相关论文: NFormer: Robust Person Re-identification with Neig…

Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions…

Transformers have recently gained increasing attention in computer vision. However, existing studies mostly use Transformers for feature representation learning, e.g. for image classification and dense predictions, and the generalizability…

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional…

Both fine-grained discriminative details and global semantic features can contribute to solving person re-identification challenges, such as occlusion and pose variations. Vision foundation models (\textit{e.g.}, DINO) excel at mining local…

Recent efforts have shown promising results for person re-identification by designing part-based architectures to allow a neural network to learn discriminative representations from semantically coherent parts. Some efforts use soft…

Transformer is the backbone of modern NLP models. In this paper, we propose RealFormer, a simple and generic technique to create Residual Attention Layer Transformer networks that significantly outperform the canonical Transformer and its…

In person re-identification (re-ID), extracting part-level features from person images has been verified to be crucial to offer fine-grained information. Most of the existing CNN-based methods only locate the human parts coarsely, or rely…

Weakly-supervised Human-Object Interaction (HOI) detection is essential for scalable scene understanding, as it learns interactions from only image-level annotations. Due to the lack of localization signals, prior works typically rely on an…

Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical…

This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection. Most facial landmark detectors focus on learning representative image features. However, these CNN-based feature representations are not…

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…

Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain…

The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. Hence learning a feature representation that can adaptively…

Visual place recognition is a challenging task in the field of computer vision, and autonomous robotics and vehicles, which aims to identify a location or a place from visual inputs. Contemporary methods in visual place recognition employ…

Person re-identification aims at establishing the identity of a pedestrian from a gallery that contains images of multiple people obtained from a multi-camera system. Many challenges such as occlusions, drastic lighting and pose variations…

Multi-agent trajectory prediction is a fundamental problem in autonomous driving. The key challenges in prediction are accurately anticipating the behavior of surrounding agents and understanding the scene context. To address these…

Transformers have emerged as viable alternatives to convolutional neural networks owing to their ability to learn non-local region relationships in the spatial domain. The self-attention mechanism of the transformer enables transformers to…

Transformers have shown preferable performance on many vision tasks. However, for the task of person re-identification (ReID), vanilla transformers leave the rich contexts on high-order feature relations under-exploited and deteriorate…