2k citations
- Ghent UniversityBE28 papers
- KU LeuvenBE27 papers
- University of AntwerpBE17 papers
- Universitat Politècnica de CatalunyaES4 papers
- Vrije Universiteit BrusselBE4 papers
- Centre National de la Recherche ScientifiqueFR3 papers
- Ghent University HospitalBE3 papers
- Hasselt UniversityBE3 papers
- Politecnico di TorinoIT3 papers
- Sapienza University of RomeIT3 papers
- University College LondonGB3 papers
- University of AmsterdamNL3 papers
14 papers · 1 filter
In-Field Mapping of Grape Yield and Quality with Illumination-Invariant Deep Learning
Ciem Cornelissen, Sander De Coninck, Axel Willekens +2
This paper presents an end-to-end, IoT-enabled robotic system for the non-destructive, real-time, and spatially-resolved mapping of grape yield and quality (Brix, Acidity) in viney…
Who's that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images
Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars
In this work, we aim at automatically labeling actors in a TV series. Rather than relying on transcripts and subtitles, as has been demonstrated in the past, we show how to achieve…
Multi-modal dictionary learning for image separation with application in art investigation
Nikos Deligiannis, Joao F. C. Mota, Bruno Cornelis +2
In support of art investigation, we propose a new source separation method that unmixes a single X-ray scan acquired from double-sided paintings. In this problem, the X-ray signals…
Cross-modal Supervision for Learning Active Speaker Detection in Video
Punarjay Chakravarty, Tinne Tuytelaars
In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based class…
Lightweight Unsupervised Domain Adaptation by Convolutional Filter Reconstruction
Rahaf Aljundi, Tinne Tuytelaars
End-to-end learning methods have achieved impressive results in many areas of computer vision. At the same time, these methods still suffer from a degradation in performance when t…
Rank Pooling for Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas +2
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We sh…