CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation

2022-03-24 · Mohammed Hassanin, Abdelwahed Khamiss, Mohammed Bennamoun, Farid Boussaid, Ibrahim Radwan

3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints in the spatial and temporal domains. While they had shown excellence in long-range dependencies, studies have noted the need for improving the locality of vision Transformers. In this direction, we propose a novel pose estimation Transformer featuring rich representations of body joints critical for capturing subtle changes across frames (i.e., inter-feature representation). Specifically, through two novel interaction modules; Cross-Joint Interaction and Cross-Frame Interaction, the model explicitly encodes the local and global dependencies between the body joints. The proposed architecture achieved state-of-the-art performance on two popular 3D human pose estimation datasets, Human3.6 and MPI-INF-3DHP. In particular, our proposed CrossFormer method boosts performance by 0.9% and 0.3%, compared to the closest counterpart, PoseFormer, using the detected 2D poses and ground-truth settings respectively.

📄 PDF Abstract BibTeX arXiv:2203.13387

Code (1)

mfawzy/CrossFormer 공식 구현 pytorch

Tasks

3D Human Pose Estimation Pose Estimation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Position-Wise Feed-Forward Layer 설명 없음

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…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

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…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting

2023-02-02 · ICLR 2023 2 · Yunhao Zhang, Junchi Yan

Recently many deep models have been proposed for multivariate time series (MTS) forecasting. In particular, Transformer-based models have shown great potential because they can capture long-term dependency. However, exis…

Decoder Multivariate Time Series Forecasting Time Series Time Series Forecasting

CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale Attention

2023-03-13 · Wenxiao Wang, Wei Chen, Qibo Qiu, Long Chen 외

While features of different scales are perceptually important to visual inputs, existing vision transformers do not yet take advantage of them explicitly. To this end, we first propose a cross-scale vision transformer, C…

image-classification Image Classification Instance Segmentation object-detection+2

Crossformer: Transformer with Alternated Cross-Layer Guidance

2021-09-29 · Shujian Zhang, Zhibin Duan, Huangjie Zheng, Pengcheng He 외

Transformers with stacked attention layers have achieved state-of-the-art results on a wide range of tasks related to discrete sequences. Significant work has been done to better understand or interpret the capabilities …

Inductive Bias Machine Translation Node Classification Question Answering+2

Stiff Circuit System Modeling via Transformer

2025-10-06 · Weiman Yan, Yi-Chia Chang, Wanyu Zhao arxiv

Accurate and efficient circuit behavior modeling is a cornerstone of modern electronic design automation. Among different types of circuits, stiff circuits are challenging to model using previous frameworks. In this work…

Parking Availability Prediction via Fusing Multi-Source Data with A Self-Supervised Learning Enhanced Spatio-Temporal Inverted Transformer

2025-09-04 · Yin Huang, Yongqi Dong, Youhua Tang, Li Li arxiv

The rapid growth of private car ownership has worsened the urban parking predicament, underscoring the need for accurate and effective parking availability prediction to support urban planning and management. To address …

Self-Supervised Learning Representation Learning