The paper introduces a one-stage end-to-end model for wildlife instance-level recognition that integrates detection and re-identification within a single latent space. It leverages DINOv2 for spatial geometry and MegaDescriptor for re-identification, while enhancing latent queries with prompt re-identification features. Preliminary results show a competitive mean average precision of 30.584% compared to the state-of-the-art two-stage approach of 44.89%, with qualitative evidence of effective bounding and identification of animal identities.
arXiv:2603.04163v2 Announce Type: replace Abstract: Wildlife re-identification aims to recognise individual animals by matching query images to a database of previously identified individuals, based...
The study investigates whether Vision Transformer (ViT)-based animal re-identification models learn biologically meaningful concepts. Using a DINOv3 backbone fine‑tuned on Western lowland gorilla images, the authors find that sex and age emerge as linear directions in the model’s representations, generalizing to unseen individuals with high AUROC scores. They demonstrate that the sex direction is causally used by the model, that fine‑tuning relocates these concepts within the network, and that the representations reflect a graded biological axis encoded redundantly across the population.
arXiv:2609.09705v1 Announce Type: new Abstract: Generalizable animal Re-Identification (ReID) aims to recognize individual animals across species with diverse morphologies and ecological contexts. Un...
arXiv:2607. 09443v1 Announce Type: cross Abstract: Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts.
Animal pose estimation and tracking is important for wildlife monitoring and conservation research, and with limited expert time for labelling automated approaches are imperative. While human pose estimation and tracking has seen rapid progress thanks to large annotated datasets, animal pose remain challenging, due to large morphological and behavioural differences between species and limited annotated data.
arXiv:2512.07776v2 Announce Type: replace Abstract: Monitoring critically endangered western lowland gorillas is currently hampered by the immense manual effort required to re-identify individuals fr...
The paper presents MaxBoxCount, the winning solution to the iWildCam 2021 Challenge, which tackles counting animals in camera‑trap image sequences without using count labels. It combines a robust species classification pipeline with a counting heuristic based on MegaDetector detections to estimate the number of unique individuals across short image bursts. The method addresses challenges posed by temporal discontinuities and the high cost of manual count annotations.
PuTR-CouT is a transformer‑based counting‑by‑tracking framework designed for camera‑trap image sequences. It generates synthetic training data using structural priors to create pseudo‑tracking labels, enabling the tracker to associate detections across frames and estimate per‑species counts. The method improves upon the MaxBoxCount baseline on the iWildCam 2021 benchmark, offering competitive counting results along with multi‑species predictions and track‑level verification.
Det‑LIME is a detector‑aware, multi‑instance adaptation of LIME designed to explain black‑box object detectors used in marine mammal research. It generates instance‑specific, box‑aligned explanations by weighting detections, applying a proximity kernel, and using IoU‑based matching to track instances across perturbations. Evaluated on aerial drone imagery of harbor seals and a seabird case study, Det‑LIME outperformed vanilla LIME, Stabilized LIME, Deterministic LIME, and gradient‑based methods in Attribution Ratio and Max Saliency Hit Rate, offering higher‑resolution, instance‑aware explanations that aid debugging, data augmentation, and modeling improvements.
arXiv:2607. 17157v1 Announce Type: cross Abstract: Multi-object tracking (MOT) aims to localize multiple objects in videos while preserving their identities over time.
arXiv:2607. 09876v1 Announce Type: cross Abstract: Automatically retrieving videos from large camera-trap datasets remains challenging.
GrabVG is a visual grounding framework for UAV imagery that tackles the challenges of small, densely packed, and visually similar objects. It splits the task into preattentive hypothesis search and graph‑attentive feature binding, using distillation‑guided proposals and a sparse graph to capture intra‑ and inter‑instance relationships. Experiments on AerialVG and AerialSense show that GrabVG achieves higher accuracy and speed, outperforming baselines by significant margins.