26 accepted papers
Federated Graph Learning enables multiple clients to collaboratively train graph models while protecting local private data. However, most studies have assumed that all clients contribute data voluntarily and actively. Without reasonable incentives, clients are often reluctant to contribute personal
Bundle Adjustment (BA) aims to estimate the camera poses and build maps utilizing the nonlinear optimization algorithm. The update step of the optimization is obtained by solving a linear system, which is the bottleneck of the BA efficiency. Many works perform bundle adjustment in a distributed mann
The rapid development of the Internet of Things (IoT) has resulted in an increasing volume of data, much of which contains sensitive private information. Federated Learning (FL) allows clients to train models without sharing raw data, showing significant potential for privacy protection. However, de…
The Active Binocular Vision System (ABVS), resembling the human eye, demonstrates potential for improving visual perception in robotic systems, especially in dynamic and complex environments. In this letter, we present an optimized design of a three degree-of-freedom (DoF) Active Monocular Vision Sy
Panoptic segmentation is a challenging perception task, which can help robots to comprehensively perceive the surrounding environment. In the task, we notice that semantic, instance, and panoptic have rich relations, however, which are rarely explored. In this work, we propose a novel panoptic, inst…
With the increasing demands for perception accuracy in autonomous driving, there is a growing focus on fine-grained 3D semantic occupancy prediction. Effectively representing detailed three-dimensional scenes has become a significant challenge in the development of this task. In this paper, we prese…
Perspective-n-Point (PnP) problem aims to estimate pose from known 3D map points and their projections. Efficient PnP (EPnP), one of the classical PnP solvers, represents camera pose with control points, which are easier to estimate utilizing the least square (LS) formulation. However, the geometry
We propose a vision-based method to achieve Pixel-Level precision saccadic movements in an active binocular vision system (ABVS). Traditional methods for precise saccadic motion rely heavily on extensive training or accurate kinematic models. However, extensive pre-training reduces the flexibility o
Accurate localization for intelligent robots remains a significant challenge, and self-supervised visual-inertial odometry (VIO) has emerged as a promising solution. However, existing self-supervised VIO works consider inertial information as the ordinary data input, losing its ability to recover ab
The weakly-supervised audio-visual video parsing (AVVP) task aims to parse duration and categories of each snippet when only the video-level event labels are provided. Most methods either leverage attention mechanisms to explore cross-modal and cross-video event semantics or alleviate label noise to…
In this paper, we propose a fast extrinsic calibration method for fusing multiple inertial measurement units (MIMU) to improve visual-inertial odometry (VIO) localization accuracy. Currently, data fusion algorithms for MIMU highly depend on the number of inertial sensors. Based on the assumption tha…
Unsupervised domain adaptation (UDA) is proposed to better adapt the network trained on labeled synthetic data to unlabeled real-world data for addressing the annotation cost. However, most of these methods pay more attention to domain distributions in input and output stages while ignoring the impo…
Node classification is the task of predicting the labels of unlabeled nodes in a graph. State-of-the-art methods based on graph neural networks achieve excellent performance when all labels are available during training. But in real-life, models are of ten applied on data with new classes, which…
Depth estimation and semantic edge detection are two key tasks in computer vision, which have made great progress. To date, how to associatively predict the depth and the semantic edge is rarely explored. In this work, we first propose a flexible two-branch framework that can make the two tasks take…
We propose a vision-based approach to calibrate kinematic structure of low degree-of-freedom (DoF) articulated systems. Standard hand-eye calibration yields excellent eye-to-hand relations by explicitly estimating end-effector mounted camera poses from the Perspective-n-Point (PnP) problem of a sing
Recovering depth information from a single image is a long-standing challenge, and self-supervised depth estimation methods have gradually attracted attention due to not relying on high-cost ground truth. Constructing an accurate photometric loss based on photometric consistency is crucial for these…
Learning to distinguish independent moving objects from the observed optical flow with a moving camera remains challenging. In this work, we first present a novel camera pose compensation (CPC) scheme. With the help of ingenious geometric analysis, it breaks the observed optical flow into patterns t…
We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation. Inspired by the human scene perception process, we design a novel coupled feature selection module, named CFSM, that adaptiv…
Weakly supervised localization aims at finding target object regions using only image-level supervision. However, localization maps extracted from classification networks are often not accurate due to the lack of fine pixel-level supervision. In this paper, we propose to leverage pixel-level similar…
Neural networks have recently achieved impressive success in semantic and instance segmentation on 2D images. However, their capabilities have not been fully explored to address semantic instance segmentation on unstructured 3D point cloud data. Digging into the regional feature representation to bo…
Recent CNN-based optical flow approaches have a separated structure of feature extraction and flow estimation. The core task of optical flow is finding the corresponding points while rich representation is just the key part of such matching problems. However, the prior work usually pays more attenti…
Despite the great success achieved by supervised fully convolutional models in semantic segmentation, training the models requires a large amount of labor-intensive work to generate pixel-level annotations. Recent works exploit synthetic data to train the model for semantic segmentation, but the dom…
Semantic segmentation of 3D unstructured point clouds remains an open research problem. Recent works predict semantic labels of 3D points by virtue of neural networks but take limited context knowledge into consideration. In this paper, a novel end-to-end approach for unstructured point cloud semant…
In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly selecting the class-specific feature maps of the last convo…
Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We propose to generate Self-produced Guidance (SPG) masks which sep…