-
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ...
Omnidirectional depth perception is essential for mobile robotics applications that require scene understanding across a full 360° field of view. Camera-based setups offer a... -
Content-Adaptive Downsampling in Convolutional Neural Networks
Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost.... -
NLPEERv2: A Unified Resource for the Computational Study of Peer Review
Dataset of peer review reports and paper drafts from diverse domains and venues. It extends the previous dataset NLPEER to version 2. We provide all sub-versions of the dataset... -
Semantic Self-adaptation: Enhancing Generalization with a Single Sample
The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e.,... -
ARR Data Collection Initiative 2024
Dataset of peer review reports, meta-reviews, reviewer-author discussions, and paper drafts collected from ACL Rolling Review within the context of the new data collection... -
Benchmarking the Attribution Quality of Vision Models
Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how... -
Scene-Centric Unsupervised Panoptic Segmentation
Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In... -
Measurement series of smartphone experiments for recognizing AR markers in th...
In December 2024, experiments were carried out in the Mont Terri underground laboratory in Switzerland as part of the Master's thesis by Ole Woock. The experiments aimed to... -
NLPEER: A Unified Resource for the Computational Study of Peer Review
Dataset of peer review reports and paper drafts from diverse domains and venues. We provide multiple versions of the dataset; when in doubt, download the newest version. You can... -
Real-world misleading visualizations QA dataset
The real-world misleading visualization QA dataset accompanies the paper "'Protecting multimodal large language models againts misleading visualizations". The dataset contains... -
Geovisuelle Ansätze zur Analyse von Raum-Zeit-Zusammenhängen in urbanen Anwen...
Bei diesem Datensatz handelt es sich um die ergänzenden, qualitativen und quantitativen Forschungsdaten der Dissertation „Geovisuelle Ansätze zur Analyse von... -
Attribute or Abstain: Large Language Models as Long Document Assistants
This folder contains data to run experiments on LAB, the Long document Attribution Benchmark introduced in "Attribute or Abstain: Large Language Models as Long Document... -
Podoportation - dataset
Data recorded during the experiment. For additional information see the readme file within. -
DensingQueen - dataset
Dataset of the paper "DensingQueen: Exploration Methods for Spatial Dense Dynamic Data". For more information see the readme file. -
A Qualitative Investigation of User Transitions and Frictions in Cross-Realit...
transcripts of the audio from the recordings of users interacting with the cross reality apparatus. With added transition indicators. For more details see readme file -
LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversaria...
In this paper, we propose LiOn-XA, an unsupervised domain adaptation (UDA) approach that combines LiDAR-Only Cross-Modal (X) learning with Adversarial training for 3D LiDAR... -
Systematic Task Exploration with LLMs: A Study in Citation Text Generation
The components of this dataset are used in the experiments of the paper "Systematic Task Exploration with LLMs: A Study in Citation Text Generation" published at main conference... -
Are Large Language Models Good Classifiers? A Study on Edit Intent Classifica...
Re3-Sci2.0, a new large-scale dataset of 1,780 scientific document revisions with over 94k labeled edits intent. This dataset is a supplement to the EMNLP24 paper: Are Large... -
Few-Shot-150T (FS150T) Corpus
The Few-Shot-150T Corpus includes 21,600 sentences over 150 controversial topics. Each sentence was annotated via crowdsourcing as either a supporting argument, an attacking... -
The Lou Dataset - Exploring the Impact of Gender-Fair Language in German Text...
The Lou dataset provides gender-fair reformulations for instances from seven German classification tasks. It is intended for non-commercial use, and research is licensed under...
