# Adaptive Interaction Modeling via Graph Operations Search

arXiv: https://arxiv.org/abs/2005.02113 · HTML: https://mlsanity.com/paper/2005.02113/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2020.

## Built on by (most cited first, 5 of 5)

- [MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain](https://mlsanity.com/paper/2209.08691/) (2022)
- [Diversifying Spatial-Temporal Perception for Video Domain Generalization](https://mlsanity.com/paper/2310.17942/) (2023)
- [Representing Videos as Discriminative Sub-graphs for Action Recognition](https://mlsanity.com/paper/2201.04027/) (2022)
- [Optimization Planning for 3D ConvNets](https://mlsanity.com/paper/2201.04021/) (2022)
- [A Grammatical Compositional Model for Video Action Detection](https://mlsanity.com/paper/2310.02887/) (2023)

## Abstract (arXiv)

Interaction modeling is important for video action analysis. Recently, several works design specific structures to model interactions in videos. However, their structures are manually designed and non-adaptive, which require structures design efforts and more importantly could not model interactions adaptively. In this paper, we automate the process of structures design to learn adaptive structures for interaction modeling. We propose to search the network structures with differentiable architecture search mechanism, which learns to construct adaptive structures for different videos to facilitate adaptive interaction modeling. To this end, we first design the search space with several basic graph operations that explicitly capture different relations in videos. We experimentally demonstrate that our architecture search framework learns to construct adaptive interaction modeling structures, which provides more understanding about the relations between the structures and some interaction characteristics, and also releases the requirement of structures design efforts. Additionally, we show that the designed basic graph operations in the search space are able to model different interactions in videos. The experiments on two interaction datasets show that our method achieves competitive performance with state-of-the-arts.