Related papers: Siamese Keypoint Prediction Network for Visual Obj…
This paper presents a novel approach for image retrieval and pattern spotting in document image collections. The manual feature engineering is avoided by learning a similarity-based representation using a Siamese Neural Network trained on a…
Most Siamese network-based trackers perform the tracking process without model update, and cannot learn targetspecific variation adaptively. Moreover, Siamese-based trackers infer the new state of tracked objects by generating axis-aligned…
Augmented Reality (AR) applications often require robust real-time tracking of objects in the user's environment to correctly overlay virtual content. Recent advances in computer vision have produced highly accurate deep learning-based…
Tracking by detection is a common approach to solving the Multiple Object Tracking problem. In this paper we show how learning a deep similarity metric can improve three key aspects of pedestrian tracking on a multiple object tracking…
Classification-regression prediction networks have realized impressive success in several modern deep trackers. However, there is an inherent difference between classification and regression tasks, so they have diverse even opposite demands…
Thermal infrared (TIR) images typically lack detailed features and have low contrast, making it challenging for conventional feature extraction models to capture discriminative target characteristics. As a result, trackers are often…
Two-stage point-to-box network acts as a critical role in the recent popular 3D Siamese tracking paradigm, which first generates proposals and then predicts corresponding proposal-wise scores. However, such a network suffers from tedious…
Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…
Single Object Tracking in LiDAR point cloud is one of the most essential parts of environmental perception, in which small objects are inevitable in real-world scenarios and will bring a significant barrier to the accurate location.…
Long-term visual tracking has drawn increasing attention because it is much closer to practical applications than short-term tracking. Most top-ranked long-term trackers adopt the offline-trained Siamese architectures, thus, they cannot…
While recent years have witnessed remarkable progress in the feature representation of visual tracking, the problem of feature misalignment between the classification and regression tasks is largely overlooked. The approaches of feature…
Object detection and object tracking are usually treated as two separate processes. Significant progress has been made for object detection in 2D images using deep learning networks. The usual tracking-by-detection pipeline for object…
Recent approaches for 3D object detection have made tremendous progresses due to the development of deep learning. However, previous researches are mostly based on individual frames, leading to limited exploitation of information between…
Object detection is an essential step towards holistic scene understanding. Most existing object detection algorithms attend to certain object areas once and then predict the object locations. However, neuroscientists have revealed that…
In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder…
Discriminative correlation filters (DCF) and siamese networks have achieved promising performance on visual tracking tasks thanks to their superior computational efficiency and reliable similarity metric learning, respectively. However, how…
The objective of this paper is to address the localization problem using omnidirectional images captured by a catadioptric vision system mounted on the robot. For this purpose, we explore the potential of Siamese Neural Networks for…
This paper proposes an online visual multi-object tracking algorithm using a top-down Bayesian formulation that seamlessly integrates state estimation, track management, clutter rejection, occlusion and mis-detection handling into a single…
Event-based sensors, distinguished by their high temporal resolution of 1 $\mathrm{\mu}\text{s}$ and a dynamic range of 120 $\text{dB}$, stand out as ideal tools for deployment in fast-paced settings like vehicles and drones. Traditional…
We propose a single-stage, category-level 6-DoF pose estimation algorithm that simultaneously detects and tracks instances of objects within a known category. Our method takes as input the previous and current frame from a monocular RGB…