Related papers: Global Occlusion-Aware Transformer for Robust Ster…
Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the training images with artificial occlusions has been proved as…
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…
Accurate estimation of three-dimensional human skeletons from depth images can provide important metrics for healthcare applications, especially for biomechanical gait analysis. However, there exist inherent problems associated with depth…
In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by…
In this work, we address the problem of cross-view geo-localization, which estimates the geospatial location of a street view image by matching it with a database of geo-tagged aerial images. The cross-view matching task is extremely…
Depth completion aims to recover a dense depth map from the sparse depth data and the corresponding single RGB image. The observed pixels provide the significant guidance for the recovery of the unobserved pixels' depth. However, due to the…
Transformers achieve strong performance across diverse domains but implicitly assume Euclidean geometry in their attention mechanisms, limiting their effectiveness on data with non-Euclidean structure. While recent extensions to hyperbolic…
Internet of Things (IoT) sensor data or readings evince variations in timestamp range, sampling frequency, geographical location, unit of measurement, etc. Such presented sequence data heterogeneity makes it difficult for traditional time…
Sequential labeling is a fundamental NLP task, forming the backbone of many applications. Supervised learning of Seq2Seq models has shown great success on these problems. However, the training objectives are still significantly disconnected…
Neural operators have shown great potential in solving a family of Partial Differential Equations (PDEs) by modeling the mappings between input and output functions. Fourier Neural Operator (FNO) implements global convolutions via…
Recent progress in cross-lingual relation and event extraction use graph convolutional networks (GCNs) with universal dependency parses to learn language-agnostic sentence representations such that models trained on one language can be…
Vision Transformers achieved outstanding performance in many computer vision tasks. Early Vision Transformers such as ViT and DeiT adopt global self-attention, which is computationally expensive when the number of patches is large. To…
We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new learnable normalization function in an end-to-end manner. The attention module guides our model to focus on more…
Human pose transfer aims at transferring the appearance of the source person to the target pose. Existing methods utilizing flow-based warping for non-rigid human image generation have achieved great success. However, they fail to preserve…
Transformer architectures have emerged as promising deep learning (DL) tools for modeling complex sequence-to-sequence interactions in channel decoding. However, current transformer-based decoders for error correction codes (ECCs)…
Considerable efforts have been made to improve monocular depth estimation under ideal conditions. However, in challenging environments, monocular depth estimation still faces difficulties. In this paper, we introduce visual prompt learning…
While large models demonstrate the strong representational power of vanilla attention, this core mechanism cannot be directly applied to Dense Object Tracking: its quadratic all-to-all interactions are computationally prohibitive for dense…
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or…
Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based…
Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames. Most methods accomplish the task by explicitly or implicitly leveraging strong cues (i.e., spatial and appearance information), which exhibit…