Related papers: Domain-Adaptive Pretraining Improves Primate Behav…

This paper presents a detection-aware pre-training (DAP) approach, which leverages only weakly-labeled classification-style datasets (e.g., ImageNet) for pre-training, but is specifically tailored to benefit object detection tasks. In…

The brain can only be fully understood through the lens of the behavior it generates -- a guiding principle in modern neuroscience research that nevertheless presents significant technical challenges. Many studies capture behavior with…

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…

We propose the first metric learning system for the recognition of great ape behavioural actions. Our proposed triple stream embedding architecture works on camera trap videos taken directly in the wild and demonstrates that the utilisation…

We propose a novel end-to-end curriculum learning approach for sparsely labelled animal datasets leveraging large volumes of unlabelled data to improve supervised species detectors. We exemplify the method in detail on the task of finding…

This paper addresses the significant challenge of recognizing behaviors in non-human primates, specifically focusing on chimpanzees. Automated behavior recognition is crucial for both conservation efforts and the advancement of behavioral…

Biodiversity conservation depends on accurate, up-to-date information about wildlife population distributions. Motion-activated cameras, also known as camera traps, are a critical tool for population surveys, as they are cheap and…

Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of…

Prompt learning has recently become a very efficient transfer learning paradigm for Contrastive Language Image Pretraining (CLIP) models. Compared with fine-tuning the entire encoder, prompt learning can obtain highly competitive results by…

Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence…

Advances in computer vision as well as increasingly widespread video-based behavioral monitoring have great potential for transforming how we study animal cognition and behavior. However, there is still a fairly large gap between the…

The vast majority of visual animals actively control their eyes, heads, and/or bodies to direct their gaze toward different parts of their environment. In contrast, recent applications of reinforcement learning in robotic manipulation…

Domain-Adaptive Pre-training (DAP) has recently gained attention for its effectiveness in fine-tuning pre-trained models. Building on this, continual DAP has been explored to develop pre-trained models capable of incrementally incorporating…

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…

Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems. We investigate the ability to automatically, accurately, and…

Domain-adaptive trajectory imitation is a skill that some predators learn for survival, by mapping dynamic information from one domain (their speed and steering direction) to a different domain (current position of the moving prey). An…

The deep learning-based analysis of medical images suffers from data scarcity because of high annotation costs and privacy concerns. Researchers in this domain have used transfer learning to avoid overfitting when using complex…

Understanding non-human primate behavior is crucial for improving animal welfare, modeling social behavior, and gaining insights into both distinctly human and shared behaviors. Despite recent advances in computer vision, automated analysis…

Person re-identification is a key technology for analyzing video-based human behavior; however, its application is still challenging in practical situations due to the performance degradation for domains different from those in the training…

Deep neural networks have recently achieved competitive accuracy for human activity recognition. However, there is room for improvement, especially in modeling long-term temporal importance and determining the activity relevance of…