1 code implementation • 30 Jan 2024 • Ruiping Liu, Jiaming Zhang, Kunyu Peng, Yufan Chen, Ke Cao, Junwei Zheng, M. Saquib Sarfraz, Kailun Yang, Rainer Stiefelhagen
Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework.
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.
no code implementations • 8 Nov 2023 • Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background.
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 • 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 • 15 Sep 2022 • Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali
To this end, we first propose a new, plug-and-play, train-time calibration loss for object detection (coined as TCD).
no code implementations • 14 May 2022 • Constantin Seibold, Simon Reiß, M. Saquib Sarfraz, Rainer Stiefelhagen, Jens Kleesiek
We show that despite using unstructured medical report supervision, we perform on par with direct label supervision through a sophisticated inference setting.
Ranked #1 on Thoracic Disease Classification on ChestX-ray14
1 code implementation • CVPR 2022 • M. Saquib Sarfraz, Marios Koulakis, Constantin Seibold, Rainer Stiefelhagen
Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning.
no code implementations • 1 Oct 2021 • Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali
In this paper, we propose to leverage model predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment.
1 code implementation • CVPR 2021 • M. Saquib Sarfraz, Naila Murray, Vivek Sharma, Ali Diba, Luc van Gool, Rainer Stiefelhagen
Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos and is an important requirement for many video understanding tasks.
Ranked #1 on Action Segmentation on MPII Cooking 2 Dataset
1 code implementation • 19 Aug 2020 • Alexander Wolpert, Michael Teutsch, M. Saquib Sarfraz, Rainer Stiefelhagen
In this way, we can both simplify the network architecture and achieve higher detection performance, especially for pedestrians under occlusion or at low object resolution.
no code implementations • 5 Apr 2020 • Vivek Sharma, Makarand Tapaswi, M. Saquib Sarfraz, Rainer Stiefelhagen
We demonstrate our method on the challenging task of learning representations for video face clustering.
1 code implementation • 1 Aug 2019 • M. Saquib Sarfraz, Constantin Seibold, Haroon Khalid, Rainer Stiefelhagen
In this paper, we propose a novel method of computing the loss directly between the source and target images that enable proper distillation of shape/content and colour/style.
1 code implementation • 3 Mar 2019 • Vivek Sharma, Makarand Tapaswi, M. Saquib Sarfraz, Rainer Stiefelhagen
In this paper, we address video face clustering using unsupervised methods.
1 code implementation • 28 Feb 2019 • M. Saquib Sarfraz, Vivek Sharma, Rainer Stiefelhagen
We present a new clustering method in the form of a single clustering equation that is able to directly discover groupings in the data.
2 code implementations • CVPR 2018 • M. Saquib Sarfraz, Arne Schumann, Andreas Eberle, Rainer Stiefelhagen
In contrast to the recent direction of explicitly modeling body parts or correcting for misalignment based on these, we show that a rather straightforward inclusion of acquired camera view and/or the detected joint locations into a convolutional neural network helps to learn a very effective representation.
Ranked #17 on Person Re-Identification on MARS
no code implementations • 19 Jul 2017 • M. Saquib Sarfraz, Arne Schumann, Yan Wang, Rainer Stiefelhagen
The visual cues hinting at attributes can be strongly localized and inference of person attributes such as hair, backpack, shorts, etc., are highly dependent on the acquired view of the pedestrian.
no code implementations • 20 Jan 2016 • M. Saquib Sarfraz, Rainer Stiefelhagen
Our method bridges the drop in performance due to the modality gap by more than 40\%.
Ranked #2 on Face Recognition on UND-X1
no code implementations • 10 Jul 2015 • M. Saquib Sarfraz, Rainer Stiefelhagen
Cross modal face matching between the thermal and visible spectrum is a much de- sired capability for night-time surveillance and security applications.