Related papers: Open Vocabulary Multi-Label Classification with Du…

Referring Audio-Visual Segmentation (Ref-AVS) seeks to localize and segment target objects in video frames based on visual, auditory, and textual referring cues. The task is challenging because the relevance of different modalities varies…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…

Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to find efficient similarity metrics to compare the similarity…

Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using…

Weakly supervised multimodal video anomaly detection has gained significant attention, yet the potential of the text modality remains under-explored. Text provides explicit semantic information that can enhance anomaly characterization and…

Generating visually grounded image captions with specific linguistic styles using unpaired stylistic corpora is a challenging task, especially since we expect stylized captions with a wide variety of stylistic patterns. In this paper, we…

Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts have explored language-driven zero-shot SED by exploiting…

Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering…

Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achieved remarkable results, they only explore the intrinsic…

This paper proposes a novel deep architecture to address multi-label image recognition, a fundamental and practical task towards general visual understanding. Current solutions for this task usually rely on an extra step of extracting…

Open-vocabulary semantic segmentation is a challenging task, which requires the model to output semantic masks of an image beyond a close-set vocabulary. Although many efforts have been made to utilize powerful CLIP models to accomplish…

Open-vocabulary object detection (OVD) aims to scale up vocabulary size to detect objects of novel categories beyond the training vocabulary. Recent work resorts to the rich knowledge in pre-trained vision-language models. However, existing…

In this work, we propose an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes. It is a two-stage training approach that first uses a…

Industrial anomaly detection based on RGB-3D multimodal data has emerged as a mainstream paradigm for intelligent quality inspection. However, existing unsupervised methods suffer from two critical limitations: ambiguous cross-modal…

Recently, a few open-vocabulary methods have been proposed by employing a unified architecture to tackle generic segmentation and detection tasks. However, their performance still lags behind the task-specific models due to the conflict…

Modern image classification is based upon directly predicting classes via large discriminative networks, which do not directly contain information about the intuitive visual features that may constitute a classification decision. Recently,…

Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional…

Legal multi-label classification is a critical task for organizing and accessing the vast amount of legal documentation. Despite its importance, it faces challenges such as the complexity of legal language, intricate label dependencies, and…

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…