34 accepted papers
Due to the ability to provide point clouds and Doppler velocity, as well as the adaptability in harsh weather conditions, 4D Radar has emerged as a new option for Simultaneous Localization and Mapping (SLAM). However, there is limited research on both robustness and computational efficiency, which a
Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hinders continuous knowledge acquisition. Effective knowledge injection thus becomes critical, involving…
Modality alignment is critical for vision-language models (VLMs) to effectively integrate information across modalities. However, existing methods extract hierarchical features from text while representing each image with a single feature, leading to asymmetric and suboptimal alignment. To address t…
In vision–language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations. This issue becomes particularly severe in dense prediction tasks such as spatial–temporal video grounding (STVG). Prior approaches typically focus on enhancing visual–text…
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI agents is the lack of sufficient trajectory data across various o
Video understanding has made remarkable progress in recent years, largely driven by advances in deep models and the availability of large-scale annotated datasets. However, the robustness of these models to domain shifts encountered in real-world video applications remains a critical yet underexplor…
Large Multimodal Models (LMMs) store vast amounts of pretrained knowledge but struggle to remain aligned with real-world updates, making it difficult to avoid capability degradation when acquiring evolving knowledge. Furthermore, most current work focuses on exploring static textual knowledge inject…
Open-vocabulary learning requires modeling the data distribution in open environments, which consists of both seen-class and unseen-class data. Existing methods estimate the distribution in open environments using seen-class data, where the absence of unseen classes makes the estimation error inhe…
Point cloud semantic segmentation is crucial in various applications such as autonomous driving, robotics, and virtual reality, aiming to assign labels to each point in a cloud to reflect spatial relationships and boundaries. While previous methods primarily focus on geometric features, they often o
Multimodal agents, which integrate a controller (e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extens…
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining from scratch. However, existing benchmarks for multimodal knowl…
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-moda…
Due to the complementary properties between sensors, multi-sensor fusion can effectively promote accuracy and tackle the challenging scenes in simultaneous localization and mapping (SLAM) tasks. To this end, we propose a novel LiDAR-camera fused method for odometry and mapping using dense colored po
Loop Closure Detection (LCD) is an essential component of Simultaneous Localization and Mapping (SLAM), helping to correct drift errors, facilitate map merging, or both by identifying previously observed scenes. Despite its importance, traditional LCD algorithms based on single sensor such as camera…
Utilizing large language models (LLMs) to compose off-the-shelf visual tools represents a promising avenue of research for developing robust visual assistants capable of addressing diverse visual tasks. However these methods often overlook the potential for continual learning typically by freezing t…
In recent years, significant progress has been made in the field of underwater image enhancement (UIE). However, its practical utility for high-level vision tasks, such as underwater object detection (UOD) in Autonomous Underwater Vehicles (AUVs), remains relatively unexplored. It may be attributed…
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spon…
Extrinsic calibration is an essential prerequisite for the applications of camera-LiDAR fusion. Existing methods either suffer from the complex offline setting of man-made targets or tend to produce suboptimal and unrobust results. In this paper, we propose an online two-stage calibration method tha…
In indoor scenes, pose estimation drift in SLAM systems is challenging to mitigate due to factors like low texture and texture repetition. Several studies utilize Manhattan structural information to achieve low-drift rotation estimation consequently reducing the cumulative error. However, the applic
"We explore how reconciling several foundation models (large language models and vision-language models) with a novel unified memory mechanism could tackle the challenging video understanding problem, especially capturing the long-term temporal relations in lengthy videos. In particular, the propose…
Continual learning aims to efficiently learn from a non-stationary stream of data while avoiding forgetting the knowledge of old data. In many practical applications, data complies with non-Euclidean geometry. As such, the commonly used Euclidean space cannot gracefully capture non-Euclidean geometr…
Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain s…
Underwater image enhancement (UIE) is vital for high-level vision-related underwater tasks. Although learning-based UIE methods have made remarkable achievements in recent years, it's still challenging for them to consistently deal with various underwater conditions, which could be caused by: 1) the…
Aerial-aquatic vehicles are capable to move in the two most dominant fluids, making them more promising for a wide range of applications. We propose a prototype with special designs for propulsion and thruster configuration to cope with the vast differences in the fluid properties of water and air.…
To solve optimization problems with nonlinear constrains, the recently developed Riemannian meta-optimization methods show promise, which train neural networks as an optimizer to perform optimization on Riemannian manifolds. A key challenge is the heavy computational and memory burdens, because com…
Learning in hyperbolic spaces has attracted growing attention recently, owing to their capabilities in capturing hierarchical structures of data. However, existing learning algorithms in the hyperbolic space tend to overfit when limited data is given. In this paper, we propose a hyperbolic feature a…
Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level understanding tasks, especially when labels are extremely limited. Thi…
"Current state-of-the-art 3D scene understanding methods are merely designed in a full-supervised way. However, in the limited reconstruction cases, only limited 3D scenes can be reconstructed and annotated. We are in need of a framework that can concurrently be applied to 3D point cloud semantic se…
Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds, which is inferior because tangent space is only a local appr…
Few-shot learning describes the challenging problem of recognizing samples from unseen classes given very few labeled examples. In many cases, few-shot learning is cast as learning an embedding space that assigns test samples to their corresponding class prototypes. Previous methods assume that data…
This work presents a general deep learning framework for large-scale point clouds understanding without voxelizations, called FG-Conv, which achieves an accurate and real-time understanding of point clouds. Through our novel design combining feature level correlation mining and deformable convolutio…
A principal way of addressing constrained optimization problems is to model them as problems on Riemannian manifolds. Recently, Riemannian meta-optimization provides a promising way for solving constrained optimization problems by learning optimizers on Riemannian manifolds in a data-driven fashion,…
With the booming development in aerospace technology, the video satellite which observes the live phenomena on the ground by video shooting has gradually emerged as a new Earth observation method. And remote sensing comes into a "dynamic" era with the demand for new processing techniques, especially…
Many tasks in computer vision and machine learning are modeled as optimization problems with constraints in the form of Symmetric Positive Definite (SPD) matrices. Solving such optimization problems is challenging due to the non-linearity of the SPD manifold, making optimization with SPD constraints…