Related papers: Generalization to Novel Objects using Prior Relati…
The collaboration between agents has gradually become an important topic in multi-agent systems. The key is how to efficiently solve the credit assignment problems. This paper introduces MGAN for collaborative multi-agent reinforcement…
In this paper, we tackle the problem of relational behavior forecasting from sensor data. Towards this goal, we propose a novel spatially-aware graph neural network (SpAGNN) that models the interactions between agents in the scene.…
Accurate video understanding involves reasoning about the relationships between actors, objects and their environment, often over long temporal intervals. In this paper, we propose a message passing graph neural network that explicitly…
We update the method of describing and assessing the process of the study of an abstract environment by a system, proposed earlier. We do not model any biological cognition mechanisms and consider the system as an agent equipped with an…
As a structured representation of the image content, the visual scene graph (visual relationship) acts as a bridge between computer vision and natural language processing. Existing models on the scene graph generation task notoriously…
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…
Human ability at solving complex tasks is helped by priors on object and event semantics of their environment. This paper investigates the use of similar prior knowledge for transfer learning in Reinforcement Learning agents. In particular,…
In this paper, we propose an effective global relation learning algorithm to recommend an appropriate location of a building unit for in-game customization of residential home complex. Given a construction layout, we propose a visual…
The idea of reusing or transferring information from previously learned tasks (source tasks) for the learning of new tasks (target tasks) has the potential to significantly improve the sample efficiency of a reinforcement learning agent. In…
We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering. Relaxing the common assumption…
The problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-of-the-art formulate this problem as a sequence-to-sequence task, in which a…
Vision-and-Language Navigation (VLN) requires an agent to navigate in a real-world environment following natural language instructions. From both the textual and visual perspectives, we find that the relationships among the scene, its…
An embodied agent assisting humans is often asked to complete new tasks, and there may not be sufficient time or labeled examples to train the agent to perform these new tasks. Large Language Models (LLMs) trained on considerable knowledge…
Knowledge graphs (KGs) contain rich information about world knowledge, entities and relations. Thus, they can be great supplements to existing pre-trained language models. However, it remains a challenge to efficiently integrate information…
We address the problem of recognizing situations in images. Given an image, the task is to predict the most salient verb (action), and fill its semantic roles such as who is performing the action, what is the source and target of the…
Humans have a remarkable ability to perceive and reason about the world around them by understanding the relationships between objects. In this paper, we investigate the effectiveness of using such relationships for object detection and…
Deep learning has gained great success in various classification tasks. Typically, deep learning models learn underlying features directly from data, and no underlying relationship between classes are included. Similarity between classes…
This paper tackles the problem of how to pre-train a model and make it generally reusable backbones for downstream task learning. In pre-training, we propose a method that builds an agent-environment interaction model by learning domain…
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…
Stowing, the task of placing objects in cluttered shelves or bins, is a common task in warehouse and manufacturing operations. However, this task is still predominantly carried out by human workers as stowing is challenging to automate due…