Researcher profile

Rainer Stiefelhagen

Rainer Stiefelhagen contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate

Computer Vision Robotics eess.IV Artificial Intelligence Machine Learning Human-Computer Interaction Systems and Control Computation and Language Data Structures and Algorithms eess.SP Graphics Multimedia

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author

40works

0followers

12topics

4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

EgoExoMem: Cross-View Memory Reasoning over Synchronized Egocentric and Exocentric Videos

Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall from both field and observer perspectives, we introduce EgoExoMem, the first benchmark for cross-view memory reasoning over synchronized egocentric and exocentric videos. EgoExoMem contains $2.6K$ high-quality MCQs across eight temporal, spatial, and cross-view QA types. To support dual-view retrieval, we propose E$^2$-Select, a training-free frame selection method for synchronized ego-exo videos. It combines relevance-based budget allocation with per-view k-DPP sampling to handle view asymmetry and cross-view temporal consistency. Experiments show that ego and exo views provide complementary memory cues, while existing MLLMs remain far from solving the benchmark: the best model reaches only $55.3\%$. E$^2$-Select achieves state-of-the-art performance of $58.2\%$ over frame-selection and RAG-based memory baselines. Further analysis reveals systematic view-preference conflicts between question framing and answer grounding, underscoring the novelty and challenge of cross-view memory reasoning.

preprint2026arXiv

IMPACT-HOI: Supervisory Control for Onset-Anchored Partial HOI Event Construction

We present IMPACT-HOI, a mixed-initiative framework for annotating egocentric procedural video by constructing structured event graphs for Human-Object Interactions (HOI), motivated by the need for high-quality structured supervision for learning robot manipulation from human demonstration. IMPACT-HOI frames this task as the incremental resolution of a partially specified, onset-anchored event state. A trust-calibrated controller selects among direct queries, human-confirmed suggestions, and conservative completions based on empirical annotator behavior and evidence quality. A risk-bounded execution protocol, utilizing atomic rollback, ensures that human-confirmed decisions are preserved against conflicting automated updates. A user study with 9 participants shows a 13.5% reduction in manual annotation actions, a 46.67% event match rate, and zero confirmed-field violations under the studied protocol. The code will be made publicly available at https://github.com/541741106/IMPACT_HOI.

preprint2026arXiv

IMPACT-Scribe: Interactive Temporal Action Segmentation with Boundary Scribbles and Query Planning

Dense temporal annotation of procedural activity videos is vital for action understanding and embodied intelligence but remains labor-intensive due to reactive tools. Each correction is treated as an isolated edit, limiting reuse of information on annotator uncertainty and model reliability. We introduce IMPACT-Scribe, a correction-driven framework for dense labeling that uses each correction to improve future human-machine collaboration. IMPACT-Scribe combines uncertainty-aware boundary scribble supervision, local proposal modeling, cost-aware query planning, structured propagation, and correction-driven adaptation. Experiments and a human study show that this closed-loop design improves labeling quality per effort, enhances boundary accuracy, and fosters better human-machine interaction over time. The code will be made publicly available at https://github.com/BanzQians/IMPACT_AS.

preprint2026arXiv

Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization

Open-Set Domain Generalization (OSDG) is a challenging task requiring models to accurately predict familiar categories while minimizing confidence for unknown categories to effectively reject them in unseen domains. While the OSDG field has seen considerable advancements, the impact of label noise--a common issue in real-world datasets--has been largely overlooked. Label noise can mislead model optimization, thereby exacerbating the challenges of open-set recognition in novel domains. In this study, we take the first step towards addressing Open-Set Domain Generalization under Noisy Labels (OSDG-NL) by constructing dedicated benchmarks derived from widely used OSDG datasets, including PACS and DigitsDG. We evaluate baseline approaches by integrating techniques from both label denoising and OSDG methodologies, highlighting the limitations of existing strategies in handling label noise effectively. To address these limitations, we propose HyProMeta, a novel framework that integrates hyperbolic category prototypes for label noise-aware meta-learning alongside a learnable new-category agnostic prompt designed to enhance generalization to unseen classes. Our extensive experiments demonstrate the superior performance of HyProMeta compared to state-of-the-art methods across the newly established benchmarks. The source code of this work is released at https://github.com/KPeng9510/HyProMeta.

preprint2026arXiv

The autoPET3 Challenge: Automated Lesion Segmentation in Whole-Body PET/CT $\unicode{x2013}$ Multitracer Multicenter Generalization

We report the design and results of the third autoPET challenge (MICCAI 2024), which benchmarked automated lesion segmentation in whole-body PET/CT under a compositional generalization setting. Training data comprised 1,014 [18F]-FDG PET/CT studies from the University Hospital Tübingen and 597 [18F]/[68Ga]-PSMA PET/CT studies from the LMU University Hospital Munich, constituting the largest publicly available annotated PSMA PET/CT dataset to date. The held-out test set of 200 studies covered four tracer-center combinations, two of which represented unseen compositional pairings. A complementary data-centric award category isolated the contribution of data handling strategies by restricting participants to a fixed baseline model. Seventeen teams submitted 27 algorithms, predominantly nnU-Net-based 3D networks with PET/CT channel concatenation. The top-ranked algorithm achieved a mean DSC of 0.66, FNV of 3.18 mL, and FPV of 2.78 mL across all four test conditions, improving DSC by 8% and reducing the false-negative volume by 5 mL relative to the provided baseline. Ranking was stable across bootstrap resampling and alternative ranking schemes for the top tier. Beyond the benchmark, we provide an in-depth analysis of segmentation performance at the patient and lesion level. Three main conclusions can be drawn: (1) in-domain multitracer PET/CT segmentation is sufficient and probably approaching reader agreement; (2) compositional generalization to unseen tracer-center combinations remains an open problem mainly driven by systematic volume overestimation; (3) heterogeneity and case difficulty drive performance variation substantially more than the choice of algorithm among top-ranked teams.

preprint2026arXiv

TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT

Automated segmentation of liver lesions on non-contrast computed tomography (NCCT) is clinically important but fundamentally challenging, particularly in low-resource settings across Africa and Asia where contrast agents are frequently unavailable. Progress has been limited by the absence of annotated NCCT benchmarks. Here we describe the TriALS challenge for automated liver lesion segmentation under contrast-limited conditions, supported by a multi-centre dataset of 150 cases with four-phase CT acquisitions (600 volumes) from Egyptian and Chinese institutions. Algorithms were evaluated on 70 cases from three institutions, including an independent external cohort. The top-performing method achieved a mean venous-phase Dice of 0.754, consistent with human-level performance, yet dropped to 0.57 on NCCT. On external validation, the leading method outperformed off-the-shelf models by up to 28% in Dice on NCCT. Algorithm performance was most strongly predicted by training data scale and pre-training strategy. A cross-year comparison exposed a persistent perceptual barrier on NCCT that scaling pre-training alone cannot overcome. Data, annotations, and code are available at https://github.com/xmed-lab/TriALS.

preprint2023arXiv

Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions

Occlusions are universal disruptions constantly present in the real world. Especially for sparse representations, such as human skeletons, a few occluded points might destroy the geometrical and temporal continuity critically affecting the results. 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. In this work, we explicitly tackle body occlusions for Skeleton-based One-shot Action Recognition (SOAR). We mainly consider two occlusion variants: 1) random occlusions and 2) more realistic occlusions caused by diverse everyday objects, which we generate by projecting the existing IKEA 3D furniture models into the camera coordinate system of the 3D skeletons with different geometric parameters. We leverage the proposed pipeline to blend out portions of skeleton sequences of the three popular action recognition datasets and formalize the first benchmark for SOAR from partially occluded body poses. Another key property of our benchmark are the more realistic occlusions generated by everyday objects, as even in standard recognition from 3D skeletons, only randomly missing joints were considered. We re-evaluate existing state-of-the-art frameworks for SOAR in the light of this new task and further introduce Trans4SOAR - a new transformer-based model which leverages three data streams and mixed attention fusion mechanism to alleviate the adverse effects caused by occlusions. While our experiments demonstrate a clear decline in accuracy with missing skeleton portions, this effect is smaller with Trans4SOAR, which outperforms other architectures on all datasets. Although we specifically focus on occlusions, Trans4SOAR additionally yields state-of-the-art in the standard SOAR without occlusion, surpassing the best published approach by 2.85% on NTU-120.

preprint2022arXiv

A Comparative Analysis of Decision-Level Fusion for Multimodal Driver Behaviour Understanding

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. Multimodal recognition mitigates a number of such issues: prediction outcomes of different sensors complement each other due to different modality-specific strengths and weaknesses. While several late fusion methods have been considered in previously published frameworks, they constantly feature different architecture backbones and building blocks making it very hard to isolate the role of the chosen late fusion strategy itself. This paper presents an empirical evaluation of different paradigms for decision-level late fusion in video-based driver observation. We compare seven different mechanisms for joining the results of single-modal classifiers which have been both popular, (e.g. score averaging) and not yet considered (e.g. rank-level fusion) in the context of driver observation evaluating them based on different criteria and benchmark settings. This is the first systematic study of strategies for fusing outcomes of multimodal predictors inside the vehicles, conducted with the goal to provide guidance for fusion scheme selection.

preprint2022arXiv

Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation

Panoramic images with their 360-degree directional view encompass exhaustive information about the surrounding space, providing a rich foundation for scene understanding. To unfold this potential in the form of robust panoramic segmentation models, large quantities of expensive, pixel-wise annotations are crucial for success. Such annotations are available, but predominantly for narrow-angle, pinhole-camera images which, off the shelf, serve as sub-optimal resources for training panoramic models. Distortions and the distinct image-feature distribution in 360-degree panoramas impede the transfer from the annotation-rich pinhole domain and therefore come with a big dent in performance. To get around this domain difference and bring together semantic annotations from pinhole- and 360-degree surround-visuals, we propose to learn object deformations and panoramic image distortions in the Deformable Patch Embedding (DPE) and Deformable MLP (DMLP) components which blend into our Transformer for PAnoramic Semantic Segmentation (Trans4PASS) model. Finally, we tie together shared semantics in pinhole- and panoramic feature embeddings by generating multi-scale prototype features and aligning them in our Mutual Prototypical Adaptation (MPA) for unsupervised domain adaptation. On the indoor Stanford2D3D dataset, our Trans4PASS with MPA maintains comparable performance to fully-supervised state-of-the-arts, cutting the need for over 1,400 labeled panoramas. On the outdoor DensePASS dataset, we break state-of-the-art by 14.39% mIoU and set the new bar at 56.38%. Code will be made publicly available at https://github.com/jamycheung/Trans4PASS.

preprint2022arXiv

Continuous Self-Localization on Aerial Images Using Visual and Lidar Sensors

This paper proposes a novel method for geo-tracking, i.e. continuous metric self-localization in outdoor environments by registering a vehicle's sensor information with aerial imagery of an unseen target region. Geo-tracking methods offer the potential to supplant noisy signals from global navigation satellite systems (GNSS) and expensive and hard to maintain prior maps that are typically used for this purpose. The proposed geo-tracking method aligns data from on-board cameras and lidar sensors with geo-registered orthophotos to continuously localize a vehicle. We train a model in a metric learning setting to extract visual features from ground and aerial images. The ground features are projected into a top-down perspective via the lidar points and are matched with the aerial features to determine the relative pose between vehicle and orthophoto. Our method is the first to utilize on-board cameras in an end-to-end differentiable model for metric self-localization on unseen orthophotos. It exhibits strong generalization, is robust to changes in the environment and requires only geo-poses as ground truth. We evaluate our approach on the KITTI-360 dataset and achieve a mean absolute position error (APE) of 0.94m. We further compare with previous approaches on the KITTI odometry dataset and achieve state-of-the-art results on the geo-tracking task.

preprint2022arXiv

Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction

Dimensionality reduction is crucial both for visualization and preprocessing high dimensional data for machine learning. We introduce a novel method based on a hierarchy built on 1-nearest neighbor graphs in the original space which is used to preserve the grouping properties of the data distribution on multiple levels. The core of the proposal is an optimization-free projection that is competitive with the latest versions of t-SNE and UMAP in performance and visualization quality while being an order of magnitude faster in run-time. Furthermore, its interpretable mechanics, the ability to project new data, and the natural separation of data clusters in visualizations make it a general purpose unsupervised dimension reduction technique. In the paper, we argue about the soundness of the proposed method and evaluate it on a diverse collection of datasets with sizes varying from 1K to 11M samples and dimensions from 28 to 16K. We perform comparisons with other state-of-the-art methods on multiple metrics and target dimensions highlighting its efficiency and performance. Code is available at https://github.com/koulakis/h-nne

preprint2022arXiv

Indoor Navigation Assistance for Visually Impaired People via Dynamic SLAM and Panoptic Segmentation with an RGB-D Sensor

Exploring an unfamiliar indoor environment and avoiding obstacles is challenging for visually impaired people. Currently, several approaches achieve the avoidance of static obstacles based on the mapping of indoor scenes. To solve the issue of distinguishing dynamic obstacles, we propose an assistive system with an RGB-D sensor to detect dynamic information of a scene. Once the system captures an image, panoptic segmentation is performed to obtain the prior dynamic object information. With sparse feature points extracted from images and the depth information, poses of the user can be estimated. After the ego-motion estimation, the dynamic object can be identified and tracked. Then, poses and speed of tracked dynamic objects can be estimated, which are passed to the users through acoustic feedback.

preprint2022arXiv

Is my Driver Observation Model Overconfident? Input-guided Calibration Networks for Reliable and Interpretable Confidence Estimates

Driver observation models are rarely deployed under perfect conditions. In practice, illumination, camera placement and type differ from the ones present during training and unforeseen behaviours may occur at any time. While observing the human behind the steering wheel leads to more intuitive human-vehicle-interaction and safer driving, it requires recognition algorithms which do not only predict the correct driver state, but also determine their prediction quality through realistic and interpretable confidence measures. Reliable uncertainty estimates are crucial for building trust and are a serious obstacle for deploying activity recognition networks in real driving systems. 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. To correct this misalignment between the confidence values and the actual uncertainty, we consider two strategies. First, we enhance two activity recognition models often used for driver observation with temperature scaling-an off-the-shelf method for confidence calibration in image classification. Then, we introduce Calibrated Action Recognition with Input Guidance (CARING)-a novel approach leveraging an additional neural network to learn scaling the confidences depending on the video representation. Extensive experiments on the Drive&Act dataset demonstrate that both strategies drastically improve the quality of model confidences, while our CARING model out-performs both, the original architectures and their temperature scaling enhancement, leading to best uncertainty estimates.

preprint2022arXiv

MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

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. While most previous works focus on sparse segmentation of the LiDAR input, dense output masks provide self-driving cars with almost complete environment information. In this paper, we introduce MASS - a Multi-Attentional Semantic Segmentation model specifically built for dense top-view understanding of the driving scenes. Our framework operates on pillar- and occupancy features and comprises three attention-based building blocks: (1) a keypoint-driven graph attention, (2) an LSTM-based attention computed from a vector embedding of the spatial input, and (3) a pillar-based attention, resulting in a dense 360-degree segmentation mask. With extensive experiments on both, SemanticKITTI and nuScenes-LidarSeg, we quantitatively demonstrate the effectiveness of our model, outperforming the state of the art by 19.0% on SemanticKITTI and reaching 30.4% in mIoU on nuScenes-LidarSeg, where MASS is the first work addressing the dense segmentation task. Furthermore, our multi-attention model is shown to be very effective for 3D object detection validated on the KITTI-3D dataset, showcasing its high generalizability to other tasks related to 3D vision.

preprint2022arXiv

Multi-modal Depression Estimation based on Sub-attentional Fusion

Failure to timely diagnose and effectively treat depression leads to over 280 million people suffering from this psychological disorder worldwide. The information cues of depression can be harvested from diverse heterogeneous resources, e.g., audio, visual, and textual data, raising demand for new effective multi-modal fusion approaches for automatic estimation. In this work, we tackle the task of automatically identifying depression from multi-modal data and introduce a sub-attention mechanism for linking heterogeneous information while leveraging Convolutional Bidirectional LSTM as our backbone. To validate this idea, we conduct extensive experiments on the public DAIC-WOZ benchmark for depression assessment featuring different evaluation modes and taking gender-specific biases into account. The proposed model yields effective results with 0.89 precision and 0.70 F1-score in detecting major depression and 4.92 MAE in estimating the severity. Our attention-based fusion module consistently outperforms conventional late fusion approaches and achieves competitive performance compared to the previously published depression estimation frameworks, while learning to diagnose the disorder end-to-end and relying on far fewer preprocessing steps.

preprint2022arXiv

Should I take a walk? Estimating Energy Expenditure from Video Data

We explore the problem of automatically inferring the amount of kilocalories used by human during physical activity from his/her video observation. 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. In practice, a training set would only cover a certain amount of activity types, and it is important to validate, if the model indeed captures the essence of energy expenditure, (e.g., how many and which muscles are involved and how intense they work) instead of memorizing fixed values of specific activity categories seen during training. Ideally, the models should look beyond such category-specific biases and regress the caloric cost in videos depicting activity categories not explicitly present during training. With this property in mind, Vid2Burn is accompanied with a cross-category benchmark, where the task is to regress caloric expenditure for types of physical activities not present during training. An extensive evaluation of state-of-the-art approaches for video recognition modified for the energy expenditure estimation task demonstrates the difficulty of this problem, especially for new activity types at test-time, marking a new research direction. Dataset and code are available at https://github.com/KPeng9510/Vid2Burn.

preprint2022arXiv

Towards Automatic Parsing of Structured Visual Content through the Use of Synthetic Data

Structured Visual Content (SVC) such as graphs, flow charts, or the like are used by authors to illustrate various concepts. While such depictions allow the average reader to better understand the contents, images containing SVCs are typically not machine-readable. This, in turn, not only hinders automated knowledge aggregation, but also the perception of displayed in-formation for visually impaired people. In this work, we propose a synthetic dataset, containing SVCs in the form of images as well as ground truths. We show the usage of this dataset by an application that automatically extracts a graph representation from an SVC image. This is done by training a model via common supervised learning methods. As there currently exist no large-scale public datasets for the detailed analysis of SVC, we propose the Synthetic SVC (SSVC) dataset comprising 12,000 images with respective bounding box annotations and detailed graph representations. Our dataset enables the development of strong models for the interpretation of SVCs while skipping the time-consuming dense data annotation. We evaluate our model on both synthetic and manually annotated data and show the transferability of synthetic to real via various metrics, given the presented application. Here, we evaluate that this proof of concept is possible to some extend and lay down a solid baseline for this task. We discuss the limitations of our approach for further improvements. Our utilized metrics can be used as a tool for future comparisons in this domain. To enable further research on this task, the dataset is publicly available at https://bit.ly/3jN1pJJ

preprint2022arXiv

Towards Robust Semantic Segmentation of Accident Scenes via Multi-Source Mixed Sampling and Meta-Learning

Autonomous vehicles utilize urban scene segmentation to understand the real world like a human and react accordingly. Semantic segmentation of normal scenes has experienced a remarkable rise in accuracy on conventional benchmarks. However, a significant portion of real-life accidents features abnormal scenes, such as those with object deformations, overturns, and unexpected traffic behaviors. Since even small mis-segmentation of driving scenes can lead to serious threats to human lives, the robustness of such models in accident scenarios is an extremely important factor in ensuring safety of intelligent transportation systems. In this paper, we propose a Multi-source Meta-learning Unsupervised Domain Adaptation (MMUDA) framework, to improve the generalization of segmentation transformers to extreme accident scenes. In MMUDA, we make use of Multi-Domain Mixed Sampling to augment the images of multiple-source domains (normal scenes) with the target data appearances (abnormal scenes). To train our model, we intertwine and study a meta-learning strategy in the multi-source setting for robustifying the segmentation results. We further enhance the segmentation backbone (SegFormer) with a HybridASPP decoder design, featuring large window attention spatial pyramid pooling and strip pooling, to efficiently aggregate long-range contextual dependencies. Our approach achieves a mIoU score of 46.97% on the DADA-seg benchmark, surpassing the previous state-of-the-art model by more than 7.50%. Code will be made publicly available at https://github.com/xinyu-laura/MMUDA.

preprint2022arXiv

TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration

Traditional video-based human activity recognition has experienced remarkable progress linked to the rise of deep learning, but this effect was slower as it comes to the downstream task of driver behavior understanding. Understanding the situation inside the vehicle cabin is essential for Advanced Driving Assistant System (ADAS) as it enables identifying distraction, predicting driver's intent and leads to more convenient human-vehicle interaction. At the same time, driver observation systems face substantial obstacles as they need to capture different granularities of driver states, while the complexity of such secondary activities grows with the rising automation and increased driver freedom. Furthermore, a model is rarely deployed under conditions identical to the ones in the training set, as sensor placements and types vary from vehicle to vehicle, constituting a substantial obstacle for real-life deployment of data-driven models. In this work, we present a novel vision-based framework for recognizing secondary driver behaviours based on visual transformers and an additional augmented feature distribution calibration module. 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. Our framework consistently leads to better recognition rates, surpassing previous state-of-the-art results of the public Drive&Act benchmark on all granularity levels. Our code is publicly available at https://github.com/KPeng9510/TransDARC.

preprint2021arXiv

Panoptic Lintention Network: Towards Efficient Navigational Perception for the Visually Impaired

Classic computer vision algorithms, instance segmentation, and semantic segmentation can not provide a holistic understanding of the surroundings for the visually impaired. In this paper, we utilize panoptic segmentation to assist the navigation of visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired efficiently. To this end, we propose an efficient Attention module -- Lintention which can model long-range interactions in linear time using linear space. Based on Lintention, we then devise a novel panoptic segmentation model which we term Panoptic Lintention Net. Experiments on the COCO dataset indicate that the Panoptic Lintention Net raises the Panoptic Quality (PQ) from 39.39 to 41.42 with 4.6\% performance gain while only requiring 10\% fewer GFLOPs and 25\% fewer parameters in the semantic branch. Furthermore, a real-world test via our designed compact wearable panoptic segmentation system, indicates that our system based on the Panoptic Lintention Net accomplishes a relatively stable and exceptionally remarkable panoptic segmentation in real-world scenes.

preprint2021arXiv

Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired

As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks. Building on the compact ResNet backbone, our designed network architecture has two paths with shared parameters. In the structure, the semantic segmentation path integrates fast attention, with the aim of harvesting long-range contextual information in an efficient manner. Simultaneously, the scene recognition path attains the scene type inference by passing the semantic features into semantic-driven attention networks and combining the semantic extracted representations with the RGB extracted representations through a gated attention module. In the experiments, we have verified the systems' accuracy and efficiency on both public datasets and real-world scenes. This system runs on a wearable belt with an Intel RealSense LiDAR camera and an Nvidia Jetson AGX Xavier processor, which can accompany visually impaired people and provide assistive scene information in their navigation tasks.

preprint2021arXiv

Uncertainty-sensitive Activity Recognition: a Reliability Benchmark and the CARING Models

Beyond assigning the correct class, an activity recognition model should also be able to determine, how certain it is in its predictions. We present the first study of how welthe confidence values of modern action recognition architectures indeed reflect the probability of the correct outcome and propose a learning-based approach for improving it. First, we extend two popular action recognition datasets with a reliability benchmark in form of the expected calibration error and reliability diagrams. Since our evaluation highlights that confidence values of standard action recognition architectures do not represent the uncertainty well, we introduce a new approach which learns to transform the model output into realistic confidence estimates through an additional calibration network. The main idea of our Calibrated Action Recognition with Input Guidance (CARING) model is to learn an optimal scaling parameter depending on the video representation. We compare our model with the native action recognition networks and the temperature scaling approach - a wide spread calibration method utilized in image classification. 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.

preprint2020arXiv

Anchor-free Small-scale Multispectral Pedestrian Detection

Multispectral images consisting of aligned visual-optical (VIS) and thermal infrared (IR) image pairs are well-suited for practical applications like autonomous driving or visual surveillance. Such data can be used to increase the performance of pedestrian detection especially for weakly illuminated, small-scaled, or partially occluded instances. The current state-of-the-art is based on variants of Faster R-CNN and thus passes through two stages: a proposal generator network with handcrafted anchor boxes for object localization and a classification network for verifying the object category. In this paper we propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. 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. In addition, we provide a study on well-suited multispectral data augmentation techniques that improve the commonly used augmentations. The results show our method's effectiveness in detecting small-scaled pedestrians. We achieve 5.68% log-average miss rate in comparison to the best current state-of-the-art of 7.49% (25% improvement) on the challenging KAIST Multispectral Pedestrian Detection Benchmark. Code: https://github.com/HensoldtOptronicsCV/MultispectralPedestrianDetection

preprint2020arXiv

Can we cover navigational perception needs of the visually impaired by panoptic segmentation?

Navigational perception for visually impaired people has been substantially promoted by both classic and deep learning based segmentation methods. In classic visual recognition methods, the segmentation models are mostly object-dependent, which means a specific algorithm has to be devised for the object of interest. In contrast, deep learning based models such as instance segmentation and semantic segmentation allow to individually recognize part of the entire scene, namely things or stuff, for blind individuals. However, both of them can not provide a holistic understanding of the surroundings for the visually impaired. Panoptic segmentation is a newly proposed visual model with the aim of unifying semantic segmentation and instance segmentation. Motivated by that, we propose to utilize panoptic segmentation as an approach to navigating visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired. We demonstrate that panoptic segmentation is able to equip the visually impaired with a holistic real-world scene perception through a wearable assistive system.

preprint2020arXiv

Clustering based Contrastive Learning for Improving Face Representations

A good clustering algorithm can discover natural groupings in data. These groupings, if used wisely, provide a form of weak supervision for learning representations. In this work, we present Clustering-based Contrastive Learning (CCL), a new clustering-based representation learning approach that uses labels obtained from clustering along with video constraints to learn discriminative face features. We demonstrate our method on the challenging task of learning representations for video face clustering. Through several ablation studies, we analyze the impact of creating pair-wise positive and negative labels from different sources. Experiments on three challenging video face clustering datasets: BBT-0101, BF-0502, and ACCIO show that CCL achieves a new state-of-the-art on all datasets.

preprint2020arXiv

Deep Multimodal Feature Encoding for Video Ordering

True understanding of videos comes from a joint analysis of all its modalities: the video frames, the audio track, and any accompanying text such as closed captions. We present a way to learn a compact multimodal feature representation that encodes all these modalities. Our model parameters are learned through a proxy task of inferring the temporal ordering of a set of unordered videos in a timeline. To this end, we create a new multimodal dataset for temporal ordering that consists of approximately 30K scenes (2-6 clips per scene) based on the "Large Scale Movie Description Challenge". We analyze and evaluate the individual and joint modalities on three challenging tasks: (i) inferring the temporal ordering of a set of videos; and (ii) action recognition. We demonstrate empirically that multimodal representations are indeed complementary, and can play a key role in improving the performance of many applications.

preprint2020arXiv

Detective: An Attentive Recurrent Model for Sparse Object Detection

In this work, we present Detective - an attentive object detector that identifies objects in images in a sequential manner. Our network is based on an encoder-decoder architecture, where the encoder is a convolutional neural network, and the decoder is a convolutional recurrent neural network coupled with an attention mechanism. At each iteration, our decoder focuses on the relevant parts of the image using an attention mechanism, and then estimates the object's class and the bounding box coordinates. Current object detection models generate dense predictions and rely on post-processing to remove duplicate predictions. Detective is a sparse object detector that generates a single bounding box per object instance. However, training a sparse object detector is challenging, as it requires the model to reason at the instance level and not just at the class and spatial levels. We propose a training mechanism based on the Hungarian algorithm and a loss that balances the localization and classification tasks. This allows Detective to achieve promising results on the PASCAL VOC object detection dataset. Our experiments demonstrate that sparse object detection is possible and has a great potential for future developments in applications where the order of the objects to be predicted is of interest.

preprint2020arXiv

DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing

Semantically interpreting the traffic scene is crucial for autonomous transportation and robotics systems. However, state-of-the-art semantic segmentation pipelines are dominantly designed to work with pinhole cameras and train with narrow Field-of-View (FoV) images. In this sense, the perception capacity is severely limited to offer higher-level confidence for upstream navigation tasks. In this paper, we propose a network adaptation framework to achieve Panoramic Annular Semantic Segmentation (PASS), which allows to re-use conventional pinhole-view image datasets, enabling modern segmentation networks to comfortably adapt to panoramic images. Specifically, we adapt our proposed SwaftNet to enhance the sensitivity to details by implementing attention-based lateral connections between the detail-critical encoder layers and the context-critical decoder layers. We benchmark the performance of efficient segmenters on panoramic segmentation with our extended PASS dataset, demonstrating that the proposed real-time SwaftNet outperforms state-of-the-art efficient networks. Furthermore, we assess real-world performance when deploying the Detail-Sensitive PASS (DS-PASS) system on a mobile robot and an instrumented vehicle, as well as the benefit of panoramic semantics for visual odometry, showing the robustness and potential to support diverse navigational applications.

preprint2020arXiv

Fashion Forward: Forecasting Visual Style in Fashion

What is the future of fashion? Tackling this question from a data-driven vision perspective, we propose to forecast visual style trends before they occur. We introduce the first approach to predict the future popularity of styles discovered from fashion images in an unsupervised manner. Using these styles as a basis, we train a forecasting model to represent their trends over time. The resulting model can hypothesize new mixtures of styles that will become popular in the future, discover style dynamics (trendy vs. classic), and name the key visual attributes that will dominate tomorrow's fashion. We demonstrate our idea applied to three datasets encapsulating 80,000 fashion products sold across six years on Amazon. Results indicate that fashion forecasting benefits greatly from visual analysis, much more than textual or meta-data cues surrounding products.

preprint2020arXiv

Unsupervised Domain Adaptation by Uncertain Feature Alignment

Unsupervised domain adaptation (UDA) deals with the adaptation of models from a given source domain with labeled data to an unlabeled target domain. In this paper, we utilize the inherent prediction uncertainty of a model to accomplish the domain adaptation task. The uncertainty is measured by Monte-Carlo dropout and used for our proposed Uncertainty-based Filtering and Feature Alignment (UFAL) that combines an Uncertain Feature Loss (UFL) function and an Uncertainty-Based Filtering (UBF) approach for alignment of features in Euclidean space. Our method surpasses recently proposed architectures and achieves state-of-the-art results on multiple challenging datasets. Code is available on the project website.

preprint2016arXiv

Deep Perceptual Mapping for Cross-Modal Face Recognition

Cross modal face matching between the thermal and visible spectrum is a much desired capability for night-time surveillance and security applications. Due to a very large modality gap, thermal-to-visible face recognition is one of the most challenging face matching problem. In this paper, we present an approach to bridge this modality gap by a significant margin. Our approach captures the highly non-linear relationship between the two modalities by using a deep neural network. Our model attempts to learn a non-linear mapping from visible to thermal spectrum while preserving the identity information. We show substantive performance improvement on three difficult thermal-visible face datasets. The presented approach improves the state-of-the-art by more than 10\% on UND-X1 dataset and by more than 15-30\% on NVESD dataset in terms of Rank-1 identification. Our method bridges the drop in performance due to the modality gap by more than 40\%.

preprint2016arXiv

Exact Maximum Entropy Inverse Optimal Control for Modelling Human Attention Switching and Control

Maximum Causal Entropy (MCE) Inverse Optimal Control (IOC) has become an effective tool for modelling human behaviour in many control tasks. Its advantage over classic techniques for estimating human policies is the transferability of the inferred objectives: Behaviour can be predicted in variations of the control task by policy computation using a relaxed optimality criterion. However, exact policy inference is often computationally intractable in control problems with imperfect state observation. In this work, we present a model class that allows modelling human control of two tasks of which only one be perfectly observed at a time requiring attention switching. We show how efficient and exact objective and policy inference via MCE can be conducted for these control problems. Both MCE-IOC and Maximum Causal Likelihood (MCL)-IOC, a variant of the original MCE approach, as well as Direct Policy Estimation (DPE) are evaluated using simulated and real behavioural data. Prediction error and generalization over changes in the control process are both considered in the evaluation. The results show a clear advantage of both IOC methods over DPE, especially in the transfer over variation of the control process. MCE and MCL performed similar when training on a large set of simulated data, but differed significantly on small sets and real data.

preprint2016arXiv

How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes

Attribute based knowledge transfer has proven very successful in visual object analysis and learning previously unseen classes. However, the common approach learns and transfers attributes without taking into consideration the embedded structure between the categories in the source set. Such information provides important cues on the intra-attribute variations. We propose to capture these variations in a hierarchical model that expands the knowledge source with additional abstraction levels of attributes. We also provide a novel transfer approach that can choose the appropriate attributes to be shared with an unseen class. We evaluate our approach on three public datasets: aPascal, Animals with Attributes and CUB-200-2011 Birds. The experiments demonstrate the effectiveness of our model with significant improvement over state-of-the-art.

preprint2016arXiv

MovieQA: Understanding Stories in Movies through Question-Answering

We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both video and text. The dataset consists of 14,944 questions about 408 movies with high semantic diversity. The questions range from simpler "Who" did "What" to "Whom", to "Why" and "How" certain events occurred. Each question comes with a set of five possible answers; a correct one and four deceiving answers provided by human annotators. Our dataset is unique in that it contains multiple sources of information -- video clips, plots, subtitles, scripts, and DVS. We analyze our data through various statistics and methods. We further extend existing QA techniques to show that question-answering with such open-ended semantics is hard. We make this data set public along with an evaluation benchmark to encourage inspiring work in this challenging domain.

preprint2016arXiv

Predicting Lane Keeping Behavior of Visually Distracted Drivers Using Inverse Suboptimal Control

Driver distraction strongly contributes to crash-risk. Therefore, assistance systems that warn the driver if her distraction poses a hazard to road safety, promise a great safety benefit. Current approaches either seek to detect critical situations using environmental sensors or estimate a driver's attention state solely from her behavior. However, this neglects that driving situation, driver deficiencies and compensation strategies altogether determine the risk of an accident. This work proposes to use inverse suboptimal control to predict these aspects in visually distracted lane keeping. In contrast to other approaches, this allows a situation-dependent assessment of the risk posed by distraction. Real traffic data of seven drivers are used for evaluation of the predictive power of our approach. For comparison, a baseline was built using established behavior models. In the evaluation our method achieves a consistently lower prediction error over speed and track-topology variations. Additionally, our approach generalizes better to driving speeds unseen in training phase.

preprint2016arXiv

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based methods require a full description of attribute associations for each unseen class. Providing these associations is time consuming and often requires domain specific knowledge. In this work, we aim to carry out attribute-based zero-shot classification in an unsupervised manner. We propose an approach to learn relations that couples class embeddings with their corresponding attributes. Given only the name of an unseen class, the learned relationship model is used to automatically predict the class-attribute associations. Furthermore, our model facilitates transferring attributes across data sets without additional effort. Integrating knowledge from multiple sources results in a significant additional improvement in performance. We evaluate on two public data sets: Animals with Attributes and aPascal/aYahoo. Our approach outperforms state-of-the-art methods in both predicting class-attribute associations and unsupervised ZSL by a large margin.

preprint2016arXiv

Relaxed Earth Mover's Distances for Chain- and Tree-connected Spaces and their use as a Loss Function in Deep Learning

The Earth Mover's Distance (EMD) computes the optimal cost of transforming one distribution into another, given a known transport metric between them. In deep learning, the EMD loss allows us to embed information during training about the output space structure like hierarchical or semantic relations. This helps in achieving better output smoothness and generalization. However EMD is computationally expensive.Moreover, solving EMD optimization problems usually require complex techniques like lasso. These properties limit the applicability of EMD-based approaches in large scale machine learning. We address in this work the difficulties facing incorporation of EMD-based loss in deep learning frameworks. Additionally, we provide insight and novel solutions on how to integrate such loss function in training deep neural networks. Specifically, we make three main contributions: (i) we provide an in-depth analysis of the fastest state-of-the-art EMD algorithm (Sinkhorn Distance) and discuss its limitations in deep learning scenarios. (ii) we derive fast and numerically stable closed-form solutions for the EMD gradient in output spaces with chain- and tree- connectivity; and (iii) we propose a relaxed form of the EMD gradient with equivalent computational complexity but faster convergence rate. We support our claims with experiments on real datasets. In a restricted data setting on the ImageNet dataset, we train a model to classify 1000 categories using 50K images, and demonstrate that our relaxed EMD loss achieves better Top-1 accuracy than the cross entropy loss. Overall, we show that our relaxed EMD loss criterion is a powerful asset for deep learning in the small data regime.

preprint2015arXiv

Deep Perceptual Mapping for Thermal to Visible Face Recognition

Cross modal face matching between the thermal and visible spectrum is a much de- sired capability for night-time surveillance and security applications. Due to a very large modality gap, thermal-to-visible face recognition is one of the most challenging face matching problem. In this paper, we present an approach to bridge this modality gap by a significant margin. Our approach captures the highly non-linear relationship be- tween the two modalities by using a deep neural network. Our model attempts to learn a non-linear mapping from visible to thermal spectrum while preserving the identity in- formation. We show substantive performance improvement on a difficult thermal-visible face dataset. The presented approach improves the state-of-the-art by more than 10% in terms of Rank-1 identification and bridge the drop in performance due to the modality gap by more than 40%.

preprint2015arXiv

On the Distribution of Salient Objects in Web Images and its Influence on Salient Object Detection

It has become apparent that a Gaussian center bias can serve as an important prior for visual saliency detection, which has been demonstrated for predicting human eye fixations and salient object detection. Tseng et al. have shown that the photographer's tendency to place interesting objects in the center is a likely cause for the center bias of eye fixations. We investigate the influence of the photographer's center bias on salient object detection, extending our previous work. We show that the centroid locations of salient objects in photographs of Achanta and Liu's data set in fact correlate strongly with a Gaussian model. This is an important insight, because it provides an empirical motivation and justification for the integration of such a center bias in salient object detection algorithms and helps to understand why Gaussian models are so effective. To assess the influence of the center bias on salient object detection, we integrate an explicit Gaussian center bias model into two state-of-the-art salient object detection algorithms. This way, first, we quantify the influence of the Gaussian center bias on pixel- and segment-based salient object detection. Second, we improve the performance in terms of F1 score, Fb score, area under the recall-precision curve, area under the receiver operating characteristic curve, and hit-rate on the well-known data set by Achanta and Liu. Third, by debiasing Cheng et al.'s region contrast model, we exemplarily demonstrate that implicit center biases are partially responsible for the outstanding performance of state-of-the-art algorithms. Last but not least, as a result of debiasing Cheng et al.'s algorithm, we introduce a non-biased salient object detection method, which is of interest for applications in which the image data is not likely to have a photographer's center bias (e.g., image data of surveillance cameras or autonomous robots).

preprint2015arXiv

What's the point? Frame-wise Pointing Gesture Recognition with Latent-Dynamic Conditional Random Fields

We use Latent-Dynamic Conditional Random Fields to perform skeleton-based pointing gesture classification at each time instance of a video sequence, where we achieve a frame-wise pointing accuracy of roughly 83%. Subsequently, we determine continuous time sequences of arbitrary length that form individual pointing gestures and this way reliably detect pointing gestures at a false positive detection rate of 0.63%.

Institution

Affiliation not imported yet

This author record came from a source that does not expose affiliation metadata. Once the author claims the profile or we enrich the record from another provider, this section will link to the concrete institution.

Topic footprint

Fields this researcher appears in

Source provenance