3 papers
q-bio.PE2026
Centering Ecological Goals in Automated Identification of Individual Animals
Lukas Picek, Timm Haucke, Lukáš Adam +16
Recognizing individual animals over time is central to many ecological and conservation questions, including estimating abundance, survival, movement, and social structure. Recent…
cs.CV2026
Degradation-based augmented training for robust individual animal re-identification
Thanos Polychronou, Lukáš Adam, Viktor Penchev +1
Wildlife re-identification aims to recognise individual animals by matching query images to a database of previously identified individuals, based on their fine-scale unique morpho…
cs.CV2024
WildFusion: Individual Animal Identification with Calibrated Similarity Fusion
VojtÄch Cermak, Lukas Picek, Lukáš Adam +2
We propose a new method - WildFusion - for individual identification of a broad range of animal species. The method fuses deep scores (e.g., MegaDescriptor or DINOv2) and local mat…