Related papers: CPR++: Object Localization via Single Coarse Point…

In recent years there has been significant improvement in the capability of Visual Place Recognition (VPR) methods, building on the success of both hand-crafted and learnt visual features, temporal filtering and usage of semantic scene…

Important high-level vision tasks such as human-object interaction, image captioning and robotic manipulation require rich semantic descriptions of objects at part level. Based upon previous work on part localization, in this paper, we…

Tiny objects, with their limited spatial resolution, often resemble point-like distributions. As a result, bounding box prediction using point-level supervision emerges as a natural and cost-effective alternative to traditional box-level…

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances. Concretely, the well-known challenge of low overlaps between the priors and object…

Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exacerbated…

For best performance, today's semantic segmentation methods use large and carefully labeled datasets, requiring expensive annotation budgets. In this work, we show that coarse annotation is a low-cost but highly effective alternative for…

One recent promising approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques using methods such as SRAL and multi-process fusion. These approaches come…

Point cloud registration (PCR) is crucial for many downstream tasks, such as simultaneous localization and mapping (SLAM) and object tracking. This makes detecting and quantifying registration misalignment, i.e., PCR quality validation, an…

Place recognition and loop closure detection are challenging for long-term visual navigation tasks. SeqSLAM is considered to be one of the most successful approaches to achieving long-term localization under varying environmental conditions…

Large Language Models (LLMs) have made significant strides in generating human-like responses, largely due to preference alignment techniques. However, these methods often assume unbiased human feedback, which is rarely the case in…

Human keypoint detection from a single image is very challenging due to occlusion, blur, illumination and scale variance of person instances. In this paper, we find that context information plays an important role in addressing these…

Efficient LiDAR Place Recognition (LPR) compresses dense pointwise features into compact global descriptors. While first-order aggregators such as GeM and NetVLAD are widely used, they overlook inter-feature correlations that second-order…

Conformal Prediction (CP) is a distribution-free method for constructing prediction sets with marginal finite-sample coverage guarantees, making it a suitable framework for reliable uncertainty quantification in safety-critical object…

Visual place recognition (VPR) enables autonomous systems to localize themselves within an environment using image information. While Convolution Neural Networks (CNNs) currently dominate state-of-the-art VPR performance, their high…

Recent studies show that vision models pre-trained in generic visual learning tasks with large-scale data can provide useful feature representations for a wide range of visual perception problems. However, few attempts have been made to…

In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately. Recently, point-guided approach is introduced to anchor-based method. However, we observe points predicted by this way…

Although recent advances in regional Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their response time is still slow for real-time performance.…

We propose a multi-precision extension of the Quadratic Regularization (R2) algorithm that enables it to take advantage of low-precision computations, and by extension to decrease energy consumption during the solve. The lower the precision…

This paper presents a new annotation method called Sparse Annotation (SA) for crowd counting, which reduces human labeling efforts by sparsely labeling individuals in an image. We argue that sparse labeling can reduce the redundancy of full…

Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for…