Related papers: Unbiased Directed Object Attention Graph for Objec…
Graph embedding techniques are pivotal in real-world machine learning tasks that operate on graph-structured data, such as social recommendation and protein structure modeling. Embeddings are mostly performed on the node level for learning…
Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph. One aspect that is often overlooked is whether the graph…
3D object detection is crucial for applications like autonomous driving and robotics. However, in real-world environments, variations in sensor data distribution due to sensor upgrades, weather changes, and geographic differences can…
In this paper, we present two approaches and algorithms that adapt areas of interest (AOI) or regions of interest (ROI), respectively, to the eye tracking data quality and classification task. The first approach uses feature importance in a…
Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies. We investigate the…
The object-based nature of human visual attention is well-known in cognitive science, but has only played a minor role in computational visual attention models so far. This is mainly due to a lack of suitable datasets and evaluation metrics…
A modern deep neural network (DNN) for image classification tasks typically consists of two parts: a backbone for feature extraction, and a head for feature encoding and class predication. We observe that the head structures of mainstream…
Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple…
Accurate and real-time traffic state prediction is of great practical importance for urban traffic control and web mapping services. With the support of massive data, deep learning methods have shown their powerful capability in capturing…
Transformer models have recently gained popularity in graph representation learning as they have the potential to learn complex relationships beyond the ones captured by regular graph neural networks. The main research question is how to…
The human visual system processes images with varied degrees of resolution, with the fovea, a small portion of the retina, capturing the highest acuity region, which gradually declines toward the field of view's periphery. However, the…
Air quality prediction is a typical spatio-temporal modeling problem, which always uses different components to handle spatial and temporal dependencies in complex systems separately. Previous models based on time series analysis and…
In this paper, we introduce the Semantic Environment Atlas (SEA), a novel mapping approach designed to enhance visual navigation capabilities of embodied agents. The SEA utilizes semantic graph maps that intricately delineate the…
Unsupervised domain adaptation (UDA) greatly facilitates the deployment of neural networks across diverse environments. However, most state-of-the-art approaches are overly complex, relying on challenging adversarial training strategies, or…
Object oriented data analysis (OODA) aims at statistically analyzing populations of complicated objects. This paper is motivated by a study of cell images in cell culture biology, which highlights a common critical issue: choice of data…
Arbitrary-oriented object detection (AOOD) has been widely applied to locate and classify objects with diverse orientations in remote sensing images. However, the inconsistent features for the localization and classification tasks in AOOD…
Multi-task learning of deformable object manipulation is a challenging problem in robot manipulation. Most previous works address this problem in a goal-conditioned way and adapt goal images to specify different tasks, which limits the…
Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection (AOOD) addresses this challenge by training on base categories in the source domain and…
Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as there exist numerous application scenarios that have…
While deep learning has significantly improved ReID model accuracy under the independent and identical distribution (IID) assumption, it has also become clear that such models degrade notably when applied to an unseen novel domain due to…