Related papers: Towards Sequence-Level Training for Visual Trackin…
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning…
We propose a novel memory-based tracker via part-level dense memory and voting-based retrieval, called DMV. Since deep learning techniques have been introduced to the tracking field, Siamese trackers have attracted many researchers due to…
In this paper, we study the challenging problem of multi-object tracking in a complex scene captured by a single camera. Different from the existing tracklet association-based tracking methods, we propose a novel and efficient way to obtain…
Conventional visual object trackers localize targets using handcrafted spatial priors, often in the form of heatmaps. Such priors provide only surrogate supervision and are poorly aligned with tracking optimization and evaluation metrics,…
Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers.…
Single object tracking aims to locate one specific target in video sequences, given its initial state. Classical trackers rely solely on visual cues, restricting their ability to handle challenges such as appearance variations, ambiguity,…
We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this, we define a common format, "visual sentences", in which we can represent raw images…
Tracking the 6D pose of objects in video sequences is important for robot manipulation. This task, however, introduces multiple challenges: (i) robot manipulation involves significant occlusions; (ii) data and annotations are troublesome…
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…
Deep metric learning is essential for visual recognition. The widely used pair-wise (or triplet) based loss objectives cannot make full use of semantical information in training samples or give enough attention to those hard samples during…
While traditional methods for instruction-following typically assume prior linguistic and perceptual knowledge, many recent works in reinforcement learning (RL) have proposed learning policies end-to-end, typically by training neural…
We aim for domestic robots to perform long-term indoor service. Under the object-level scene dynamics induced by daily human activities, a robot needs to robustly localize itself in the environment subject to scene uncertainties. Previous…
As a crucial robotic perception capability, visual tracking has been intensively studied recently. In the real-world scenarios, the onboard processing time of the image streams inevitably leads to a discrepancy between the tracking results…
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…
Visual tracking fundamentally involves regressing the state of the target in each frame of a video. Despite significant progress, existing regression-based trackers still tend to experience failures and inaccuracies. To enhance the…
Perceiving the world in terms of objects and tracking them through time is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric…
Robust and accurate visual tracking is one of the most challenging computer vision problems. Due to the inherent lack of training data, a robust approach for constructing a target appearance model is crucial. Recently, discriminatively…
Visual object tracking aims to estimate the location of an arbitrary target in a video sequence given its initial bounding box. By utilizing offline feature learning, the siamese paradigm has recently been the leading framework for high…
Applying new computing paradigms like quantum computing to the field of machine learning has recently gained attention. However, as high-dimensional real-world applications are not yet feasible to be solved using purely quantum hardware,…
The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…