Related papers: Hierarchy-Guided Multimodal Representation Learnin…

Taxonomic classification in biodiversity research involves organizing biological specimens into structured hierarchies based on evidence, which can come from multiple modalities such as images and genetic information. We investigate whether…

Measuring biodiversity is crucial for understanding ecosystem health. While prior works have developed machine learning models for taxonomic classification of photographic images and DNA separately, in this work, we introduce a multimodal…

Hierarchical knowledge structures are ubiquitous across real-world domains and play a vital role in organizing information from coarse to fine semantic levels. While such structures have been widely used in taxonomy systems, biomedical…

Acoustic identification of individual animals (AIID) is closely related to audio-based species classification but requires a finer level of detail to distinguish between individual animals within the same species. In this work, we frame…

A high-performing, general-purpose visual understanding model should map visual inputs to a taxonomic tree of labels, identify novel categories beyond the training set for which few or no publicly available images exist. Large Multimodal…

Multimodal intent recognition aims to infer human intents by jointly modeling various modalities, playing a pivotal role in real-world dialogue systems. However, current methods struggle to model hierarchical semantics underlying complex…

Deep learning for Earth imagery plays an increasingly important role in geoscience applications such as agriculture, ecology, and natural disaster management. Still, progress is often hindered by the limited training labels. Given Earth…

Hierarchical image recognition seeks to predict class labels along a semantic taxonomy, from broad categories to specific ones, typically under the tidy assumption that every training image is fully annotated along its taxonomy path.…

Human-aligned deep learning models exhibit behaviors consistent with human values, such as robustness, fairness, and honesty. Transferring these behavioral properties to models trained on different tasks or data distributions remains…

Hierarchical classification predicts labels across multiple levels of a taxonomy, e.g., from coarse-level 'Bird' to mid-level 'Hummingbird' to fine-level 'Green hermit', allowing flexible recognition under varying visual conditions. It is…

Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of order, family, and species. Existing methods commonly address…

A major challenge in multimodal learning is the presence of noise within individual modalities. This noise inherently affects the resulting multimodal representations, especially when these representations are obtained through explicit…

Unsupervised visible-infrared person re-identification (USVI-ReID) aims to learn modality-invariant image features from unlabeled cross-modal person datasets by reducing the modality gap while minimizing reliance on costly manual…

Modeling hierarchical latent dynamics behind time series data is critical for capturing temporal dependencies across multiple levels of abstraction in real-world tasks. However, existing temporal causal representation learning methods fail…

Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…

Vision-Language Models (VLMs) learn powerful multimodal representations through large-scale image-text pretraining, but adapting them to hierarchical classification is underexplored. Standard approaches treat labels as flat categories and…

Understanding how chemical perturbations propagate through biological systems is essential for robust molecular property prediction. While most existing methods focus on chemical structures alone, recent advances highlight the crucial role…

Composed Video Retrieval (CVR) is a challenging video retrieval task that utilizes multi-modal queries, consisting of a reference video and modification text, to retrieve the desired target video. The core of this task lies in understanding…

We address an important problem in ecology called Species Distribution Modeling (SDM), whose goal is to predict whether a species exists at a certain position on Earth. In particular, we tackle a challenging version of this task, where we…

Microbial identification is a central issue in microbiology, in particular in the fields of infectious diseases diagnosis and industrial quality control. The concept of species is tightly linked to the concept of biological and clinical…