Specifically, ARTIC3D is built upon a skeleton-based surface representation and is further guided by 2D diffusion priors from Stable Diffusion. First, we enhance the input images with occlusions/truncation via 2D diffusion to obtain cleaner mask estimates and semantic features.

Specifically, ARTIC3D is built upon a skeleton-based surface representation and is further guided by 2D diffusion priors from Stable Diffusion. First, we enhance the input images with occlusions/truncation via 2D diffusion to obtain cleaner mask estimates and semantic features.

In this supplementary document, we present the implementation details, model analyses, and additional results of our method. We also provide a short video to explain our framework with illustrations and visual results. We then collect and cluster the features of salient image patches by thresholding the saliency scores. As shown in Figure 3, the primitive MLP and part MLPs adopt a similar architecture as NeRS, i.e., three fully-connected layers with instance normalization and Leaky ReLU activation for middle layers. We show the architecture diagrams for primitive MLP and part MLPs.

Monitoring animal populations in natural environments requires systems that can interpret both visual data and human language queries. This work introduces ViLLa (Vision-Language-Logic Approach), a neuro-symbolic framework designed for interpretable animal monitoring. ViLLa integrates three core components: a visual detection module for identifying animals and their spatial locations in images, a language parser for understanding natural language queries, and a symbolic reasoning layer that applies logic-based inference to answer those queries. Given an image and a question such as "How many dogs are in the scene?" or "Where is the buffalo?", the system grounds visual detections into symbolic facts and uses predefined rules to compute accurate answers related to count, presence, and location. Unlike end-to-end black-box models, ViLLa separates perception, understanding, and reasoning, offering modularity and transparency. The system was evaluated on a range of animal imagery tasks and demonstrates the ability to bridge visual content with structured, human-interpretable queries.

Few-shot object classification is the task of classifying objects in an image with limited number of examples as supervision. We propose a one-shot/few-shot classification model that can classify an object of any unseen class into a relatively general category in an hierarchically based classification. Our model uses a three-level hierarchical contrastive loss based ResNet152 classifier for classifying an object based on its features extracted from Image embedding, not used during the training phase. For our experimentation, we have used a subset of the ImageNet (ILSVRC-12) dataset that contains only the animal classes for training our model and created our own dataset of unseen classes for evaluating our trained model. Our model provides satisfactory results in classifying the unknown objects into a generic category which has been later discussed in greater detail.

One common point of confusion with many students starting with Object-oriented programming (OOP) would be how to write the __init__ functions within subclasses. This article attempts to make this concept as simple as possible using a couple of shapes. Given these 4 shapes, we will be dealing with 5 classes -- Shape, Rectangle, Square, Triangle and EquilateralTriangle. Here, the Shape class is the parent class. To keep things simple, let's just create 1 attribute num_corners.

We propose an end-to-end unified 3D mesh recovery of humans and quadruped animals trained in a weakly-supervised way. Unlike recent work focusing on a single target class only, we aim to recover 3D mesh of broader classes with a single multi-task model. However, there exists no dataset that can directly enable multi-task learning due to the absence of both human and animal annotations for a single object, e.g., a human image does not have animal pose annotations; thus, we have to devise a new way to exploit heterogeneous datasets. To make the unstable disjoint multi-task learning jointly trainable, we propose to exploit the morphological similarity between humans and animals, motivated by animal exercise where humans imitate animal poses. We realize the morphological similarity by semantic correspondences, called sub-keypoint, which enables joint training of human and animal mesh regression branches. Besides, we propose class-sensitive regularization methods to avoid a mean-shape bias and to improve the distinctiveness across multi-classes. Our method performs favorably against recent uni-modal models on various human and animal datasets while being far more compact.

The most advanced framework for dense pose estimation for chimpanzees. It will help primatologists and other scientists study how chimps across Africa behave in the wild and in captive settings. The framework leverages a large-scale data set of unlabeled videos in the wild, a pretrained dense pose estimator for humans, and dense self-training techniques. This is a joint project in collaboration with our partners the Max Planck Institute for Evolutionary Anthropology (MPI EVA) and the Pan African Programme: The Cultured Chimpanzee, and their network of collaborators. We show that we can train a model to detect and recognize chimpanzees by transferring knowledge from existing detection, segmentation, and human dense pose labeling models.