Norbert Oswald
YOU?
Author Swipe
ViewSparsifier: Killing Redundancy in Multi-View Plant Phenotyping Open
Plant phenotyping involves analyzing observable characteristics of plants to better understand their growth, health, and development. In the context of deep learning, this analysis is often approached through single-view classification or …
View article: synth-dacl: Does Synthetic Defect Data Enhance Segmentation Accuracy and Robustness for Real-World Bridge Inspections?
synth-dacl: Does Synthetic Defect Data Enhance Segmentation Accuracy and Robustness for Real-World Bridge Inspections? Open
Adequate bridge inspection is increasingly challenging in many countries due to growing ailing stocks, compounded with a lack of staff and financial resources. Automating the key task of visual bridge inspection, classification of defects …
NeRFtrinsic Four: An end-to-end trainable NeRF jointly optimizing diverse intrinsic and extrinsic camera parameters Open
Novel view synthesis using neural radiance fields (NeRF) is the state-of-the-art technique for generating high- quality images from novel viewpoints. Existing methods require a priori knowledge about extrinsic and intrinsic camera paramete…
View article: SoccerNet 2024 Challenges Results
SoccerNet 2024 Challenges Results Open
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding,…
dacl1k: Real-world bridge damage dataset putting open-source data to the test Open
Recognising reinforced concrete defects (RCDs) is a crucial element for determining the structural integrity, traffic safety and durability of bridges. However, most of the existing datasets in the RCD domain are derived from a small numbe…
Unimodal Multi-Task Fusion for Emotional Mimicry Intensity Prediction Open
In this research, we introduce a novel methodology for assessing Emotional Mimicry Intensity (EMI) as part of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild. Our methodology utilises the Wav2Vec 2.0 architectur…
Enhancing Conceptual Understanding in Multimodal Contrastive Learning through Hard Negative Samples Open
Current multimodal models leveraging contrastive learning often face limitations in developing fine-grained conceptual understanding. This is due to random negative samples during pretraining, causing almost exclusively very dissimilar con…
View article: SoccerNet 2023 Challenges Results
SoccerNet 2023 Challenges Results Open
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first th…
dacl1k: Real-World Bridge Damage Dataset Putting Open-Source Data to the Test Open
Recognising reinforced concrete defects (RCDs) is a crucial element for determining the structural integrity, traffic safety and durability of bridges. However, most of the existing datasets in the RCD domain are derived from a small numbe…
Orientation-Guided Contrastive Learning for UAV-View Geo-Localisation Open
Retrieving relevant multimedia content is one of the main problems in a world that is increasingly data-driven. With the proliferation of drones, high quality aerial footage is now available to a wide audience for the first time. Integrati…
Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation Open
Cross-View Geo-Localisation is still a challenging task where additional modules, specific pre-processing or zooming strategies are necessary to determine accurate positions of images. Since different views have different geometries, pre-p…
NeRFtrinsic Four: An End-To-End Trainable NeRF Jointly Optimizing Diverse Intrinsic and Extrinsic Camera Parameters Open
Novel view synthesis using neural radiance fields (NeRF) is the state-of-the-art technique for generating high-quality images from novel viewpoints. Existing methods require a priori knowledge about extrinsic and intrinsic camera parameter…
CLIP-ReIdent: Contrastive Training for Player Re-Identification Open
Sports analytics benefits from recent advances in machine learning providing\na competitive advantage for teams or individuals. One important task in this\ncontext is the performance measurement of individual players to provide reports\nan…
Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model Open
Current architectures for multi-modality tasks such as visual question answering suffer from their high complexity. As a result, these architectures are difficult to train and require high computational resources. To address these problems…
Building Inspection Toolkit: Unified Evaluation and Strong Baselines for Damage Recognition Open
In recent years, several companies and researchers have started to tackle the problem of damage recognition within the scope of automated inspection of built structures. While companies are neither willing to publish associated data nor mo…