Related papers: Gramformer: Learning Crowd Counting via Graph-Modu…

Social group activity recognition is a challenging task extended from group activity recognition, where social groups must be recognized with their activities and group members. Existing methods tackle this task by leveraging region…

Transductive tasks on graphs differ fundamentally from typical supervised machine learning tasks, as the independent and identically distributed (i.i.d.) assumption does not hold among samples. Instead, all train/test/validation samples are…

Graph clustering is essential in graph analysis for revealing structural patterns and node communities. Despite recent advances in self-supervised contrastive learning that have improved clustering via structural and attribute signals,…

Graph Transformers typically rely on explicit positional or structural encodings and dense global attention to incorporate graph topology. In this work, we show that neither is essential. We introduce HopFormer, a graph Transformer that…

Recurrent Neural Networks were, until recently, one of the best ways to capture the timely dependencies in sequences. However, with the introduction of the Transformer, it has been proven that an architecture with only attention-mechanisms…

Community detection is crucial for applications like targeted marketing and recommendation systems. Traditional methods rely on network structure, and embedding-based models integrate semantic information. However, there is a challenge when…

Graph classification is a problem with practical applications in many different domains. Most of the existing methods take the entire graph into account when calculating graph features. In a graphlet-based approach, for instance, the entire…

Single image-based crowd counting has recently witnessed increased focus, but many leading methods are far from optimal, especially in highly congested scenes. In this paper, we present Hierarchical Attention-based Crowd Counting Network…

Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning frameworks to train efficient policies. However, their performance deteriorates when…

Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods used a subset of combinations of component functions and weight matrices within the random feature paradigm. We…

Graph Transformers (GTs) have demonstrated great effectiveness across various graph analytical tasks. However, the existing GTs focus on training and testing graph data originated from the same distribution, but fail to generalize under…

This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens. GRC attention enables attending…

Crowd counting problem that counts the number of people in an image has been extensively studied in recent years. In this paper, we introduce a new variant of crowd counting problem, namely "Categorized Crowd Counting", that counts the…

There has been a recent surge in transformer-based architectures for learning on graphs, mainly motivated by attention as an effective learning mechanism and the desire to supersede handcrafted operators characteristic of message passing…

Occlusions, complex backgrounds, scale variations and non-uniform distributions present great challenges for crowd counting in practical applications. In this paper, we propose a novel method using an attention model to exploit head…

Transformers are built upon multi-head scaled dot-product attention and positional encoding, which aim to learn the feature representations and token dependencies. In this work, we focus on enhancing the distinctive representation by…

Topological Deep Learning seeks to enhance the predictive performance of neural network models by harnessing topological structures in input data. Topological neural networks operate on spaces such as cell complexes and hypergraphs, that…

This paper proposes a crowd counting method. Crowd counting is difficult because of large appearance changes of a target which caused by density and scale changes. Conventional crowd counting methods generally utilize one predictor (e,g.,…

Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are beneficial to graph transformers, and find that current…

Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility…