Related papers: CPM R-CNN: Calibrating Point-guided Misalignment i…
We identify and formalize an underexplored phenomenon in deep learning optimization: directional alignment and loss convergence can be decoupled. An optimizer can exhibit near-perfect directional consistency (cc_t -> 1, measured via…
Collaborative perception enhances sensing in multirobot and vehicular networks by fusing information from multiple agents, improving perception accuracy and sensing range. However, mobility and non-rigid sensor mounts introduce extrinsic…
Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position…
Generic object detection is one of the most fundamental problems in computer vision, yet it is difficult to provide all the bounding-box-level annotations aiming at large-scale object detection for thousands of categories. In this paper, we…
Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures…
Large imbalance often exists between the foreground points (i.e., objects) and the background points in outdoor LiDAR point clouds. It hinders cutting-edge detectors from focusing on informative areas to produce accurate 3D object detection…
360{\deg} images are usually represented in either equirectangular projection (ERP) or multiple perspective projections. Different from the flat 2D images, the detection task is challenging for 360{\deg} images due to the distortion of ERP…
CNN-based object detection methods have achieved significant progress in recent years. The classic structures of CNNs produce pyramid-like feature maps due to the pooling or other re-scale operations. The feature maps in different levels of…
Ship detection in aerial images remains an active yet challenging task due to arbitrary object orientation and complex background from a bird's-eye perspective. Most of the existing methods rely on angular prediction or predefined anchor…
Changepoint detection is an important problem with applications across many application domains. There are many different types of changes that one may wish to detect, and a wide-range of algorithms and software for detecting them. However…
Object detection has long been dominated by traditional coordinate regression-based models, such as YOLO, DETR, and Grounding DINO. Although recent efforts have attempted to leverage MLLMs to tackle this task, they face challenges like low…
While object detection is a common problem in computer vision, it is even more challenging when dealing with aerial satellite images. The variety in object scales and orientations can make them difficult to identify. In addition, there can…
Recent researches attempt to improve the detection performance by adopting the idea of cascade for single-stage detectors. In this paper, we analyze and discover that inconsistency is the major factor limiting the performance. The refined…
Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this…
Modern software-defined networks, such as Open Radio Access Network (O-RAN) systems, rely on artificial intelligence (AI)-powered applications running on controllers interfaced with the radio access network. To ensure that these AI…
One of the main challenges in LiDAR-based 3D object detection is that the sensors often fail to capture the complete spatial information about the objects due to long distance and occlusion. Two-stage detectors with point cloud completion…
In recent years, much progress has been made in LiDAR-based 3D object detection mainly due to advances in detector architecture designs and availability of large-scale LiDAR datasets. Existing 3D object detectors tend to perform well on the…
The rapid advancement of large language models has raised significant concerns regarding their potential misuse by malicious actors. As a result, developing effective detectors to mitigate these risks has become a critical priority.…
This paper presents a novel dataset for traffic accidents analysis. Our goal is to resolve the lack of public data for research about automatic spatio-temporal annotations for traffic safety in the roads. Through the analysis of the…
Anchor-based detectors have been continuously developed for object detection. However, the individual anchor box makes it difficult to predict the boundary's offset accurately. Instead of taking each bounding box as a closed individual, we…