相关论文: Global Semantic Description of Objects based on Pr…

Planet-scale photo geolocalization is the complex task of estimating the location depicted in an image solely based on its visual content. Due to the success of convolutional neural networks (CNNs), current approaches achieve super-human…

Machine-learning algorithms offer immense possibilities in the development of several cognitive applications. In fact, large scale machine-learning classifiers now represent the state-of-the-art in a wide range of object…

Concept Bottleneck Models (CBMs) assume that training examples (e.g., x-ray images) are annotated with high-level concepts (e.g., types of abnormalities), and perform classification by first predicting the concepts, followed by predicting…

Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. To boost the transferability of the pre-trained models, recent works adopt fixed or learnable prompts, i.e.,…

Concept Bottleneck Models (CBMs) provide inherent interpretability by first predicting a set of human-understandable concepts and then mapping them to labels through a simple classifier. While users can intervene in the concept space to…

The security and efficiency of modern computing systems are fundamentally undermined by the absence of a native architectural mechanism to propagate high-level program semantics, such as object identity, bounds, and lifetime, across the…

Open-world object counting leverages the robust text-image alignment of pre-trained vision-language models (VLMs) to enable counting of arbitrary categories in images specified by textual queries. However, widely adopted naive fine-tuning…

Explainable object recognition using vision-language models such as CLIP involves predicting accurate category labels supported by rationales that justify the decision-making process. Existing methods typically rely on prompt-based…

According to the software engineering community, the acknowledgement is growing that a theory of software development is needed to integrate the currently myriad popular methodologies, some of which are based on opposing perspectives.…

We propose an approach to analogical inference that marries the neuro-symbolic computational power of complex-sampled hyperdimensional computing (HDC) with Conceptual Spaces Theory (CST), a promising theory of semantic meaning. CST…

Video captioning targets interpreting the complex visual contents as text descriptions, which requires the model to fully understand video scenes including objects and their interactions. Prevailing methods adopt off-the-shelf object…

Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating…

Developing high-performing, yet interpretable models remains a critical challenge in modern AI. Concept-based models (CBMs) attempt to address this by extracting human-understandable concepts from a global encoding (e.g., image encoding)…

Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degrade visual information and increase prediction uncertainty. Existing methods either…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Classification of sets of inputs (e.g., images and texts) is an active area of research within both computer vision (CV) and natural language processing (NLP). A common way to represent a set of vectors is to model them as linear subspaces.…

Predicting and explaining the private information contained in an image in human-understandable terms is a complex and contextual task. This task is challenging even for large language models. To facilitate the understanding of privacy…

Semantic communication, rather than on a bit-by-bit recovery of the transmitted messages, focuses on the meaning and the goal of the communication itself. In this paper, we propose a novel semantic image coding scheme that preserves the…

Category-level pose estimation is a challenging task with many potential applications in computer vision and robotics. Recently, deep-learning-based approaches have made great progress, but are typically hindered by the need for large…

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of…