Related papers: Environment-Invariant Curriculum Relation Learning…

Scene graphs are nodes and edges consisting of objects and object-object relationships, respectively. Scene graph generation (SGG) aims to identify the objects and their relationships. We propose a bidirectional GRU (BiGRU) transformer…

During the last half decade, convolutional neural networks (CNNs) have triumphed over semantic segmentation, which is one of the core tasks in many applications such as autonomous driving. However, to train CNNs requires a considerable…

Models are expected to engage in invariance learning, which involves distinguishing the core relations that remain consistent across varying environments to ensure the predictions are safe, robust and fair. While existing works consider…

The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with…

Radiology report generation (RRG) methods often lack sufficient medical knowledge to produce clinically accurate reports. The scene graph contains rich information to describe the objects in an image. We explore enriching the medical…

Graph machine learning has been extensively studied in both academia and industry. However, in the literature, most existing graph machine learning models are designed to conduct training with data samples in a random order, which may…

One of the key issues of Visual Question Answering (VQA) is to reason with semantic clues in the visual content under the guidance of the question, how to model relational semantics still remains as a great challenge. To fully capture…

Intra-class variability is given according to the significance in the degree of dissimilarity between images within a class. In that sense, depending on its intensity, intra-class variability can hinder the learning process for DL models,…

In Scene Graph Generation (SGG), structured representations are extracted from visual inputs as object nodes and connecting predicates, enabling image-based reasoning for diverse downstream tasks. While fully supervised SGG has improved…

Real-world social events typically exhibit a severe class-imbalance distribution, which makes the trained detection model encounter a serious generalization challenge. Most studies solve this problem from the frequency perspective and…

Perspective-Aware AI requires modeling evolving internal states--goals, emotions, contexts--not merely preferences. Progress is limited by a data bottleneck: digital footprints are privacy-sensitive and perspective states are rarely…

Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning, leading to state-of-the-art models for various downstream multimodal tasks. However, recent research has…

Scene graph generation (SGG) aims to predict graph-structured descriptions of input images, in the form of objects and relationships between them. This task is becoming increasingly useful for progress at the interface of vision and…

Scene Graph Generation (SGG) aims to extract <subject, predicate, object> relationships in images for vision understanding. Although recent works have made steady progress on SGG, they still suffer long-tail distribution issues that…

Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…

Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and…

A major challenge in scene graph classification is that the appearance of objects and relations can be significantly different from one image to another. Previous works have addressed this by relational reasoning over all objects in an…

Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contrast to the…

A pervasive challenge in Reinforcement Learning (RL) is the "curse of dimensionality" which is the exponential growth in the state-action space when optimizing a high-dimensional target task. The framework of curriculum learning trains the…

Heterogeneous trajectory forecasting is critical for intelligent transportation systems, but it is challenging because of the difficulty of modeling the complex interaction relations among the heterogeneous road agents as well as their…