The task of 2D animal pose estimation plays a crucial role in advancing deep learning applications in animal behavior analysis and ecological research. Despite notable progress in some existing approaches, our study reveals that the scarcity of high-quality datasets remains a significant bottleneck, limiting the full potential of current methods. To address this challenge, we propose a novel Controllable Image Generation Pipeline for synthesizing animal pose estimation data, termed AP-CAP. Within this pipeline, we introduce a Multi-Modal Animal Image Generation Model capable of producing images with expected poses. To enhance the quality and diversity of the generated data, we further propose three innovative strategies: (1) Modality-Fusion-Based Animal Image Synthesis Strategy to integrate multi-source appearance representations, (2) Pose-Adjustment-Based Animal Image Synthesis Strategy to dynamically capture diverse pose variations, and (3) Caption-Enhancement-Based Animal Image Synthesis Strategy to enrich visual semantic understanding. Leveraging the proposed model and strategies, we create the MPCH Dataset (Modality-Pose-Caption Hybrid), the first hybrid dataset that innovatively combines synthetic and real data, establishing the largest-scale multi-source heterogeneous benchmark repository for animal pose estimation to date. Extensive experiments demonstrate the superiority of our method in improving both the performance and generalization capability of animal pose estimators.
Advances in tracking technologies for animal movement require new statistical tools to better exploit the increasing amount of data. Animal positions are usually calculated using the GPS or Argos satellite system and include potentially complex non-Gaussian and heavy-tailed measurement error patterns. Errors are usually handled through a Kalman filter algorithm, which can be sensitive to non-Gaussian error distributions. In this paper, we introduce a realistic latent movement model through an underdamped Langevin stochastic differential equation (SDE) that includes an additional drift term to ensure that the animal remains in a known spatial domain of interest. This can be applied to aquatic animals moving in water or terrestrial animals moving in a restricted zone delimited by fences or natural barriers. We demonstrate that the incorporation of these spatial constraints into the latent movement model improves the accuracy of filtering for noisy observations of the positions. We implement an Extended Kalman Filter as well as a particle filter adapted to non-Gaussian error distributions. Our filters are based on solving the SDE through splitting schemes to approximate the latent dynamic.
Humans possess a unique ability to perceive meaningful patterns in ambiguous stimuli, a cognitive phenomenon known as pareidolia. This paper introduces Shape2Animal framework to mimics this imaginative capacity by reinterpreting natural object silhouettes, such as clouds, stones, or flames, as plausible animal forms. Our automated framework first performs open-vocabulary segmentation to extract object silhouette and interprets semantically appropriate animal concepts using vision-language models. It then synthesizes an animal image that conforms to the input shape, leveraging text-to-image diffusion model and seamlessly blends it into the original scene to generate visually coherent and spatially consistent compositions. We evaluated Shape2Animal on a diverse set of real-world inputs, demonstrating its robustness and creative potential. Our Shape2Animal can offer new opportunities for visual storytelling, educational content, digital art, and interactive media design. Our project page is here: https://shape2image.github.io
Mudasir Ahmad Shah, Bilal Ahmad Malla, Prakash Kinjavdekar
et al.
Epidural anaesthesia is one among the most frequently used central neuraxial block techniques because of its simplicity and safety. This study aimed to assess the changes in haematological and haemodynamic parameters induced in dogs by epidurally administered lidocaine, bupivacaine, and ropivacaine together with dexmedetomidine in atropine-midazolam premedicated dogs subjected to elective ovariohysterectomy. A total of twenty-four adult dogs were allocated randomly (n=6) to 4 different groups, namely: A (dexmedetomidine), B (dexmedetomidine with lidocaine), C (dexmedetomidine with bupivacaine), and D (dexmedetomidine with ropivacaine). After a 10 minute premedication period, Dexmedetomidine @ 7 μg/kg, Lidocaine @ 4.4 mg/kg, Bupivacaine @ 2 mg/kg and Ropivacaine @ 2 mg/kg were dispensed into the epidural space. Different haematological and haemodynamic parameters were recorded during the study period. Haemoglobin levels showed a significant decline in Group B at the 30 and 90 minute with respect to baseline values. Packed cell volume, neutrophil and lymphocyte counts showed nonsignificant changes in all the groups relative to baseline. At 90 minutes, Group D exhibited a highly significant reduction (p < 0.05) in total leukocyte count compared to the other groups. Groups A, C and D exhibited significant variations in systolic, diastolic blood pressure, mean arterial pressure and haemoglobin oxygen saturation (SpO2) at various time points with respect to the baseline values. It was concluded that combining dexmedetomidine with lignocaine for epidural administration does not lead to haematological or haemodynamic instability.
Mengzhou Xue MD, PhD1, Jianbo Liu MD, PhD5 and Guang Han MD, PhD6 1Department of Cerebrovascular Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China, 2Department of Gynecology and Obstetrics, Renmin Hospital of Wuhan University, Wuhan, Hubei Province, China, 3Key Laboratory of Animal Physiology, Biochemistry and Molecular Biology of Hebei Province, College of Life Sciences, Hebei Normal University, Shijiazhuang, China, 4Department of Public Health, Wuhan University, Wuhan, China, 5Department of Respiratory Diseases, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, China and 6Department of Radiation Oncology, Hubei Cancer Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
Recent advancements in text-to-3D generation have demonstrated the ability to generate high quality 3D assets. However while generating animals these methods underperform, often portraying inaccurate anatomy and geometry. Towards ameliorating this defect, we present C3DAG, a novel pose-Controlled text-to-3D Animal Generation framework which generates a high quality 3D animal consistent with a given pose. We also introduce an automatic 3D shape creator tool, that allows dynamic pose generation and modification via a web-based tool, and that generates a 3D balloon animal using simple geometries. A NeRF is then initialized using this 3D shape using depth-controlled SDS. In the next stage, the pre-trained NeRF is fine-tuned using quadruped-pose-controlled SDS. The pipeline that we have developed not only produces geometrically and anatomically consistent results, but also renders highly controlled 3D animals, unlike prior methods which do not allow fine-grained pose control.
Audio-driven portrait animation has made significant advances with diffusion-based models, improving video quality and lipsync accuracy. However, the increasing complexity of these models has led to inefficiencies in training and inference, as well as constraints on video length and inter-frame continuity. In this paper, we propose JoyVASA, a diffusion-based method for generating facial dynamics and head motion in audio-driven facial animation. Specifically, in the first stage, we introduce a decoupled facial representation framework that separates dynamic facial expressions from static 3D facial representations. This decoupling allows the system to generate longer videos by combining any static 3D facial representation with dynamic motion sequences. Then, in the second stage, a diffusion transformer is trained to generate motion sequences directly from audio cues, independent of character identity. Finally, a generator trained in the first stage uses the 3D facial representation and the generated motion sequences as inputs to render high-quality animations. With the decoupled facial representation and the identity-independent motion generation process, JoyVASA extends beyond human portraits to animate animal faces seamlessly. The model is trained on a hybrid dataset of private Chinese and public English data, enabling multilingual support. Experimental results validate the effectiveness of our approach. Future work will focus on improving real-time performance and refining expression control, further expanding the applications in portrait animation. The code is available at: https://github.com/jdh-algo/JoyVASA.
Agriculture faces a growing challenge with wildlife wreaking havoc on crops, threatening sustainability. The project employs advanced object detection, the system utilizes the Mobile Net SSD model for real-time animal classification. The methodology initiates with the creation of a dataset, where each animal is represented by annotated images. The SSD Mobile Net architecture facilitates the use of a model for image classification and object detection. The model undergoes fine-tuning and optimization during training, enhancing accuracy for precise animal classification. Real-time detection is achieved through a webcam and the OpenCV library, enabling prompt identification and categorization of approaching animals. By seamlessly integrating intelligent scarecrow technology with object detection, this system offers a robust solution to field protection, minimizing crop damage and promoting precision farming. It represents a valuable contribution to agricultural sustainability, addressing the challenge of wildlife interference with crops. The implementation of the Intelligent Scarecrow Monitoring System stands as a progressive tool for proactive field management and protection, empowering farmers with an advanced solution for precision agriculture. Keywords: Machine learning, Deep Learning, Computer Vision, MobileNet SSD
Sexual selection is critical to animal reproduction. Mate choice not only determines an individual's capacity for reproduction but is also the primary mode of selection in sexual selection. Mate choice behavior relies on social information, and animals can extract useful information (e.g., genetic quality, hormone levels, physiological status, habitat) about potential mates based on morphological and behavioral traits they observe or perceive and can modify their mate choice strategy by detecting and integrating this information. The information conveyed by potential mates is multimodal. This paper synthesizes the effects of several factors, including individual biological characteristics, sensory systems, hormones and genotype on mate choice, demonstrating that mate choice preferences in the traditional sense are generally more favorable for individuals with superior genes and phenotypes. And the paper also explores the limitations of these studies on mate choice and proposes the future major trend of the correlational research in this field. This work will provide helpful information for guiding the subsequent studies of mate choice in animals.
Adolescence is a time of major plasticity of brain systems that regulate motivated behavior and cognition, and is also the age of peak onset of nicotine use. Although there has been a decline in teen use of cigarettes in recent years, there has been a huge increase in nicotine vaping. It is therefore critically important to understand the impact of nicotine on this critical phase of brain development. Animal studies have shown that nicotine has unique effects on adolescent brain. The goal of this review is therefore to systematically evaluate age- and sex-differences in the effects of nicotine on brain and behavior. Both acute and chronic effects of nicotine on brain biochemistry and behavior, particularly drug reward, aversion, cognition and emotion, are evaluated. Gaps in our current knowledge that need to be addressed are also highlighted. This review compares and integrates human and animals findings. Although there can be no experimental studies in humans to confirm similar behavioral effects of teen nicotine exposure, an emerging observational literature suggests similarities across species. Given the substantial evidence for long-term negative impact of adolescent nicotine exposure on brain and behavior, further longitudinal assessment of health outcomes in teen and young adult e-cigarette users is warranted.
Md. Aminul Islam, Md. Aminul Islam, Shatila Shahi
et al.
Introduction: Coronavirus disease 2019 (COVID-19), caused by SARS-CoV-2, has had a disastrous effect worldwide during the previous three years due to widespread infections with SARS-CoV-2 and its emerging variations. More than 674 million confirmed cases and over 6.7 million deaths have been attributed to successive waves of SARS-CoV-2 infections as of 29th January 2023. Similar to other RNA viruses, SARS-CoV-2 is more susceptible to genetic evolution and spontaneous mutations over time, resulting in the continual emergence of variants with distinct characteristics. Spontaneous mutations of SARS-CoV-2 variants increase its transmissibility, virulence, and disease severity and diminish the efficacy of therapeutics and vaccines, resulting in vaccine-breakthrough infections and re-infection, leading to high mortality and morbidity rates.Materials and methods: In this study, we evaluated 10,531 whole genome sequences of all reported variants globally through a computational approach to assess the spread and emergence of the mutations in the SARS-CoV-2 genome. The available data sources of NextCladeCLI 2.3.0 (https://clades.nextstrain.org/) and NextStrain (https://nextstrain.org/) were searched for tracking SARS-CoV-2 mutations, analysed using the PROVEAN, Polyphen-2, and Predict SNP mutational analysis tools and validated by Machine Learning models.Result: Compared to the Wuhan-Hu-1 reference strain NC 045512.2, genome-wide annotations showed 16,954 mutations in the SARS-CoV-2 genome. We determined that the Omicron variant had 6,307 mutations (retrieved sequence:1947), including 67.8% unique mutations, more than any other variant evaluated in this study. The spike protein of the Omicron variant harboured 876 mutations, including 443 deleterious mutations. Among these deleterious mutations, 187 were common and 256 were unique non-synonymous mutations. In contrast, after analysing 1,884 sequences of the Delta variant, we discovered 4,468 mutations, of which 66% were unique, and not previously reported in other variants. Mutations affecting spike proteins are mostly found in RBD regions for Omicron, whereas most of the Delta variant mutations drawn to focus on amino acid regions ranging from 911 to 924 in the context of epitope prediction (B cell & T cell) and mutational stability impact analysis protruding that Omicron is more transmissible.Discussion: The pathogenesis of the Omicron variant could be prevented if the deleterious and persistent unique immunosuppressive mutations can be targeted for vaccination or small-molecule inhibitor designing. Thus, our findings will help researchers monitor and track the continuously evolving nature of SARS-CoV-2 strains, the associated genetic variants, and their implications for developing effective control and prophylaxis strategies.
Vittorio Giammarino, James Queeney, Lucas C. Carstensen
et al.
We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a series of 2D navigation tasks. We show how our methods can leverage animal videos to improve performance over RL algorithms that do not leverage such observations.
Various existing studies have analyzed what social biases are inherited by NLP models. These biases may directly or indirectly harm people, therefore previous studies have focused only on human attributes. However, until recently no research on social biases in NLP regarding nonhumans existed. In this paper, we analyze biases to nonhuman animals, i.e. speciesist bias, inherent in English Masked Language Models such as BERT. We analyzed speciesist bias against 46 animal names using template-based and corpus-extracted sentences containing speciesist (or non-speciesist) language. We found that pre-trained masked language models tend to associate harmful words with nonhuman animals and have a bias toward using speciesist language for some nonhuman animal names. Our code for reproducing the experiments will be made available on GitHub.
El-Sayed A., Fayed R.H., Castañeda Vázquez H.
et al.
Since thousands of years, herbal products were used for medical purposes in old cultures. The present trend to re-discover the medical potential of herbs started to grow with the general awareness of the medical hazards of several chemical pharmaceutical preparations. Similarly, for several decades, antibiotics, Coccidiostat and other chemical feed additives were massively used in animal husbandry. However, due to their negative impact on consumer health, they were banned in many countries. The present work discusses some natural alternative available for use in human and veterinary medical fields. The number of commercially available herbal products increases rapidly in the markets worldwide and are expected to overtake the number of pharmaceuticals of chemical origin in food sector in the future.