paper-with-me

Papers

Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation

2021-10-11 · Hui Shuai, Lele Wu, Qingshan Liu

This paper proposes a unified framework dubbed Multi-view and Temporal Fusing Transformer (MTF-Transformer) to adaptively handle varying view numbers and video length without camera calibration in 3D Human Pose Estimation (HPE). It consists of Feature Extractor, Multi-view Fusing Transformer (MFT), and Temporal Fusing Transformer (TFT). Feature Extractor estimates 2D pose from each image and fuses the prediction according to the confidence. It provides pose-focused feature embedding and makes subsequent modules computationally lightweight. MFT fuses the features of a varying number of views with a novel Relative-Attention block. It adaptively measures the implicit relative relationship between each pair of views and reconstructs more informative features. TFT aggregates the features of the whole sequence and predicts 3D pose via a transformer. It adaptively deals with the video of arbitrary length and fully unitizes the temporal information. The migration of transformers enables our model to learn spatial geometry better and preserve robustness for varying application scenarios. We report quantitative and qualitative results on the Human3.6M, TotalCapture, and KTH Multiview Football II. Compared with state-of-the-art methods with camera parameters, MTF-Transformer obtains competitive results and generalizes well to dynamic capture with an arbitrary number of unseen views.

📄 PDF Abstract BibTeX arXiv:2110.05092

Code (0)

등록된 구현이 없습니다.

Tasks

3D Human Pose EstimationCamera CalibrationPose Estimation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Adam 설명 없음
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 $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

GAFusion: Adaptive Fusing LiDAR and Camera with Multiple Guidance for 3D Object Detection

2024-11-01 · CVPR 2024 1 · Xiaotian Li, Baojie Fan, Jiandong Tian, Huijie Fan

Recent years have witnessed the remarkable progress of 3D multi-modality object detection methods based on the Bird's-Eye-View (BEV) perspective. However, most of them overlook the complementary interaction and guidance …

3D Object Detectionobject-detectionObject Detection

A Multi-Channel Spatial-Temporal Transformer Model for Traffic Flow Forecasting

2024-05-10 · Jianli Xiao, Baichao Long

Traffic flow forecasting is a crucial task in transportation management and planning. The main challenges for traffic flow forecasting are that (1) as the length of prediction time increases, the accuracy of prediction w…

ManagementPrediction

Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering

2023-10-30 · Xin Su, Phillip Howard, Nagib Hakim, Steven Bethard

Answering time-sensitive questions from long documents requires temporal reasoning over the times in questions and documents. An important open question is whether large language models can perform such reasoning solely …

Question AnsweringTemporal Information Extraction

DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention

2022-12-15 · Zhipeng Luo, Changqing Zhou, Gongjie Zhang, Shijian Lu

3D object detection with surround-view images is an essential task for autonomous driving. In this work, we propose DETR4D, a Transformer-based framework that explores sparse attention and direct feature query for 3D obj…

3D Object DetectionAutonomous DrivingObjectobject-detection+1

MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo

2024-01-22 · Chenjie Cao, Xinlin Ren, Yanwei Fu

Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches have not thoroughly investigated the profou…

3D ReconstructionDepth EstimationPoint Clouds