PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild

• URL: http://arxiv.org/abs/2511.09675v2
• Date: Sat, 15 Nov 2025 09:24:28 GMT
• Title: PriVi: Towards A General-Purpose Video Model For Primate Behavior In The Wild
• Authors: Felix B. Mueller, Jan F. Meier, Timo Lueddecke, Richard Vogg, Roger L. Freixanet, Valentin Hassler, Tiffany Bosshard, Elif Karakoc, William J. O'Hearn, Sofia M. Pereira, Sandro Sehner, Kaja Wierucka, Judith Burkart, Claudia Fichtel, Julia Fischer, Alexander Gail, Catherine Hobaiter, Julia Ostner, Liran Samuni, Oliver Schülke, Neda Shahidi, Erin G. Wessling, Alexander S. Ecker,
• Abstract summary: We introduce PriVi, a large-scale primate-centric video pretraining dataset.<n>We pretrain V-JEPA, a large-scale video model, on PriVi to learn primate-specific representations.<n>Results demonstrate that primate-centric pretraining substantially improves data efficiency and generalization.
• Score: 50.656578456979496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Non-human primates are our closest living relatives, and analyzing their behavior is central to research in cognition, evolution, and conservation. Computer vision could greatly aid this research, but existing methods often rely on human-centric pretrained models and focus on single datasets, which limits generalization. We address this limitation by shifting from a model-centric to a data-centric approach and introduce PriVi, a large-scale primate-centric video pretraining dataset. PriVi contains 424 hours of curated video, combining 174 hours from behavioral research across 11 settings with 250 hours of diverse web-sourced footage, assembled through a scalable data curation pipeline. We pretrain V-JEPA, a large-scale video model, on PriVi to learn primate-specific representations and evaluate it using a lightweight frozen classifier. Across four benchmark datasets, ChimpACT, BaboonLand, PanAf500, and ChimpBehave, our approach consistently outperforms prior work, including fully finetuned baselines, and scales favorably with fewer labels. These results demonstrate that primate-centric pretraining substantially improves data efficiency and generalization, making it a promising approach for low-label applications. Code, models, and the majority of the dataset will be made available.

Related papers

• Silhouette-based Gait Foundation Model [56.27974816297294]
  Building a unified gait foundation model requires addressing two longstanding barriers: Scalability and Generalization.<n>We introduce FoundationGait, the first scalable, self-supervised pretraining framework for gait understanding.
  arXiv  Detail & Related papers  (2025-11-30T01:53:41Z)
• Domain-Adaptive Pretraining Improves Primate Behavior Recognition [43.65707056647872]
  We show that we can utilize self-supervised learning to considerably improve action recognition on primate behavior.<n>On two datasets of great ape behavior (PanAf and ChimpACT), we outperform published state-of-the-art action recognition models by 6.1 %pt. accuracy and 6.3 %pt. mAP, respectively.
  arXiv  Detail & Related papers  (2025-09-15T17:54:20Z)
• Towards Adaptive Human-centric Video Anomaly Detection: A Comprehensive Framework and A New Benchmark [2.473948454680334]
  Human-centric Video Anomaly Detection (VAD) aims to identify human behaviors that deviate from normal.<n>We introduce the HuVAD (Human-centric privacy-enhanced Video Anomaly Detection) dataset and a novel Unsupervised Continual Anomaly Learning framework.
  arXiv  Detail & Related papers  (2024-08-26T14:55:23Z)
• From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave [0.0]
  We introduce ChimpBehave, a novel dataset featuring over 2 hours of video (approximately 193,000 video frames) of zoo-housed chimpanzees. ChimpBehave meticulously annotated with bounding boxes and behavior labels for action recognition. We benchmark our dataset using a state-of-the-art CNN-based action recognition model.
  arXiv  Detail & Related papers  (2024-05-30T13:11:08Z)
• Learning Human Action Recognition Representations Without Real Humans [66.61527869763819]
  We present a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model. We then evaluate the transferability of the representation learned on this data to a diverse set of downstream action recognition benchmarks. Our approach outperforms previous baselines by up to 5%.
  arXiv  Detail & Related papers  (2023-11-10T18:38:14Z)
• CVB: A Video Dataset of Cattle Visual Behaviors [13.233877352490923]
  Existing datasets for cattle behavior recognition are mostly small, lack well-defined labels, or are collected in unrealistic controlled environments. We introduce a new dataset, called Cattle Visual Behaviors (CVB), that consists of 502 video clips, each fifteen seconds long, captured in natural lighting conditions, and annotated with eleven visually perceptible behaviors of grazing cattle.
  arXiv  Detail & Related papers  (2023-05-26T00:44:11Z)
• Revisiting Classifier: Transferring Vision-Language Models for Video Recognition [102.93524173258487]
  Transferring knowledge from task-agnostic pre-trained deep models for downstream tasks is an important topic in computer vision research. In this study, we focus on transferring knowledge for video classification tasks. We utilize the well-pretrained language model to generate good semantic target for efficient transferring learning.
  arXiv  Detail & Related papers  (2022-07-04T10:00:47Z)
• SuperAnimal pretrained pose estimation models for behavioral analysis [42.206265576708255]
  Quantification of behavior is critical in applications ranging from neuroscience, veterinary medicine and animal conservation efforts. We present a series of technical innovations that enable a new method, collectively called SuperAnimal, to develop unified foundation models.
  arXiv  Detail & Related papers  (2022-03-14T18:46:57Z)
• STAR: Sparse Transformer-based Action Recognition [61.490243467748314]
  This work proposes a novel skeleton-based human action recognition model with sparse attention on the spatial dimension and segmented linear attention on the temporal dimension of data. Experiments show that our model can achieve comparable performance while utilizing much less trainable parameters and achieve high speed in training and inference.
  arXiv  Detail & Related papers  (2021-07-15T02:53:11Z)
• Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
  We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training. We experimentally verify that the new dataset can significantly improve the ability of the learned FER model. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
  arXiv  Detail & Related papers  (2020-05-18T09:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.