Pose Induced Video Transformer

Pose-induced video transformers leverage human pose information (2D and/or 3D) to enhance video analysis tasks, primarily focusing on action recognition and 6D pose estimation. Current research employs transformer architectures, often incorporating modules to integrate pose data with RGB video streams, aiming for improved accuracy and efficiency, particularly in challenging scenarios like Activities of Daily Living (ADL) recognition and object pose estimation from limited data. This approach shows promise for advancing applications requiring precise understanding of human movement and object location in videos, such as robotics, augmented reality, and sign language translation.

Papers

December 25, 2023

Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation
Feng Zhou, Jianqin Yin, Peiyang Li
3D Pose 3D Human Pose Estimation Motion Capture Visual Cue 2 Dimensional Pose Single Lifting Activity Pose Induced Video Transformer

November 30, 2023

Just Add $\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living
Dominick Reilly, Srijan Das
Human Action Recognition Generating User Activity Video Transformer Daily Living Pose Information Pose Induced Video Transformer

November 29, 2023

PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens
Sebastian Stapf, Tobias Bauernfeind, Marco Riboldi
Vision Transformer Transformer Architecture 6D Object 6D Pose Estimation Prediction Confidence Pose Induced Video Transformer Pruned Pose Transformer

November 20, 2023

Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models
Pooya Fayyazsanavi, Negar Nejatishahidin, Jana Kosecka
View Translation Context Aware Sign Language Translation Encoder Decoder Model Pose Induced Video Transformer

June 13, 2023

Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images
Panwang Pan, Zhiwen Fan, Brandon Y. Feng, Peihao Wang, Chenxin Li, Zhangyang Wang
LeArning Abstract Human Pose Limited Data RGB Image Object Pose Pose Induced Video Transformer Generalizable Approach Clustered Regularly Interspaced Short Palindromic

May 7, 2023

Poses as Queries: Image-to-LiDAR Map Localization with Transformers
Jinyu Miao, Kun Jiang, Yunlong Wang, Tuopu Wen, Zhongyang Xiao, Zheng Fu, Mengmeng Yang, Maolin Liu, Diange Yang
Transformer Megatron Decepticons Human Pose Place Recognition Query Information Localization Accuracy LiDAR Based Localization Vehicle Localization Cross Modal Localization Pose Induced Video Transformer

April 12, 2023

Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimation
Feixiang Ren
Human Pose Estimation Token Level Token Pruning 2 Dimensional Human Pose Estimation Pose Induced Video Transformer Pruned Pose Transformer

February 15, 2023

Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai, Hongwei Zheng, Botao Wang, Yu Sun, Min Guo, Chenlin Li, Junni Zou, Hongkai Xiong
Human Pose Estimation Iterative Refinement Pose Attention Human Topology Pose Induced Video Transformer

November 25, 2022

PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation
Thomas Jantos, Mohamed Amin Hamdad, Wolfgang Granig, Stephan Weiss, Jan Steinbrener
Object Detector 3D Object 6D Object Pose Estimation Single View 6D Pose Pose Induced Video Transformer State Estimation Task Pose Registration

October 12, 2022

Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers
Moritz Einfalt, Katja Ludwig, Rainer Lienhart
3D Human Pose Estimation Monocular 3D Upsampling Operation Upsampling Module Pose Induced Video Transformer Dense Pose Transformer Era

December 9, 2021

PE-former: Pose Estimation Transformer
Paschalis Panteleris, Antonis Argyros
Encoder Decoder Vision Transformer Architecture Convolutional Backbone Pure Transformer X Former CNN Backbone Pose Induced Video Transformer

Pose Induced Video Transformer

Papers

Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation

Just Add $\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living

PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens

Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Models

Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images

Poses as Queries: Image-to-LiDAR Map Localization with Transformers

Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimation

Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation

PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation

Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers

PE-former: Pose Estimation Transformer