Search Results

Few-shot Learning (FSL) aims to learn and distinguish new categories from a scant number of available samples, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional semantic or ...

• Previous Semantic-based few-shot methods focus on designing complex fusion modules, while ignoring the generalization capacity of language models.
• We propose a simple framework, which fully exploits the LM with learnable prompts.
• ...

Video grounding aims to locate a moment-of-interest semantically corresponding to a given query. We claim that existing methods overlook two critical issues: (1) the sparsity of language, and (2) the human perception process of events. To be ...

• Language features compared to video features tends to be sparser.
• Verbs carry discriminative information for distinguishing different videos.
• Salient action and temporal order of actions are two key factors.
• A Prompt ...

We introduce a new framework, dubbed Cerberus, for attribute-based person re-identification (reID). Our approach leverages person attribute labels to learn local and global person representations that encode specific traits, such as gender and ...

• We introduce Cerberus, a novel attribute-based person re-ID framework.
• Cerberus handles reID, PAR, and (partial) APS tasks, using a unified model.
• We encourage discerning differences between similar persons via semantic guidance.

Interactive portrait matting refers to extracting the soft portrait from a given image that best meets the user’s intent through their inputs. Existing methods often underperform in complex scenarios, mainly due to three factors. (1) Most works ...

3D occupancy prediction based on multi-sensor fusion, crucial for a reliable autonomous driving system, enables fine-grained under- standing of 3D scenes. Previous fusion-based 3D occupancy predictions relied on depth estimation for processing 2D ...

Malnutrition poses a significant threat to global health, resulting from an inadequate intake of essential nutrients that adversely impacts vital organs and overall bodily functioning. Periodic examinations and mass screenings, incorporating both ...

• A holistic feature fusion of facial, body & 3D embeddings, including the correlation between them, optimal feature combination and individual importance in estimating the weight is insightfully discussed.
• This paper is the first to ...

Multi-modal Entity Alignment (MMEA) aims to establish correlations between modalities such as images and texts to align equivalent entities across different multi-modal knowledge graphs, thereby enhancing knowledge graph coverage and addressing ...

Recent advances show that Transformer-based models and object detection-based models play an indispensable role in VQA. However, object detection-based models have significant limitations due to their redundant and complex detection box ...

Few-shot classification aims to recognize query samples from novel classes given scarce labeled data, which remains a challenging problem in machine learning. This paper proposes a Discriminative Feature Enhancement Network (DFENet) to ...

• DFENet introduces a novel approach for few-shot classification, using visual and semantic knowledge.
• The neural decoding-based attention module efficiently assigns attention weights to keys, inspired by cognitive neuroscience.
• A ...

Multi-modal 3D object detection is instrumental in identifying and localizing objects within 3D space. It combines RGB images from cameras and point-clouds data from lidar sensors, serving as a fundamental technology for autonomous driving ...

Multi-modal attention mechanisms have been successfully used in multi-modal graph learning for various tasks. However, existing attention-based multi-modal graph learning (AMGL) architectures heavily rely on manual design, requiring huge effort ...

• AutoAMS searches for attention-based multimodal graph learning (AMGL) architectures.
• AM search space supports finding multi-modal attention and graph learning components.
• A search objective using unsupervised and task-specific ...

Large-scale pre-trained models and graph neural networks have recently demonstrated remarkable success in few-shot video classification tasks. However, they generally suffer from two key limitations: i) the temporal relations between adjacent ...

Recent multi-modal fake news detection methods often use the consistency between textual and visual contents to determine the truth or fake of a news information. Higher levels of textual-visual consistency typically lead to a greater likelihood of ...

Glaucoma is one of the leading causes of vision impairment. Digital imaging techniques, such as color fundus photography (CFP) and optical coherence tomography (OCT), provide quantitative and noninvasive methods for glaucoma diagnosis. Recently, ...

Multimodal learning has demonstrated promising advantages over single-modal approaches in the diagnosis of skin lesions. However, these methods often suffer from significant accuracy degradation when encountering missing modalities, hindering ...

The development of artificial intelligence has significantly impacted the predictive analysis of molecular biomarkers, which is crucial for targeted cancer therapy. Traditional assessment of HER2 in breast cancer utilizes both Hematoxylin and ...

Multi-modal learning plays a crucial role in cancer diagnosis and prognosis. Current deep learning based multi-modal approaches are often limited by their abilities to model the complex correlations between genomics and histopathology data, ...

Multi-modal pre-trained models efficiently extract and fuse features from different modalities with low memory requirements for fine-tuning. Despite this efficiency, their application in disease diagnosis is under-explored. A significant challenge ...

Early prediction of hepatocellular carcinoma (HCC) is necessary to facilitate appropriate surveillance strategy and reduce cancer mortality. Incorporating CT scans and clinical time series can greatly increase the accuracy of predictive models. ...

Selecting the appropriate power for intraocular lenses (IOLs) is crucial for the success of cataract surgeries. Traditionally, ophthalmologists rely on manually designed formulas like “Barrett” and “Hoffer Q” to calculate IOL power. However, these ...