Related papers: GTA: A Geometry-Aware Attention Mechanism for Mult…

Real-world graphs naturally exhibit hierarchical or cyclical structures that are unfit for the typical Euclidean space. While there exist graph neural networks that leverage hyperbolic or spherical spaces to learn representations that embed…

Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully…

Answering semantically-complicated questions according to an image is challenging in Visual Question Answering (VQA) task. Although the image can be well represented by deep learning, the question is always simply embedded and cannot well…

Transformers and their attention mechanism have been revolutionary in the field of Machine Learning. While originally proposed for the language data, they quickly found their way to the image, video, graph, etc. data modalities with various…

Detection transformers like DETR have recently shown promising performance on many object detection tasks, but the generalization ability of those methods is still quite challenging for cross-domain adaptation scenarios. To address the…

Determining an appropriate number of attention heads on one hand and the number of transformer-encoders, on the other hand, is an important choice for Computer Vision (CV) tasks using the Transformer architecture. Computing experiments…

Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism. Recent studies have shown that explicitly modeling the input graph structure can significantly improve the performance. However, the vanilla…

Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it…

Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…

Impressive performance of Transformer has been attributed to self-attention, where dependencies between entire input in a sequence are considered at every position. In this work, we reform the neural $n$-gram model, which focuses on only…

3D reconstruction from multi-view images is a core challenge in computer vision. Recently, feed-forward methods have emerged as efficient and robust alternatives to traditional per-scene optimization techniques. Among them, state-of-the-art…

Monocular depth estimation is a central problem in computer vision with applications in robotics, AR, and autonomous driving, yet the self-attention mechanisms that drive modern Transformer architectures remain opaque. We introduce…

Positional encodings enable Transformers to incorporate sequential information, yet their theoretical understanding remains limited to two properties: distance attenuation and translation invariance. Because natural language lacks purely…

We present an attention-based spatial graph convolution (AGC) for graph neural networks (GNNs). Existing AGCs focus on only using node-wise features and utilizing one type of attention function when calculating attention weights. Instead,…

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

Graph Transformers (GTs) have significantly advanced the field of graph representation learning by overcoming the limitations of message-passing graph neural networks (GNNs) and demonstrating promising performance and expressive power.…

Deep learning-based approaches, particularly graph neural networks (GNNs), have gained prominence in simulating flexible deformations and contacts of solids, due to their ability to handle unstructured physical fields and nonlinear…

Graph Neural Networks (GNNs) have emerged as the de facto standard for modeling graph data, with attention mechanisms and transformers significantly enhancing their performance on graph-based tasks. Despite these advancements, the…

Geometry problem solving (GPS) is a challenging mathematical reasoning task requiring multi-modal understanding, fusion, and reasoning. Existing neural solvers take GPS as a vision-language task but are short in the representation of…

Shift equivariance is a fundamental principle that governs how we perceive the world - our recognition of an object remains invariant with respect to shifts. Transformers have gained immense popularity due to their effectiveness in both…