bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/280735

idtracker.ai: Tracking all individuals in large collectives of unmarked animals

Romero Ferrero, F.·bergomi, m. g.·Hinz, R.·Hernandez Heras, F. J.·de Polavieja, G.
View original source ↗Export metadata ↓

Abstract

Our understanding of collective animal behavior is limited by our ability to track each of the individuals. We describe an algorithm and software, idtracker.ai, that extracts from video all trajectories with correct identities at a high accuracy for collectives of up to 100 individuals. It uses two deep networks, one detecting when animals touch or cross and an-other one for animal identification, trained adaptively to conditions and difficulty of the video.

Source connections

Explore related subjects

animal behavior and cognitionPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Romero Ferrero, F., bergomi, m. g., Hinz, R., Hernandez Heras, F. J., de Polavieja, G.. 2018-03-14. idtracker.ai: Tracking all individuals in large collectives of unmarked animals. https://doi.org/10.1101/280735

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Standard touchscreen test procedures shift circadian rhythms in mice: a modified protocol to minimize circadian confounds

Touchscreen based cognitive testing for rodents offers considerable experimental benefits, including a semi automated battery approach and the use of appetitive rather than aversive reinforcement. However, food reward and touchscreen illumination introduce potential confounds, as both food and light can shift, entrain, or disrupt circadian rhythms, which in turn can affect learning and memory. The potential for the test apparatus to impact endogenous circadian rhythms is particularly problematic when probing relationships between sleep, circadian disruption, and cognitive performance. After observing phase shifting of circadian rhythms in nocturnal mice tested using standard touchscreen test procedures, which include testing during the active period (early lights off), we evaluated the relative contributions of the illuminated screen and the appetitive food reward. Our results indicate that light emitted by the touchscreen chambers is responsible for the circadian phase shifting effects, with standard screen conditions inducing a ~3.5 h phase delay in daily activity rhythms when training is conducted early in the dark period for 7 consecutive days. We then modified lighting in the test environment and the home cage to identify parameters that would minimize circadian shifting without impairing visual discrimination or performance on a widely used cognitive test (Trial Unique Nonmatching to Location, TUNL). From the 10 conditions tested, we offer specific recommendations for modifying touchscreen test protocols to minimize circadian confounds, without impacting task acquisition or performance.

animal behavior and cognition↗
bioRxiv2026

Individual differences in Game Transfer Phenomena are associated with creativity and positive schizotypy but not with perceptual priming

Game Transfer Phenomena (GTP) refer to involuntary experience of video-game elements as part of gamers everyday perception, cognition, and behaviour. Although previous research has identified Internet Gaming Disorder (IGD), positive schizotypy, and spontaneous cognitions (e.g., mind-popping, daydreaming) as key predictors of GTP, the role of implicit memory processes and creativity remains unclear. The present study examined whether these cognitive processes are associated with GTP frequency while replicating established predictors such as IGD, involuntary cognitions, and schizotypal traits. A total of 85 video game players (53% males; Mage = 24.89, SD = 5.87) completed a word fragment completion task to assess individual differences in perceptual implicit memory (priming). To measure creativity, participants completed the Alternate Uses Task (AUT) as a measure of divergent thinking, and a free association task to estimate forward flow, a robust predictor of creative cognition. Results showed robust priming effects at the group level (M = .23, SD = .14), however, individual differences in perceptual priming were not associated with GTP frequency. In contrast, AUT scores were positively associated with GTP and contributed uniquely to its prediction. A hierarchical regression model explained 58.2% of the variance in GTP frequency, with IGD, daydreaming, and positive schizotypy as the strongest predictors, alongside hours played per session and AUT scores. These findings suggest that GTP may not be driven by domain-general perceptual implicit memory processes but may be more strongly linked to individual differences in spontaneous cognitions and conceptual associative priming processes.

animal behavior and cognition↗
bioRxiv2026

How multilevel competition drives cooperation in stigmergic systems

Cooperation through stigmergy relies on reliable information left in a shared environment, yet individuals may benefit from misleading others. How competition within and between groups shapes this conflict remains unclear. We investigated this question using the Stigmer Game, in which human participants interact exclusively through ratings that modify a shared informational environment, under seven payment rules. Participants were classified as collaborators, neutrals or defectors. Between-group competition produced the highest collaboration, whereas within-group competition favoured defection. Adding between-group competition partly restored cooperation despite continued rivalry within groups, although this effect depended on reward distribution. A quantitative analysis showed that within-group and rank-based competitive pressures best described differences in behavioural composition across payment rules. A genetic algorithm further revealed distinct stationary strategy compositions under each payment rule that were largely independent of initial conditions and robust to perturbations. These results reproduced the opposing effects of between-group and within-group competition observed experimentally, while highlighting differences between immediate behavioural responses and the strategy distributions favoured by each rule's incentive structure. Defectors remained present under the mutation regime, illustrating the vulnerability of shared information to exploitation. Our findings show how the organization of competitive incentives shapes cooperation and information reliability in decentralized collective systems.

animal behavior and cognition↗