Related papers: Dense Object Detection Based on De-homogenized Que…

RT-DETR is the first real-time end-to-end transformer-based object detector. Its efficiency comes from the framework design and the Hungarian matching. However, compared to dense supervision detectors like the YOLO series, the Hungarian…

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained…

The tasks of object detection and trajectory forecasting play a crucial role in understanding the scene for autonomous driving. These tasks are typically executed in a cascading manner, making them prone to compounding errors. Furthermore,…

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and…

Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on…

This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…

Multi-object tracking from LiDAR point clouds presents unique challenges due to the sparse and irregular nature of the data, compounded by the need for temporal coherence across frames. Traditional tracking systems often rely on…

Recently, detection transformers (DETRs) have gradually taken a dominant position in 2D detection thanks to their elegant framework. However, DETR-based detectors for 3D point clouds are still difficult to achieve satisfactory performance.…

Due to object detection's close relationship with video analysis and image understanding, it has attracted much research attention in recent years. Traditional object detection methods are built on handcrafted features and shallow trainable…

The ambiguous appearance, tiny scale, and fine-grained classes of objects in remote sensing imagery inevitably lead to the noisy annotations in category labels of detection dataset. However, the effects and treatments of the label noises…

End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong detection performance, these methods suffer from relatively low…

Visual object tracking task is constantly gaining importance in several fields of application as traffic monitoring, robotics, and surveillance, to name a few. Dealing with changes in the appearance of the tracked object is paramount to…

Detection Transformers (DETR) have recently set new benchmarks in object detection. However, their performance in detecting rotated objects lags behind established oriented object detectors. Our analysis identifies a key observation: the…

Detection Transformers (DETR) are increasingly adopted in autonomous vehicle (AV) perception systems due to their superior accuracy over convolutional networks. However, concurrently executing multiple DETR tasks presents significant…

3D multiple object tracking (MOT) plays a crucial role in autonomous driving perception. Recent end-to-end query-based trackers simultaneously detect and track objects, which have shown promising potential for the 3D MOT task. However,…

Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their performance through self-supervised pre-training of…

Visual anomaly detection, an important problem in computer vision, is usually formulated as a one-class classification and segmentation task. The student-teacher (S-T) framework has proved to be effective in solving this challenge. However,…

We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D…

In radar-camera 3D object detection, the radar point clouds are sparse and noisy, which causes difficulties in fusing camera and radar modalities. To solve this, we introduce a novel query-based detection method named Radar-Camera…

Most modern multiple object tracking (MOT) systems follow the tracking-by-detection paradigm, consisting of a detector followed by a method for associating detections into tracks. There is a long history in tracking of combining motion and…