Related papers: TransCenter: Transformers with Dense Representatio…
Event cameras produce asynchronous, high-dynamic-range streams well suited for detecting small, fast-moving drones, yet most event-based detectors convert the sparse event stream into dense tensors, discarding the representational…
Object Re-identification (Re-ID) aims to identify specific objects across different times and scenes, which is a widely researched task in computer vision. For a prolonged period, this field has been predominantly driven by deep learning…
Object detection has recently seen an interesting trend in terms of the most innovative research work, this task being of particular importance in the field of remote sensing, given the consistency of these images in terms of geographical…
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT)…
As demand for robotics manipulation application increases, accurate vision-based 6D pose estimation becomes essential for autonomous operations. Convolutional Neural Networks (CNNs) based approaches for pose estimation have been previously…
The Transformer is a highly successful deep learning model that has revolutionised the world of artificial neural networks, first in natural language processing and later in computer vision. This model is based on the attention mechanism…
Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality…
Sensor fusion is an essential topic in many perception systems, such as autonomous driving and robotics. Transformers-based detection head and CNN-based feature encoder to extract features from raw sensor-data has emerged as one of the best…
Despite radar's popularity in the automotive industry, for fusion-based 3D object detection, most existing works focus on LiDAR and camera fusion. In this paper, we propose TransCAR, a Transformer-based Camera-And-Radar fusion solution for…
As a video task, Multiple Object Tracking (MOT) is expected to capture temporal information of targets effectively. Unfortunately, most existing methods only explicitly exploit the object features between adjacent frames, while lacking the…
Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions. Due to the presence of two…
Transformer-based object detectors often struggle with occlusions, fine-grained localization, and computational inefficiency caused by fixed queries and dense attention. We propose DAMM, Dual-stream Attention with Multi-Modal queries, a…
Multiple Object Tracking (MOT) is a core capability in modern computer vision, essential to autonomous driving, surveillance, sports analytics, robotics, and biomedical imaging. Persistent identity assignment across frames remains…
We present Laneformer, a conceptually simple yet powerful transformer-based architecture tailored for lane detection that is a long-standing research topic for visual perception in autonomous driving. The dominant paradigms rely on purely…
We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…
The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative…
The objective of this work is to learn an object-centric video representation, with the aim of improving transferability to novel tasks, i.e., tasks different from the pre-training task of action classification. To this end, we introduce a…
The past year has witnessed the rapid development of applying the Transformer module to vision problems. While some researchers have demonstrated that Transformer-based models enjoy a favorable ability of fitting data, there are still…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between…
Pretrained models have demonstrated impressive success in many modalities such as language and vision. Recent works facilitate the pretraining paradigm in imaging research. Transients are a novel modality, which are captured for an object…