Related papers: RPT: Learning Point Set Representation for Siamese…
What is a good visual representation for autonomous agents? We address this question in the context of semantic visual navigation, which is the problem of a robot finding its way through a complex environment to a target object, e.g. go to…
The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the computational…
Recently, we have seen a rapid development of Deep Neural Network (DNN) based visual tracking solutions. Some trackers combine the DNN-based solutions with Discriminative Correlation Filters (DCF) to extract semantic features and…
Visual Object Tracking (VOT) is a fundamental task with widespread applications in autonomous navigation, surveillance, and maritime robotics. Despite significant advances in generic object tracking, maritime environments continue to…
Defining a multi-target motion model, which is an important step of tracking algorithms, can be very challenging. Using fixed models (as in several generative Bayesian algorithms, such as Kalman filters) can fail to accurately predict…
This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection…
Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward general point tracking remains constrained by limited…
Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…
In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…
Despite rapid progress in scene segmentation in recent years, 3D segmentation methods are still limited when there is severe occlusion. The key challenge is estimating the segment boundaries of (partially) occluded objects, which are…
Retrieving object instances among cluttered scenes efficiently requires compact yet comprehensive regional image representations. Intuitively, object semantics can help build the index that focuses on the most relevant regions. However, due…
Anchor-based Siamese trackers have achieved remarkable advancements in accuracy, yet the further improvement is restricted by the lagged tracking robustness. We find the underlying reason is that the regression network in anchor-based…
State representation learning aims at learning compact representations from raw observations in robotics and control applications. Approaches used for this objective are auto-encoders, learning forward models, inverse dynamics or learning…
The problem of multi-object tracking is a fundamental computer vision research focus, widely used in public safety, transport, autonomous vehicles, robotics, and other regions involving artificial intelligence. Because of the complexity of…
The fully-convolutional siamese network based on template matching has shown great potentials in visual tracking. During testing, the template is fixed with the initial target feature and the performance totally relies on the general…
For many applications, we need to use techniques to represent convex shapes and objects. In this work, we use level set method to represent shapes and find a necessary and sufficient condition on the level set function to guarantee the…
Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants. Besides the remarkable success, it is important to note that the heuristic…
Reinforcement learning (RL) for robot control typically requires a detailed representation of the environment state, including information about task-relevant objects not directly measurable. Keypoint detectors, such as spatial autoencoders…
Convolutional Siamese neural networks have been recently used to track objects using deep features. Siamese architecture can achieve real time speed, however it is still difficult to find a Siamese architecture that maintains the…
Accurate point tracking in surgical environments remains challenging due to complex visual conditions, including smoke occlusion, specular reflections, and tissue deformation. While existing surgical tracking datasets provide coordinate…