Related papers: MBFormer: A General Transformer-based Learning Par…

Hyperbolic geometry have shown significant potential in modeling complex structured data, particularly those with underlying tree-like and hierarchical structures. Despite the impressive performance of various hyperbolic neural networks…

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and…

Quantum many-body systems realise many different phases of matter characterised by their exotic emergent phenomena. While some simple versions of these properties can occur in systems of free fermions, their occurrence generally implies…

Recognizing geometric features on B-rep models is a cornerstone technique for multimedia content-based retrieval and has been widely applied in intelligent manufacturing. However, previous research often merely focused on Machining Feature…

Attention mechanisms are developing into a viable alternative to convolutional layers as elementary building block of NNs. Their main advantage is that they are not restricted to capture local dependencies in the input, but can draw…

Modeling 3D dynamics is a fundamental problem in multi-body systems across scientific and engineering domains and has important practical implications in object trajectory prediction and simulation. While recent GNN-based approaches have…

Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with…

Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a grounded abstract representation and identify the…

Whole-body manipulation (WBM) for humanoid robots presents a promising approach for executing embracing tasks involving bulky objects, where traditional grasping relying on end-effectors only remains limited in such scenarios due to…

Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models…

We address the challenging task of human reaction generation, which aims to generate a corresponding reaction based on an input action. Most of the existing works do not focus on generating and predicting the reaction and cannot generate…

Domain generalized semantic segmentation (DGSS) is a critical yet challenging task, where the model is trained only on source data without access to any target data. Despite the proposal of numerous DGSS strategies, the generalization…

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token…

Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant…

The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce…

In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified framework that approaches various motion tasks from a prototype perspective. ProtoFormer seamlessly integrates prototype learning with Transformer…

Organic synthesis is one of the key stumbling blocks in medicinal chemistry. A necessary yet unsolved step in planning synthesis is solving the forward problem: given reactants and reagents, predict the products. Similar to other work, we…

The combination of neural network potential (NNP) with molecular simulations plays an important role in an efficient and thorough understanding of a molecular system's potential energy surface (PES). However, grasping the interplay between…

Human activity intensity prediction is crucial to many location-based services. Despite tremendous progress in modeling dynamics of human activity, most existing methods overlook physical constraints of spatial interaction, leading to…

Transformer models have demonstrated remarkable success in many domains such as natural language processing (NLP) and computer vision. With the growing interest in transformer-based architectures, they are now utilized for gesture…