Related papers: Attentive pooling for Group Activity Recognition

Graph pooling is an essential ingredient of Graph Neural Networks (GNNs) in graph classification and regression tasks. For these tasks, different pooling strategies have been proposed to generate a graph-level representation by downsampling…

Graph pooling compresses graph information into a compact representation. State-of-the-art graph pooling methods follow a hierarchical approach, which reduces the graph size step-by-step. These methods must balance memory efficiency with…

A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explanation for the…

We present a novel hierarchical model for human activity recognition. In contrast to approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels…

We propose a novel method for temporally pooling frames in a video for the task of human action recognition. The method is motivated by the observation that there are only a small number of frames which, together, contain sufficient…

Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity. Usually, this pooling step discards the temporal…

Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However,…

Pooling-based recurrent neural architectures consistently outperform their counterparts without pooling. However, the reasons for their enhanced performance are largely unexamined. In this work, we examine three commonly used pooling…

Existing AI systems for modeling human behavior operate at the level of individuals or detect events after they occur. As a result, they systematically fail to capture the collective dynamics that determine whether a group remains stable or…

Graph pooling is a crucial operation for encoding hierarchical structures within graphs. Most existing graph pooling approaches formulate the problem as a node clustering task which effectively captures the graph topology. Conventional…

Multi-person pose estimation is challenging because it localizes body keypoints for multiple persons simultaneously. Previous methods can be divided into two streams, i.e. top-down and bottom-up methods. The top-down methods localize…

Graph clustering is an unsupervised machine learning method that partitions the nodes in a graph into different groups. Despite achieving significant progress in exploiting both attributed and structured data information, graph clustering…

Despite the recent successes of multi-agent reinforcement learning (MARL) algorithms, efficiently adapting to co-players in mixed-motive environments remains a significant challenge. One feasible approach is to hierarchically model…

Recent years have witnessed the emergence and flourishing of hierarchical graph pooling neural networks (HGPNNs) which are effective graph representation learning approaches for graph level tasks such as graph classification. However,…

Group activity detection (GAD) is the task of identifying members of each group and classifying the activity of the group at the same time in a video. While GAD has been studied recently, there is still much room for improvement in both…

Group Activity Recognition (GAR) aims to detect the activity performed by multiple actors in a scene. Prior works model the spatio-temporal features based on the RGB, optical flow or keypoint data types. However, using both the temporality…

In the framework of convolutional neural networks, downsampling is often performed with an average-pooling, where all the activations are treated equally, or with a max-pooling operation that only retains an element with maximum activation…

Grouping has been commonly used in deep metric learning for computing diverse features. However, current methods are prone to overfitting and lack interpretability. In this work, we propose an improved and interpretable grouping method to…

Rather than simply recognizing the action of a person individually, collective activity recognition aims to find out what a group of people is acting in a collective scene. Previ- ous state-of-the-art methods using hand-crafted potentials…

Neural Cellular Automata (NCA) offer a robust and interpretable approach to image classification, making them a promising choice for microscopy image analysis. However, a performance gap remains between NCA and larger, more complex…