Related papers: Environment-Invariant Curriculum Relation Learning…

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

Today's open vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Most existing methods…

In many important machine learning applications, the training distribution used to learn a probabilistic classifier differs from the testing distribution on which the classifier will be used to make predictions. Traditional methods correct…

As a structured prediction task, scene graph generation aims to build a visually-grounded scene graph to explicitly model objects and their relationships in an input image. Currently, the mean field variational Bayesian framework is the de…

Scene graphs -- objects as nodes and visual relationships as edges -- describe the whereabouts and interactions of the things and stuff in an image for comprehensive scene understanding. To generate coherent scene graphs, almost all…

Scene graph prediction --- classifying the set of objects and predicates in a visual scene --- requires substantial training data. However, most predicates only occur a handful of times making them difficult to learn. We introduce the first…

Multi-modal models have shown appealing performance in visual recognition tasks, as free-form text-guided training evokes the ability to understand fine-grained visual content. However, current models cannot be trivially applied to scene…

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…

Ensuring validation for highly automated driving poses significant obstacles to the widespread adoption of highly automated vehicles. Scenario-based testing offers a potential solution by reducing the homologation effort required for these…

Text-to-Image (T2I) generation has long been an open problem, with compositional synthesis remaining particularly challenging. This task requires accurate rendering of complex scenes containing multiple objects that exhibit diverse…

As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class…

We present a novel approach to reconstructing lightweight, CAD-based representations of scanned 3D environments from commodity RGB-D sensors. Our key idea is to jointly optimize for both CAD model alignments as well as layout estimations of…

Imbalanced classification on graphs is ubiquitous yet challenging in many real-world applications, such as fraudulent node detection. Recently, graph neural networks (GNNs) have shown promising performance on many network analysis tasks.…

Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability. However, existing models answer poorly for complex reasoning questions with attributes or relations, which…

To address the intermittency of renewable energy source (RES) generation, scenario forecasting offers a series of stochastic realizations for predictive objects with superior flexibility and direct views. Based on a long time-series…

Scene Graph Generation (SGG) as a critical task in image understanding, facing the challenge of head-biased prediction caused by the long-tail distribution of predicates. However, current unbiased SGG methods can easily prioritize improving…

Deep graph learning has gained grand popularity over the past years due to its versatility and success in representing graph data across a wide range of domains. However, the pervasive issue of imbalanced graph data distributions, where…

Spatio-temporal scene graphs represent interactions in a video by decomposing scenes into individual objects and their pair-wise temporal relationships. Long-term anticipation of the fine-grained pair-wise relationships between objects is a…

Instance features in images exhibit spurious correlations with background features, affecting the training process of deep neural classifiers. This leads to insufficient attention to instance features by the classifier, resulting in…

Scene graph generation from images is a task of great interest to applications such as robotics, because graphs are the main way to represent knowledge about the world and regulate human-robot interactions in tasks such as Visual Question…