on distilling the captions from pretrained LMMs, constructing them from publicly available internet images, or even generating the
Incremental 3D object perception is a critical step toward embodied intelligence in dynamic indoor environments. However, existing incremental 3D detection methods rely on extensive annotations of novel classes for satisfactory performance. To address this limitation, we propose FI3Det, a Few-shot I
Graph-based methods have proven to be effective in capturing relationships among points for 3D point cloud analysis. However, these methods often suffer from suboptimal graph structures, particularly due to sparse connections at boundary points and noisy connections in junction areas. To address the
Outdoor LiDAR generation has shown strong potential for autonomous driving and large-scale 3D perception. However, existing approaches remain computationally intensive and primarily static, lacking explicit modeling of temporal dynamics. This limitation weakens spatiotemporal coherence and reduces t…
3D hierarchical semantic segmentation (3DHS) is crucial for embodied intelligence that demands the coarse-to-fine grained and multi-hierarchy understanding of 3D scenes. 3DHS tasks can be addressed by multi-label learning, but facing two issues: I) learning multiple labels for each point with a shar…
This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A straightforward solution is to employ a pseudo-labeling strateg
Transformable wheel-legged robots can adjust their configuration according to terrain conditions, enabling effective operation in harsh environments. While existing controllers based on preset commands have successfully demonstrated the feasibility of reconfigurable mechanisms, they still struggle t…
Recent multimodal fusion methods, integrating images with LiDAR point clouds, have shown promise in scene flow estimation. However, the fusion of 4D millimeter wave radar and LiDAR remains unexplored. Unlike LiDAR, radar is cheaper, more robust in various weather conditions and can detect point-wise
Morphing quadrotors offer enhanced maneuverability and adaptability in confined spaces, while their structural variations pose challenges to trajectory planning and control. This paper presents a time-optimal trajectory planning and model predictive control framework for the morphing quadrotor. The …
Large vision-language models (LVLMs) excel at vision-language tasks but remain vulnerable to backdoor attacks. Most existing backdoor attacks on LVLMs force the model to generate predefined target patterns. However, these fixed-pattern attacks are easy to detect, as the model tends to memorize frequ…
This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection over multi-view reconstructed 3D models by leveraging the intr
MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo--solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However, trajectory-based memory suffers from brevity bias, gradually los
Due to the difficulty of obtaining ground-truth data for 4D radar scene flow estimation, previous methods typically rely on either self-supervised losses or cross-modal supervision using 3D LiDAR data, 2D images, and odometry. However, self-supervised approaches often yield suboptimal results due to…
Effective human-agent collaboration in physical environments requires understanding not only what to act upon, but also where the actionable elements are and how to interact with them. Existing approaches often operate at the object level or disjointedly handle fine-grained affordance reasoning, lac…
3D visual grounding (3DVG), which aims to correlate a natural language description with the target object within a 3D scene, is a significant yet challenging task. Despite recent advancements in this domain, existing approaches commonly encounter a shortage: a limited amount and diversity of text-3D…
Embodied agents based on large language models (LLMs) face significant challenges in collaborative tasks, requiring effective communication and reasonable division of labor to ensure efficient and correct task completion. Previous approaches with simple communication patterns carry erroneous or inco…
High maneuverability is essential to the autonomous operation of underwater robots. To achieve real-time maneuvering motion, the control strategy must take into account nonlinear hydrodynamic effects, which are extremely difficult to accurately capture during motion and therefore a balance must be s
In logistics applications, the vision-based technology for grasping target objects in the air is relatively mature. However, when operating across the air and water such as grasping marine products from the water, the visual information collected by the camera will be disturbed by ripples and bubble
Recently, with the development of Neural Radiance Fields and Gaussian Splatting, 3D reconstruction techniques have achieved remarkably high fidelity. However, the latent representations learnt by these methods are highly entangled and lack interpretability. In this paper, we propose a novel part-awa…
View-Guided Point Cloud Completion (VG-PCC) aims to reconstruct complete point clouds from partial inputs by referencing single-view images. While existing VG-PCC models perform well on in-class predictions, they exhibit significant performance drops when generalizing to unseen categories. We identi…
Recently, numerous multi-view clustering (MVC) and multi-view graph clustering (MVGC) methods have been proposed. Despite significant progress, they still face two issues: I) MVC and MVGC are often developed independently for multi-view and multi-graph data. They have redundancy but lack a unified m
Despite recent advances in feed-forward 3D Gaussian Splatting, generalizable 3D reconstruction remains challenging, particularly in multi-view correspondence modeling. Existing approaches face a fundamental trade-off: explicit methods achieve geometric precision but struggle with ambiguous regions,…
LiDAR-based 3D panoptic segmentation often struggles with the inherent sparsity of data from LiDAR sensors, which makes it challenging to accurately recognize distant or small objects. Recently, a few studies have sought to overcome this challenge by integrating LiDAR inputs with camera images, leve…
Human motion generation and editing are key components of computer vision. However, current approaches in this field tend to offer isolated solutions tailored to specific tasks, which can be inefficient and impractical for real-world applications. While some efforts have aimed to unify motion-relate…
The rapid development of image generation models has facilitated the widespread dissemination of generated images on social networks, creating favorable conditions for provably secure image steganography. However, existing methods face issues such as low quality of generated images and lack of sema…
Recently, multi-view learning (MVL) has garnered significant attention due to its ability to fuse discriminative information from multiple views. However, real-world multi-view datasets are often heterogeneous and imperfect, which usually causes MVL methods designed for specific combinations of view…
Recent provably secure linguistic steganography (PSLS) methods rely on mainstream autoregressive language models (ARMs) to address historically challenging tasks, that is, to disguise covert communication as ``innocuous'' natural language communication. However, due to the characteristic of sequen…
Active learning has emerged as a promising approach to reduce the substantial annotation burden in 3D object detection tasks, spurring several initiatives in outdoor environments. However, its application in indoor environments remains unexplored. Compared to outdoor 3D datasets, indoor datasets fac…
Current multi-modal hybrid robots with flight and wheeled modes have fallen into the dilemma that they can only avoid obstacles by re-taking off when encountering obstacles due to the poor performance of wheeled obstacle-crossing. To tackle this problem, this paper presents a novel multi-modal hybri…
Morphing quadrotors that can be potentially applied to confined spaces such as warehouses, tanks, and pipelines have flourished in recent years. Most work has focused on the mechanical feasibility of the morphing systems and high-level flight controller design, with limited discussions on low-level…
Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing a teacher model to generate pseudo-labels for unlabeled sam…
3D instance segmentation is a fundamental and critical task for enabling robots to operate effectively in unstructured 3D environments. In order to address the challenges posed by the high demand for large-scale annotated data and the limited availability of such data in the context of 3D instance s…
Segmenting affordance in 3D data is key for bridging perception and action in robots. Existing efforts mostly focus on the visual side and overlook the affordance knowledge from a semantic aspect. This oversight not only limits their generalization to unseen objects but more importantly hinders thei…
Due to the low motion efficiency and maneuver-ability of underwater robots with six degrees of freedom, it is challenging for them to respond quickly to the attitude requirements during underwater autonomous manipulation. This paper presents a novel autonomous underwater robot with fully vectored pr…
Learning from open-world noisy data, where both closed-set and open-set noise co-exist in the dataset, is a realistic but underexplored setting. Only recently, several efforts have been initialized to tackle this problem. However, these works assume the classes are balanced when dealing with open-wo…
"The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view rendered images, which then guide the editing of 3DGS model…
Existing fully-supervised point cloud segmentation methods suffer in the dynamic testing environment with emerging new classes. Few-shot point cloud segmentation algorithms address this problem by learning to adapt to new classes at the sacrifice of segmentation accuracy for the base classes, which…
In this work, we present GraspFlow, a refinement approach for generating context-specific grasps. We formulate the problem of grasp synthesis as a sampling problem: we seek to sample from a context-conditioned probability distribution of successful grasps. However, this target distribution is unknow…
In recent years, the classification accuracy of CNN (convolutional neural network) steganalyzers has rapidly improved. However, as general CNN classifiers will misclassify adversarial samples, CNN steganalyzers can hardly detect adversarial steganography, which combines adversarial samples and stega…
"Since Intersection-over-Union (IoU) based optimization maintains the consistency of the final IoU prediction metric and losses, it has been widely used in both regression and classification branches of single-stage 2D object detectors. Recently, several 3D object detection methods adopt IoU-based o…
Deep learning-based approaches have shown remarkable performance in the 3D object detection task. However, they suffer from a catastrophic performance drop on the originally trained classes when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenom…
"In this paper, we study the task of synthetic-to-real domain generalized semantic segmentation, which aims to learn a model that is robust to unseen real-world scenes using only synthetic data. The large domain shift between synthetic and real-world data, including the limited source environmental…
"Recent studies have highlighted the problem of noisy labels in large scale in-the-wild facial expressions datasets due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators. To solve the problem of noisy labels, we propose Soft…
Inspired by the advantages from natural birds' shape-morphing adapted flight performance, this work investigates how the bioinspired adaptative morph induced inertia variation affects the flight performance of a morphing quad-rotor. Extensive numerical and experimental evaluations on a custom-built
Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes after training. To mitigate these limitations, we propose a nov…
This paper presents our comparative study on how the flight performances of an in-flight morphing quad-rotor are affected by the morph induced inertia variation. A custom-built in-flight morphing quad-rotor was employed in numerical and experimental tests for the study and analysis. In these tests,…
In this paper, we investigate the consensus problem of multiple unmanned aerial vehicles (UAVs) in the presence of environmental constraints under a general communication topology containing a directed spanning tree. First, based on a position transformation function, we propose a novel dynamic refe…
Electronic Health Record (EHR) and healthcare claim data provide rich clinical information for time series analysis. In this work, we provide a different angle of solving healthcare multivariate time series classification by turning it into a computer vision problem. We propose a Convolutional Featu…
The performance of existing point cloud-based 3D object detection methods heavily relies on large-scale high-quality 3D annotations. However, such annotations are often tedious and expensive to collect. Semi-supervised learning is a good alternative to mitigate the data annotation issue, but has rem…
In this paper, a simple tracking control scheme is proposed for quadrotor systems with uncertain dynamics. It precludes the necessity for prohibitive analytic computation of the derivatives of the desired (virtual) attitude that is typically employed in controlling quadrotor systems. Moreover, this…
Inspired by the inchworm locomotion mechanism, this paper presents our recently developed self-deformable capsule-like robot. The robot has the actuated deformation capability that relies on a novel rigid elements-based morphing structure (REMS) and its soft actuation mechanisms. When the robot defo…
The paper presents the development of a novel deformable quad-rotor enabled aerial gripper. The mechanism of our deformable quad-rotor is based on simultaneous expansion or contraction of the quad-rotor body, which is generated by controlling a rigid elements based morphing structure (REMS). Such de…
Inspired by natural earthworm locomotion behavior and segmental muscle motion mechanism, this paper presents our recently developed compliant modular earthwormlike robot with the novel segmental muscle-mimetic design unit that is capable of efficiently mimicking earthworms' segmental muscle contract…
To improve the obstacle surmounting performance of the quad-rotor vehicle, this paper focuses on designing, kinematically and dynamically characterizing a novel deformable quad-rotor that is based on the scissor-like foldable structures. The foldable structure allows that the volume of the quad-roto…