相关论文: Njobvu-AI: An open-source tool for collaborative i…

In the landscape of generative artificial intelligence, diffusion-based models have emerged as a promising method for generating synthetic images. However, the application of diffusion models poses numerous challenges, particularly…

Soft labels in image classification are vector representations of an image's true classification. In this paper, we investigate soft labels in the context of satellite object detection. We propose using detections as the basis for a new…

Augmenting Large Language Models (LLMs) with external tools enables them to execute complex, multi-step tasks. However, tool learning is hampered by the static synthetic data pipelines where data generation and model training are executed…

Computer vision (CV) techniques try to mimic human capabilities of visual perception to support labor-intensive and time-consuming tasks like the recognition and localization of critical objects. Nowadays, CV increasingly relies on…

Open-set object recognition aims to identify if an object is from a class that has been encountered during training or not. To perform open-set object recognition accurately, a key challenge is how to reduce the reliance on…

The advancement of Machine learning (ML), Large Audio Language Models (LALMs), and autonomous AI agents in Music Information Retrieval (MIR) necessitates a shift from static tagging to rich, human-aligned representation learning. However,…

AI models rely on annotated data to learn pattern and perform prediction. Annotation is usually a labor-intensive step that require associating labels ranging from a simple classification label to more complex tasks such as object…

Training and testing supervised object detection models require a large collection of images with ground truth labels. Labels define object classes in the image, as well as their locations, shape, and possibly other information such as…

Team collaboration plays a key role in the success of any multi-user activity. Software engineering is a highly collaborative activity, where multiple developers and designers work together to solve a common problem. Meaningful and…

Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-specific supervision. In fine-grained settings, however, the relevant evidence often lies in…

Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these…

More and more management and orchestration approaches for (software) networks are based on machine learning paradigms and solutions. These approaches depend not only on their program code to operate properly, but also require enough input…

Analysts need to classify, search and correlate numerous images. Automatic classification tools improve the efficiency of such tasks. However, classified data is a prerequisite to develop these tools. Labelling tools are of great use in…

Machine Learning models are deployed across a wide range of industries, performing a wide range of tasks. Tracking these models and ensuring they behave appropriately is becoming increasingly difficult as the number of deployed models…

Unsupervised 3D object detection serves as an important solution for offline 3D object annotation. However, due to the data sparsity and limited views, the clustering-based label fitting in unsupervised object detection often generates…

Agent-based editing models have substantially advanced interactive experiences, processing quality, and creative flexibility. However, two critical challenges persist: (1) instruction hallucination, text-only chain-of-thought (CoT)…

In image fusion tasks, images from different sources possess distinct characteristics. This has driven the development of numerous methods to explore better ways of fusing them while preserving their respective characteristics.Mamba, as a…

Molecular representation learning aims to learn vector embeddings that capture molecular structure and geometry, thereby enabling property prediction and downstream scientific applications. In many AI for science tasks, labeled data are…

The need to count and localize repeating objects in an image arises in different scenarios, such as biological microscopy studies, production lines inspection, and surveillance recordings analysis. The use of supervised Convoutional Neural…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…