42 accepted papers
Object navigation for mobile robots typically assumes that targets are visible and paths are unobstructed. However, real-world scenarios often involve occluded targets like objects hidden behind doors or inside containers. Such scenarios require interactive navigation and manipulation by mobile mani…
The biomimetic research of vertebrates is challenging in both mechanism design and control methods. Motivated by natural acrobatics exhibited by cats and humans, this paper presents a generic multi-joint continuous spinal system and a learning-based algorithm for agile and accurate control. The spin…
This paper proposes AutoScape, a long-horizon driving scene generation framework. At its core is a novel RGB-D diffusion model that iteratively generates sparse, geometrically consistent keyframes, serving as reliable anchors for the scene's appearance and geometry. To maintain long-range geometric…
Visual localization, the task of determining the position and orientation of a camera, typically involves three core components: offline construction of a keyframe database, efficient online keyframes retrieval, and robust local feature matching. However, significant challenges arise when there are…
Existing progress in object keypoint estimation primarily benefits from the conventional supervised learning paradigm based on numerous data labeled with pre-defined keypoints. However, these well-trained models can hardly detect the undefined new keypoints in test time, which largely hinders their…
Aerial manipulation provides an effective alternative to human labor in high-risk outdoor situations. Complex and variable environments demand the system to respond quickly with minimal latency to external disturbances. To address this challenge, we propose a learning-based variable whole-body model
Continuum robots, inspired by biological structures such as spines and tails, have attracted significant attention due to their flexibility and ability to perform complex tasks in confined and dynamic environments. However, traditional flexible continuum robots often encounter challenges such as non
Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However objects encountered on the road exhibit a long-tailed distribution with rare or unseen categories posing challenges to a deployed perception model. This necessitates an expensive process of…
Active recognition which allows intelligent agents to explore observations for better recognition performance serves as a prerequisite for various embodied AI tasks such as grasping navigation and room arrangements. Given the evolving environment and the multitude of object classes it is impractical…
Active recognition enables robots to intelligently explore novel observations thereby acquiring more information while circumventing undesired viewing conditions. Recent approaches favor learning policies from simulated or collected data wherein appropriate actions are more frequently selected when…
Large language models (LLMs) have attracted increasing attention due to its prominent performance on various tasks. Recent works seek to leverage LLMs on knowledge-based visual question answering (VQA) tasks which require common sense knowledge to answer the question about an image, since LLMs have…
Aerial manipulation has received increasing research interest with wide applications of drones. To perform specific tasks, robotic arms with various mechanical structures will be mounted on the drone. It results in sudden disturbances to the aerial manipulator when switching the robotic arm or inter…
In real-world scenarios, typical visual recognition systems could fail under two major causes, i.e., the misclassification between known classes and the excusable misbehavior on unknown-class images. To tackle these deficiencies, flexible visual recognition should dynamically predict multiple classe…
Urban mobility analysis has been extensively studied in the past decade using a vast amount of GPS trajectory data, which reveals hidden patterns in movement and human activity within urban landscapes. Despite its significant value, the availability of such datasets often faces limitations due to pr…
Knowledge-based visual question answering (VQA) requires external knowledge to answer the question about an image. Early methods explicitly retrieve knowledge from external knowledge bases, which often introduce noisy information. Recently large language models like GPT-3 have shown encouraging perf…
"The subpopulation shifting challenge, known as some subpopulations of a category that are not seen during training, severely limits the classification performance of the state-of-the-art convolutional neural networks. Thus, to mitigate this practical issue, we explore incremental subpopulation lear…
Depth information is considered valuable as it describes geometric structures, which benefits various robotic tasks. However, the depth acquired by RGB-D sensors still suffers from two deficiencies, i.e., incompletion and noises. Previous methods complete depth by exploring hand-tuned models or rais…
Animals can use the maneuver of a flipping body and flapping wings to reduce the normal rebound force of impact during landing, decreasing the adsorption force required by the contact point. This capability aids aerial vehicles with landing not only on vertical surfaces, but also on inclined surface
Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have achieved impressive results by using large amounts of labeled train…
Intelligent agents with visual sensors are allowed to actively explore their observations for better recognition performance. This task is referred to as Active Recognition (AR). Currently, most methods toward AR are implemented under a fixed-category setting, which constrains their applicability in…
Many emerging applications of intelligent robots need to explore and understand new environments, where it is desirable to detect objects of novel categories on the fly with minimum online efforts. This is an object detection on demand (ODOD) task. It is challenging, because it is impossible to anno…
Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant---application-relevant categories can be picked and merged…
Person Re-IDentification (P-RID), as an instance-level recognition problem, still remains challenging in computer vision community. Many P-RID works aim to learn faithful and discriminative features/metrics from offline training data and directly use them for the unseen online testing data. However,…
There are two main challenges in Visual Question Answering (VQA). The first one is that each model obtains its strengths and shortcomings when applied to several questions; what is more, the "ceiling effect" for specific questions is difficult to overcome with simple consecutive training. The second…
Assessing action quality from videos has attracted growing attention in recent years. Most existing approaches usually tackle this problem based on regression algorithms, which ignore the intrinsic ambiguity in the score labels caused by multiple judges or their subjective appraisals. To address thi…
Human pose estimation (HPE) is inherently a homogeneous multi-task learning problem, with the localization of each body part as a different task. Recent HPE approaches universally learn a shared representation for all parts, from which their locations are linearly regressed. However, our statistical…
Learning distances that operate directly on multi-dimensional sequences is challenging because such distances are structural by nature and the vectors in sequences are not independent. Generally, distances for sequences heavily depend on the ground metric between the vectors in sequences. We propose…
Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detection performance. While hierarchical structure modeling methods have been proposed t…
Supervised dimensionality reduction for sequence data projects the observations in sequences onto a low-dimensional subspace to better separate different sequence classes. It is typically more challenging than conventional dimensionality reduction for static data, because measuring the separability…
Recognizing the attributes of objects and their parts is central to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usual…
Single image rain removal is a typical inverse problem in computer vision. The deep learning technique has been verified to be effective for this task and achieved state-of-the-art performance. However, previous deep learning methods need to pre-collect a large set of image pairs with/without synthe…
Visual Query Answering (VQA) is of great significance in offering people convenience: one can raise a question for details of objects, or high-level understanding about the scene, over an image. This paper proposes a novel method to address the VQA problem. In contrast to prior works, our method th…
Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each other. However, the relationships between the tasks are com…
Compositional models represent patterns with hierarchies of meaningful parts and subparts. Their ability to characterize high-order relationships among body parts helps resolve low-level ambiguities in human pose estimation (HPE). However, prior compositional models make unrealistic assumptions on s…
Multi-shot person re-identification (MsP-RID) utilizes multiple images from the same person to facilitate identification. Considering the fact that motion information may not be discriminative nor reliable enough for MsP-RID, this paper is focused on handling the large variations in the visual appea…
This paper proposes a segment-free method for geometric rectification of a distorted document image captured by a hand-held camera. The method can recover the 3D page shape by exploiting the intrinsic vector fields of the image. Based on the assumption that the curled page shape is a general cylindr…
Generative adversarial networks (GANs) are powerful tools for learning generative models. In practice, the training may suffer from lack of convergence. GANs are commonly viewed as a two-player zero-sum game between two neural networks. Here, we leverage this game theoretic view to study the converg…
Low-dimensional discriminative representations enhance machine learning methods in both performance and complexity, motivating supervised dimensionality reduction (DR) that transforms high-dimensional data to a discriminative subspace. Most DR methods require data to be i.i.d., however, in some doma…
Many existing person re-identification (PRID) methods typically attempt to train a faithful global metric offline to cover the enormous visual appearance variations, so as to directly use it online on various probes for identity matching. However, their need for a huge set of positive training pairs…
Compositional models represent visual patterns as hierarchies of meaningful and reusable parts. They are attractive to vision modeling due to their ability to decompose complex patterns into simpler ones and resolve the low-level ambiguities in high-level image interpretations. However, current comp…
It is a challenging problem to accurately estimate gazes from low-resolution eye images that do not provide fine and detailed features for eyes. Existing methods attempt to establish the mapping between the visual appearance space to the gaze space. Different from the direct regression approach, the…
Many discriminant analysis methods such as LDA and HLDA actually maximize the average pairwise distances between classes, which often causes the class separation problem. Max-min distance analysis (MMDA) addresses this problem by maximizing the minimum pairwise distance in the latent subspace, but i…