Search Results for author: M. Saquib Sarfraz

Found 19 papers, 11 papers with code

Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation

1 code implementation30 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.

Autonomous Vehicles Scene Segmentation

Navigating Open Set Scenarios for Skeleton-based Action Recognition

1 code implementation11 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.

Novelty Detection Open Set Action Recognition +3

Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning

no code implementations8 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.

Object object-detection +1

RelaMiX: Exploring Few-Shot Adaptation in Video-based Action Recognition

2 code implementations15 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.

Action Recognition Unsupervised Domain Adaptation

MuscleMap: Towards Video-based Activated Muscle Group Estimation in the Wild

1 code implementation2 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.

Human Activity Recognition Knowledge Distillation +1

Towards Improving Calibration in Object Detection Under Domain Shift

no code implementations15 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).

Decision Making Object +3

Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection

no code implementations1 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.

Object object-detection +1

Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation

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.

Action Segmentation Clustering +2

Anchor-free Small-scale Multispectral Pedestrian Detection

1 code implementation19 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.

Autonomous Driving Data Augmentation +3

Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss

1 code implementation1 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.

Image Super-Resolution Translation

Efficient Parameter-free Clustering Using First Neighbor Relations

1 code implementation28 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.

Clustering

A Pose-Sensitive Embedding for Person Re-Identification with Expanded Cross Neighborhood Re-Ranking

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.

Person Re-Identification Re-Ranking +1

Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model

no code implementations19 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.

Attribute Multi-Label Image Classification +2

Deep Perceptual Mapping for Cross-Modal Face Recognition

no code implementations20 Jan 2016 M. Saquib Sarfraz, Rainer Stiefelhagen

Our method bridges the drop in performance due to the modality gap by more than 40\%.

Face Recognition

Deep Perceptual Mapping for Thermal to Visible Face Recognition

no code implementations10 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.

Face Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.