Temporal and Object Quantification Networks
Not on the map. Why?
Abstract (arXiv)
We present Temporal and Object Quantification Networks (TOQ-Nets), a new class of neuro-symbolic networks with a structural bias that enables them to learn to recognize complex relational-temporal events. This is done by including reasoning layers that implement finite-domain quantification over objects and time. The structure allows them to generalize directly to input instances with varying numbers of objects in temporal sequences of varying lengths. We evaluate TOQ-Nets on input domains that require recognizing event-types in terms of complex temporal relational patterns. We demonstrate that TOQ-Nets can generalize from small amounts of data to scenarios containing more objects than were present during training and to temporal warpings of input sequences.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 14 of its 37 references that are in the map. First posted on arXiv 10 Jun 2021.
Builds on
14 of 37 references.
References · 14
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Non-local Neural Networkscited by 2,293
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
- 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
- 2018Videos as Space-Time Region Graphscited by 221
- 2019Neural Logic Machinescited by 145
- 2020Logical Neural Networkscited by 119
- 2016Hierarchical Deep Temporal Models for Group Activity Recognitioncited by 89
- 2018Learning Linear Temporal Propertiescited by 41
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 1.
2 papers.