1 code implementation • 15 Mar 2024 • Yi Xu, Kunyu Peng, Di Wen, Ruiping Liu, Junwei Zheng, Yufan Chen, Jiaming Zhang, Alina Roitberg, Kailun Yang, Rainer Stiefelhagen
In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark.
1 code implementation • 11 Dec 2023 • Kunyu Peng, Cheng Yin, Junwei Zheng, Ruiping Liu, David Schneider, Jiaming Zhang, Kailun Yang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg
In real-world scenarios, human actions often fall outside the distribution of training data, making it crucial for models to recognize known actions and reject unknown ones.
1 code implementation • 10 Nov 2023 • Calvin Tanama, Kunyu Peng, Zdravko Marinov, Rainer Stiefelhagen, Alina Roitberg
The framework enhances 3D MobileNet, a neural architecture optimized for speed in video classification, by incorporating knowledge distillation and model quantization to balance model accuracy and computational efficiency.
1 code implementation • 21 Sep 2023 • Yifei Chen, Kunyu Peng, Alina Roitberg, David Schneider, Jiaming Zhang, Junwei Zheng, Ruiping Liu, Yufan Chen, Kailun Yang, Rainer Stiefelhagen
To integrate action recognition methods into autonomous robotic systems, it is crucial to consider adverse situations involving target occlusions.
1 code implementation • 21 Sep 2023 • Yiping Wei, Kunyu Peng, Alina Roitberg, Jiaming Zhang, Junwei Zheng, Ruiping Liu, Yufan Chen, Kailun Yang, Rainer Stiefelhagen
These works overlooked the differences in performance among modalities, which led to the propagation of erroneous knowledge between modalities while only three fundamental modalities, i. e., joints, bones, and motions are used, hence no additional modalities are explored.
no code implementations • 31 Jul 2023 • Walter Morales-Alvarez, Novel Certad, Alina Roitberg, Rainer Stiefelhagen, Cristina Olaverri-Monreal
For driver observation frameworks, clean datasets collected in controlled simulated environments often serve as the initial training ground.
1 code implementation • 5 Jul 2023 • Omar Moured, Jiaming Zhang, Alina Roitberg, Thorsten Schwarz, Rainer Stiefelhagen
The digitization of documents allows for wider accessibility and reproducibility.
2 code implementations • 15 May 2023 • Kunyu Peng, Di Wen, David Schneider, Jiaming Zhang, Kailun Yang, M. Saquib Sarfraz, Rainer Stiefelhagen, Alina Roitberg
Domain adaptation is essential for activity recognition to ensure accurate and robust performance across diverse environments, sensor types, and data sources.
1 code implementation • 7 May 2023 • Jiacheng Lin, Jiajun Chen, Kailun Yang, Alina Roitberg, Siyu Li, Zhiyong Li, Shutao Li
Interactive Image Segmentation (IIS) has emerged as a promising technique for decreasing annotation time.
1 code implementation • 24 Mar 2023 • Hao Shi, Yu Li, Kailun Yang, Jiaming Zhang, Kunyu Peng, Alina Roitberg, Yaozu Ye, Huajian Ni, Kaiwei Wang, Rainer Stiefelhagen
This paper raises the new task of Fisheye Semantic Completion (FSC), where dense texture, structure, and semantics of a fisheye image are inferred even beyond the sensor field-of-view (FoV).
1 code implementation • 2 Mar 2023 • Kunyu Peng, David Schneider, Alina Roitberg, Kailun Yang, Jiaming Zhang, Chen Deng, Kaiyu Zhang, M. Saquib Sarfraz, Rainer Stiefelhagen
In this paper, we tackle the new task of video-based Activated Muscle Group Estimation (AMGE) aiming at identifying active muscle regions during physical activity in the wild.
no code implementations • 19 Aug 2022 • Zdravko Marinov, Alina Roitberg, David Schneider, Rainer Stiefelhagen
Modality selection is an important step when designing multimodal systems, especially in the case of cross-domain activity recognition as certain modalities are more robust to domain shift than others.
1 code implementation • 3 Aug 2022 • Zdravko Marinov, David Schneider, Alina Roitberg, Rainer Stiefelhagen
We tackle this challenge and introduce an activity domain generation framework which creates novel ADL appearances (novel domains) from different existing activity modalities (source domains) inferred from video training data.
1 code implementation • 13 Jul 2022 • Ping-Cheng Wei, Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
Failure to timely diagnose and effectively treat depression leads to over 280 million people suffering from this psychological disorder worldwide.
no code implementations • 10 Apr 2022 • Alina Roitberg, Kunyu Peng, Zdravko Marinov, Constantin Seibold, David Schneider, Rainer Stiefelhagen
Visual recognition inside the vehicle cabin leads to safer driving and more intuitive human-vehicle interaction but such systems face substantial obstacles as they need to capture different granularities of driver behaviour while dealing with highly limited body visibility and changing illumination.
no code implementations • 10 Apr 2022 • Alina Roitberg, Kunyu Peng, David Schneider, Kailun Yang, Marios Koulakis, Manuel Martinez, Rainer Stiefelhagen
In this work, we for the first time examine how well the confidence values of modern driver observation models indeed match the probability of the correct outcome and show that raw neural network-based approaches tend to significantly overestimate their prediction quality.
1 code implementation • 19 Mar 2022 • Xinyu Luo, Jiaming Zhang, Kailun Yang, Alina Roitberg, Kunyu Peng, Rainer Stiefelhagen
Autonomous vehicles utilize urban scene segmentation to understand the real world like a human and react accordingly.
Ranked #1 on Semantic Segmentation on DADA-seg (using extra training data)
1 code implementation • 2 Mar 2022 • Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
This module operates in the latent feature-space enriching and diversifying the training set at feature-level in order to improve generalization to novel data appearances, (e. g., sensor changes) and general feature quality.
2 code implementations • 27 Feb 2022 • Ruiping Liu, Kailun Yang, Alina Roitberg, Jiaming Zhang, Kunyu Peng, Huayao Liu, Yaonan Wang, Rainer Stiefelhagen
Semantic segmentation benchmarks in the realm of autonomous driving are dominated by large pre-trained transformers, yet their widespread adoption is impeded by substantial computational costs and prolonged training durations.
2 code implementations • 23 Feb 2022 • Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
Yet, the research of data-scarce recognition from skeleton sequences, such as one-shot action recognition, does not explicitly consider occlusions despite their everyday pervasiveness.
Ranked #1 on Action Classification on Toyota Smarthome dataset (Accuracy metric)
1 code implementation • 1 Feb 2022 • Kunyu Peng, Alina Roitberg, Kailun Yang, Jiaming Zhang, Rainer Stiefelhagen
To study this underresearched task, we introduce Vid2Burn -- an omni-source benchmark for estimating caloric expenditure from video data featuring both, high- and low-intensity activities for which we derive energy expenditure annotations based on models established in medical literature.
1 code implementation • 30 Nov 2021 • Kunyu Peng, Alina Roitberg, David Schneider, Marios Koulakis, Kailun Yang, Rainer Stiefelhagen
Human affect recognition is a well-established research area with numerous applications, e. g., in psychological care, but existing methods assume that all emotions-of-interest are given a priori as annotated training examples.
1 code implementation • 21 Oct 2021 • Jiaming Zhang, Chaoxiang Ma, Kailun Yang, Alina Roitberg, Kunyu Peng, Rainer Stiefelhagen
We look at this problem from the perspective of domain adaptation and bring panoramic semantic segmentation to a setting, where labelled training data originates from a different distribution of conventional pinhole camera images.
Ranked #7 on Semantic Segmentation on DensePASS (using extra training data)
1 code implementation • 13 Aug 2021 • Chaoxiang Ma, Jiaming Zhang, Kailun Yang, Alina Roitberg, Rainer Stiefelhagen
First, we formalize the task of unsupervised domain adaptation for panoramic semantic segmentation, where a network trained on labelled examples from the source domain of pinhole camera data is deployed in a different target domain of panoramic images, for which no labels are available.
1 code implementation • 12 Jul 2021 • Alina Roitberg, David Schneider, Aulia Djamal, Constantin Seibold, Simon Reiß, Rainer Stiefelhagen
Recognizing Activities of Daily Living (ADL) is a vital process for intelligent assistive robots, but collecting large annotated datasets requires time-consuming temporal labeling and raises privacy concerns, e. g., if the data is collected in a real household.
1 code implementation • 1 Jul 2021 • Kunyu Peng, Juncong Fei, Kailun Yang, Alina Roitberg, Jiaming Zhang, Frank Bieder, Philipp Heidenreich, Christoph Stiller, Rainer Stiefelhagen
At the heart of all automated driving systems is the ability to sense the surroundings, e. g., through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as SemanticKITTI and nuScenes-LidarSeg.
no code implementations • 2 Jan 2021 • Alina Roitberg, Monica Haurilet, Manuel Martinez, Rainer Stiefelhagen
While temperature scaling alone drastically improves the reliability of the confidence values, our CARING method consistently leads to the best uncertainty estimates in all benchmark settings.
no code implementations • 2 Nov 2020 • Robin Ruede, Verena Heusser, Lukas Frank, Alina Roitberg, Monica Haurilet, Rainer Stiefelhagen
Our experiments demonstrate clear benefits of multi-task learning for calorie estimation, surpassing the single-task calorie regression by 9. 9%.
no code implementations • 30 Oct 2018 • Alina Roitberg, Ziad Al-Halah, Rainer Stiefelhagen
While it is common in activity recognition to assume a closed-set setting, i. e. test samples are always of training categories, this assumption is impractical in a real-world scenario.