TA-DA! - Improving Activity Recognition Using Temporal Adapters and Data Augmentation

被引：0

作者：

Hopp, Maximilian ^{[1
]}

Hartleb, Helge ^{[1
]}

Burchard, Robin ^{[1
]}

机构：

[1] Univ Siegen, Siegen, Germany

来源：

COMPANION OF THE 2024 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING, UBICOMP COMPANION 2024 | 2024年

关键词：

Human activity recognition; Deep Learning; Machine Learning; Temporal action detection; Data augmentation;

D O I：

10.1145/3675094.3678454

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this report, we describe the technical details of our submission to the WEAR Dataset Challenge 2024. For this competition, we use two approaches to boost the performance of the official WEAR GitHub repository. 1) Integration of a Temporal-Informative adapter (TIA) into the models of the WEAR repository; 2) Data Augmentation Techniques to enrich the provided test dataset. Our method achieves roughly 4.7% improved results(1) on the test set of the WEAR Dataset Challenge 2024 compared to the baseline of the WEAR repository.

引用

页码：551 / 554

页数：4

共 9 条

[1]

Bock M, 2024, Arxiv, DOI arXiv:2311.15831

[2]

Bock M, 2024, Arxiv, DOI [arXiv:2304.05088, 10.48550/ARXIV.2304.05088]

[3] Scaling Egocentric Vision: The EPIC-KITCHENS Dataset [J].

Damen, Dima ;

Doughty, Hazel ;

Farinella, Giovanni Maria ;

Fidler, Sanja ;

Furnari, Antonino ;

Kazakos, Evangelos ;

Moltisanti, Davide ;

Munro, Jonathan ;

Perrett, Toby ;

Price, Will ;

Wray, Michael .

COMPUTER VISION - ECCV 2018, PT IV, 2018, 11208 :753-771

[4] CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining [J].

Hong, Zhiqing ;

Li, Zelong ;

Zhong, Shuxin ;

Lyu, Wenjun ;

Wang, Haotian ;

Ding, Yi ;

He, Tian ;

Zhang, Desheng .

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT, 2024, 8 (02)

[5] End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames [J].

Liu, Shuming ;

Zhang, Chen-Lin ;

Zhao, Chen ;

Ghanem, Bernard .

2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, :18591-18601

[6]

Liu Shuming, 2024, OpenTAD: An Open-Source Toolbox for Temporal Action Detection

[7] TriDet: Temporal Action Detection with Relative Boundary Modeling [J].

Shi, Dingfeng ;

Zhong, Yujie ;

Cao, Qiong ;

Ma, Lin ;

Li, Jia ;

Tao, Dacheng .

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, :18857-18866

[8] Sensor Data Augmentation by Resampling in Contrastive Learning for Human Activity Recognition [J].

Wang, Jinqiang ;

Zhu, Tao ;

Gan, Jingyuan ;

Chen, Liming Luke ;

Ning, Huansheng ;

Wan, Yaping .

IEEE SENSORS JOURNAL, 2022, 22 (23) :22994-23008

[9] ActionFormer: Localizing Moments of Actions with Transformers [J].

Zhang, Chen-Lin ;

Wu, Jianxin ;

Li, Yin .

COMPUTER VISION - ECCV 2022, PT IV, 2022, 13664 :492-510

← 1 →