paper-with-me

홈 › Papers

Adaptive Interaction Modeling via Graph Operations Search

2020-05-05 · CVPR 2020 6 · Haoxin Li, Wei-Shi Zheng, Yu Tao, Haifeng Hu, Jian-Huang Lai

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.

📄 PDF Abstract BibTeX arXiv:2005.02113

Code (1)

lihaoxin05/graph-operations-search 공식 구현 pytorch

Tasks

Action Analysis

Similar Papers 제목 키워드 기반

Adaptive Graph Rewiring to Mitigate Over-Squashing in Mesh-Based GNNs for Fluid Dynamics Simulations

2025-11-16 · Sangwoo Seo, Hyunsung Kim, Jiwan Kim, Chanyoung Park arxiv

Mesh-based simulation using Graph Neural Networks (GNNs) has been recognized as a promising approach for modeling fluid dynamics. However, the mesh refinement techniques which allocate finer resolution to regions with st…

High-Order Pooling for Graph Neural Networks with Tensor Decomposition

2022-05-24 · Chenqing Hua, Guillaume Rabusseau, Jian Tang

Graph Neural Networks (GNNs) are attracting growing attention due to their effectiveness and flexibility in modeling a variety of graph-structured data. Exiting GNN architectures usually adopt simple pooling operations (…

ClassificationGraph ClassificationGraph Neural NetworkNode Classification+2

Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition

2024-02-04 · Mengyuan Liu, Chen Chen, Songtao Wu, Fanyang Meng 외

Recognizing interactive actions, including hand-to-hand interaction and human-to-human interaction, has attracted increasing attention for various applications in the field of video analysis and human-robot interaction. …

Action RecognitionHuman Interaction Recognition

Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach

2020-01-28 · Lei Chen, Le Wu, Richang Hong, Kun Zhang 외

Graph Convolutional Networks (GCNs) are state-of-the-art graph based representation learning models by iteratively stacking multiple layers of convolution aggregation operations and non-linear activation operations. Rece…

Collaborative FilteringRecommendation SystemsRepresentation Learning

MIRROR: A Multi-Agent Framework with Iterative Adaptive Revision and Hierarchical Retrieval for Optimization Modeling in Operations Research

2026-02-03 · Yifan Shi, Jiayi Wang, Minyi Wu, Ye Fan 외 arxiv

Operations Research (OR) relies on expert-driven modeling--a slow and fragile process ill-suited to novel scenarios. While large language models (LLMs) can automatically translate natural language into optimization model…