paper-with-me

홈 › Papers

Hierarchical Relational Inference

2020-10-07 · Aleksandar Stanić, Sjoerd van Steenkiste, Jürgen Schmidhuber

Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms of the complex behaviors they support. To address this, we propose a novel approach to physical reasoning that models objects as hierarchies of parts that may locally behave separately, but also act more globally as a single whole. Unlike prior approaches, our method learns in an unsupervised fashion directly from raw visual images to discover objects, parts, and their relations. It explicitly distinguishes multiple levels of abstraction and improves over a strong baseline at modeling synthetic and real-world videos.

📄 PDF Abstract BibTeX arXiv:2010.03635

Code (0)

등록된 구현이 없습니다.

Tasks

Common Sense Reasoning

Similar Papers 제목 키워드 기반

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression

2021-10-16 · EMNLP 2021 11 · Chenhe Dong, Yaliang Li, Ying Shen, Minghui Qiu

On many natural language processing tasks, large pre-trained language models (PLMs) have shown overwhelming performances compared with traditional neural network methods. Nevertheless, their huge model size and low infer…

Few-Shot LearningKnowledge DistillationLanguage ModelingLanguage Modelling+2

HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering

2021-01-01 · ICCV 2021 10 · Fei Liu, Jing Liu, Weining Wang, Hanqing Lu

Relational reasoning is at the heart of video question answering. However, existing approaches suffer from several common limitations: (1) they only focus on either object-level or frame-level relational reasoning, a…

Question AnsweringRelational ReasoningVideo Question Answering

Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers

2023-04-01 · Jiaang Li, Quan Wang, Zhendong Mao

Relation prediction on knowledge graphs (KGs) is a key research topic. Dominant embedding-based methods mainly focus on the transductive setting and lack the inductive ability to generalize to new entities for inference.…

Inductive Relation PredictionKnowledge GraphsRelationRelation Prediction

Hierarchical Infinite Relational Model

2021-08-16 · Feras A. Saad, Vikash K. Mansinghka

This paper describes the hierarchical infinite relational model (HIRM), a new probabilistic generative model for noisy, sparse, and heterogeneous relational data. Given a set of relations defined over a collection of dom…

AttributeDensity Estimationmodel

Learning Hierarchical Relational Representations through Relational Convolutions

2023-10-05 · Awni Altabaa, John Lafferty

An evolving area of research in deep learning is the study of architectures and inductive biases that support the learning of relational feature representations. In this paper, we address the challenge of learning repres…

Relation