Related papers: TransVPR: Transformer-based place recognition with…
While convolutional neural networks have shown a tremendous impact on various computer vision tasks, they generally demonstrate limitations in explicitly modeling long-range dependencies due to the intrinsic locality of the convolution…
Transformers have demonstrated great potential in computer vision tasks. To avoid dense computations of self-attentions in high-resolution visual data, some recent Transformer models adopt a hierarchical design, where self-attentions are…
Traditional visual place recognition (VPR), usually using standard cameras, is easy to fail due to glare or high-speed motion. By contrast, event cameras have the advantages of low latency, high temporal resolution, and high dynamic range,…
Visual Place Recognition (VPR) in long-term deployment requires reasoning beyond pixel similarity: systems must make transparent, interpretable decisions that remain robust under lighting, weather and seasonal change. We present Text2Graph…
Place recognition is one of the most fundamental topics in computer vision and robotics communities, where the task is to accurately and efficiently recognize the location of a given query image. Despite years of wisdom accumulated in this…
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism. Thanks to its strong representation capabilities, researchers are looking at ways to…
Weakly supervised object localization is a challenging task which aims to localize objects with coarse annotations such as image categories. Existing deep network approaches are mainly based on class activation map, which focuses on…
We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…
Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place recognition identifies a place using query sensor data and a…
Many image understanding tasks involve identifying what is present and where it appears. However, tasks that address where, such as object discovery, detection, and segmentation, are often considerably more complex than image…
This paper is on video recognition using Transformers. Very recent attempts in this area have demonstrated promising results in terms of recognition accuracy, yet they have been also shown to induce, in many cases, significant computational…
Vision Transformer (ViT) self-attention mechanism is characterized by feature collapse in deeper layers, resulting in the vanishing of low-level visual features. However, such features can be helpful to accurately represent and identify…
Video copy localization aims to precisely localize all the copied segments within a pair of untrimmed videos in video retrieval applications. Previous methods typically start from frame-to-frame similarity matrix generated by cosine…
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficiently capture large…
Visual Place Recognition (VPR) is a crucial component of 6-DoF localization, visual SLAM and structure-from-motion pipelines, tasked to generate an initial list of place match hypotheses by matching global place descriptors. However,…
Template-based discriminative trackers are currently the dominant tracking methods due to their robustness and accuracy, and the Siamese-network-based methods that depend on cross-correlation operation between features extracted from…
In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known places. This task requires robust, scalable, and efficient…
Place recognition is an important capability for autonomously navigating vehicles operating in complex environments and under changing conditions. It is a key component for tasks such as loop closing in SLAM or global localization. In this…
Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely…
Geo-localization from a single image at planet scale (essentially an advanced or extreme version of the kidnapped robot problem) is a fundamental and challenging task in applications such as navigation, autonomous driving and disaster…