相关论文: Fast-StrucTexT: An Efficient Hourglass Transformer…

The attention operator is arguably the key distinguishing factor of transformer architectures, which have demonstrated state-of-the-art performance on a variety of tasks. However, transformer attention operators often impose a significant…

In this paper, we propose a vision model that adopts token mixing, sequence-pooling, and convolutional tokenizers to achieve state-of-the-art performance and efficient inference in fixed context-length tasks. In the CIFAR100 benchmark, our…

Rapid global urbanization is a double-edged sword, heralding promises of economical prosperity and public health while also posing unique environmental and humanitarian challenges. Smart and connected communities (S&CCs) apply data-centric…

Effective multimodal fusion requires mechanisms that can capture complex cross-modal dependencies while remaining computationally scalable for real-world deployment. Existing audio-visual fusion approaches face a fundamental trade-off:…

Table structure recognition (TSR) requires both table-level coherence (row/column counts, headers, spanning cells) and precise separator localization. We introduce FastTab, a grid-centric TSR model that avoids autoregressive HTML decoding…

Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic…

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Cued Speech (CS) is a pure visual coding method used by hearing-impaired people that combines lip reading with several specific hand shapes to make the spoken language visible. Automatic CS recognition (ACSR) seeks to transcribe visual cues…

Recently, Transformers have gained significant popularity in image restoration tasks such as image super-resolution and denoising, owing to their superior performance. However, balancing performance and computational burden remains a…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Transformers have emerged as the state-of-the-art architecture in medical image registration, outperforming convolutional neural networks (CNNs) by addressing their limited receptive fields and overcoming gradient instability in deeper…

We introduce a new attention mechanism, dubbed structural self-attention (StructSA), that leverages rich correlation patterns naturally emerging in key-query interactions of attention. StructSA generates attention maps by recognizing…

Most existing multimodal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative…

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Transformers have demonstrated strong performance across a wide range of sequence modeling tasks, but their quadratic attention complexity limits scalability to long sequences. Linear models such as Mamba and sliding-window attention (SWA)…

Point scene understanding is a challenging task to process real-world scene point cloud, which aims at segmenting each object, estimating its pose, and reconstructing its mesh simultaneously. Recent state-of-the-art method first segments…

Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. However, two major challenges in modeling such multimodal human language time-series data exist: 1) inherent data…

We describe an efficient hierarchical method to compute attention in the Transformer architecture. The proposed attention mechanism exploits a matrix structure similar to the Hierarchical Matrix (H-Matrix) developed by the numerical…

Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this…

Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison,…