Zobrazeno 1 - 10
of 74
pro vyhledávání: '"Roitberg, Alina"'
Autor:
Peng, Kunyu, Wen, Di, Yang, Kailun, Luo, Ao, Chen, Yufan, Fu, Jia, Sarfraz, M. Saquib, Roitberg, Alina, Stiefelhagen, Rainer
In Open-Set Domain Generalization (OSDG), the model is exposed to both new variations of data appearance (domains) and open-set conditions, where both known and novel categories are present at test time. The challenges of this task arise from the dua
Externí odkaz:
http://arxiv.org/abs/2409.17555
Recognizing pain in video is crucial for improving patient-computer interaction systems, yet traditional data collection in this domain raises significant ethical and logistical challenges. This study introduces a novel approach that leverages synthe
Externí odkaz:
http://arxiv.org/abs/2409.16382
Foundation models (FMs) are large neural networks trained on broad datasets, excelling in downstream tasks with minimal fine-tuning. Human activity recognition in video has advanced with FMs, driven by competition among different architectures. Howev
Externí odkaz:
http://arxiv.org/abs/2407.15605
Autor:
Peng, Kunyu, Fu, Jia, Yang, Kailun, Wen, Di, Chen, Yufan, Liu, Ruiping, Zheng, Junwei, Zhang, Jiaming, Sarfraz, M. Saquib, Stiefelhagen, Rainer, Roitberg, Alina
We introduce a new task called Referring Atomic Video Action Recognition (RAVAR), aimed at identifying atomic actions of a particular person based on a textual description and the video data of this person. This task differs from traditional action r
Externí odkaz:
http://arxiv.org/abs/2407.01872
Autor:
Xu, Yi, Peng, Kunyu, Wen, Di, Liu, Ruiping, Zheng, Junwei, Chen, Yufan, Zhang, Jiaming, Roitberg, Alina, Yang, Kailun, Stiefelhagen, Rainer
Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequence
Externí odkaz:
http://arxiv.org/abs/2403.09975
Autor:
Moured, Omar, Baumgarten-Egemole, Morris, Roitberg, Alina, Muller, Karin, Schwarz, Thorsten, Stiefelhagen, Rainer
In a world driven by data visualization, ensuring the inclusive accessibility of charts for Blind and Visually Impaired (BVI) individuals remains a significant challenge. Charts are usually presented as raster graphics without textual and visual meta
Externí odkaz:
http://arxiv.org/abs/2403.06693
Autor:
Peng, Kunyu, Yin, Cheng, Zheng, Junwei, Liu, Ruiping, Schneider, David, Zhang, Jiaming, Yang, Kailun, Sarfraz, M. Saquib, Stiefelhagen, Rainer, Roitberg, Alina
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. However, using pure skeleton data in such open-set conditions poses challeng
Externí odkaz:
http://arxiv.org/abs/2312.06330
Deep learning-based models are at the forefront of most driver observation benchmarks due to their remarkable accuracies but are also associated with high computational costs. This is challenging, as resources are often limited in real-world driving
Externí odkaz:
http://arxiv.org/abs/2311.05970
Autor:
Chen, Yifei, Peng, Kunyu, Roitberg, Alina, Schneider, David, Zhang, Jiaming, Zheng, Junwei, Liu, Ruiping, Chen, Yufan, Yang, Kailun, Stiefelhagen, Rainer
To integrate action recognition methods into autonomous robotic systems, it is crucial to consider adverse situations involving target occlusions. Such a scenario, despite its practical relevance, is rarely addressed in existing self-supervised skele
Externí odkaz:
http://arxiv.org/abs/2309.12029
Autor:
Wei, Yiping, Peng, Kunyu, Roitberg, Alina, Zhang, Jiaming, Zheng, Junwei, Liu, Ruiping, Chen, Yufan, Yang, Kailun, Stiefelhagen, Rainer
Self-supervised representation learning for human action recognition has developed rapidly in recent years. Most of the existing works are based on skeleton data while using a multi-modality setup. These works overlooked the differences in performanc
Externí odkaz:
http://arxiv.org/abs/2309.12009