arXiv:2610.07384v1 Announce Type: cross Abstract: Individual animal re-identification from camera-trap imagery is an instance retrieval problem central to non-invasive wildlife monitoring: a query im...
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.
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.
arXiv:2607. 02269v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG).
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 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.
VastMAT is a large‑scale multi‑animal tracking benchmark featuring 2,947 videos, 337 animal categories, and over 3.6 million bounding boxes with 22,883 identity trajectories. It emphasizes high‑quality, expert‑reviewed annotations and introduces Seen‑category and Unseen‑category evaluation protocols, revealing significant challenges in tracking unseen animals. The authors also propose a lightweight Center‑Distance‑Augmented Association module that boosts HOTA scores for existing MOT methods without extra training.
arXiv:2607. 09443v1 Announce Type: cross Abstract: Long-term animal re-identification (ReID) must remain robust to gradual morphological evolution and seasonal appearance shifts.
The paper introduces MetaWild, a multimodal animal re-identification dataset that pairs 20,890 images from six species with environmental metadata such as temperature and circadian rhythms. It also proposes the Meta-Feature Adapter (MFA), a lightweight module that integrates this metadata into vision-language models for re-identification tasks. Experiments demonstrate that adding MFA consistently improves re-identification performance over visual-only baselines.
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:2603. 24016v2 Announce Type: replace-cross Abstract: Multi-Object Tracking (MOT) has traditionally focused on a few specific categories, restricting its applicability to real-world scenarios involving diverse objects.
MS2CAST is a semi‑supervised video anomaly detection framework that fuses multi‑scale cross‑attention between a vision transformer (MViTv2‑S) and a CNN (ConvNeXt‑T) for spatial encoding, and replaces optical flow with two interchangeable spatiotemporal modules—SwinLSTM and VMRNN—operating in latent space. The training objective combines L1 loss, Gradient Difference Loss, and Multi‑Scale SSIM to enforce pixel‑level accuracy, sharpness, and structural fidelity. Experiments on UCSD Ped2, CUHK Avenue, and ShanghaiTech show competitive ROC‑AUC scores while using less than 1 GB of GPU memory.