paper-with-me

홈 › Papers

OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification

2021-09-23 · Xianing Chen, Chunlin Xu, Qiong Cao, Jialang Xu, Yujie Zhong, Jiale Xu, Zhengxin Li, Jingya Wang, Shenghua Gao

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 local feature details, which are insufficient due to the dramatic variations of pedestrians. In this work, we propose an Omni-Relational High-Order Transformer (OH-Former) to model omni-relational features for ReID. First, to strengthen the capacity of visual representation, instead of obtaining the attention matrix based on pairs of queries and isolated keys at each spatial location, we take a step further to model high-order statistics information for the non-local mechanism. We share the attention weights in the corresponding layer of each order with a prior mixing mechanism to reduce the computation cost. Then, a convolution-based local relation perception module is proposed to extract the local relations and 2D position information. The experimental results of our model are superior promising, which show state-of-the-art performance on Market-1501, DukeMTMC, MSMT17 and Occluded-Duke datasets.

📄 PDF Abstract BibTeX arXiv:2109.11159

Code (0)

등록된 구현이 없습니다.

Tasks

Person Re-IdentificationVocal Bursts Intensity Prediction

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer

2026-04-27 · Boyang Wang, Guangyi Xu, Jiahui Zhang, Zhipeng Tang 외 arxiv

Shot Boundary Detection (SBD) aims to automatically identify shot changes and divide a video into coherent shots. While SBD was widely studied in the literature, existing methods often produce non-interpretable boundarie…

Boundary Detection

Structure Over Signal: A Globalized Approach to Multi-relational GNNs for Stock Prediction

2025-10-12 · Amber Li, Aruzhan Abil, Juno Marques Oda arxiv

In financial markets, Graph Neural Networks have been successfully applied to modeling relational data, effectively capturing nonlinear inter-stock dependencies. Yet, existing models often fail to efficiently propagate m…

Temporal-Relational CrossTransformers for Few-Shot Action Recognition

2021-01-15 · CVPR 2021 1 · Toby Perrett, Alessandro Masullo, Tilo Burghardt, Majid Mirmehdi 외

We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set. Distinct from previous few-shot works, we construct class prototy…

Action RecognitionFew-Shot action recognitionFew Shot Action Recognition

OmniNet: Omnidirectional Representations from Transformers

2021-03-01 · Yi Tay, Mostafa Dehghani, Vamsi Aribandi, Jai Gupta 외

This paper proposes Omnidirectional Representations from Transformers (OmniNet). In OmniNet, instead of maintaining a strictly horizontal receptive field, each token is allowed to attend to all tokens in the entire netwo…

de-enFew-Shot LearningLanguage ModelingLanguage Modelling+2

Benchmarking Omni-Vision Representation through the Lens of Visual Realms

2022-07-14 · Yuanhan Zhang, Zhenfei Yin, Jing Shao, Ziwei Liu

Though impressive performance has been achieved in specific visual realms (e.g. faces, dogs, and places), an omni-vision representation generalizing to many natural visual domains is highly desirable. But, existing bench…

BenchmarkingContrastive LearningRepresentation LearningSelf-Supervised Learning