Related papers: Unveil: Unified Visual-Textual Integration and Dis…
With the rise of deep learning, large datasets and complex models have become common, requiring significant computing power. To address this, data distillation has emerged as a technique to quickly train models with lower memory and time…
Dense retrieval is widely used for entity linking to retrieve entities from large-scale knowledge bases. Mainstream techniques are based on a dual-encoder framework, which encodes mentions and entities independently and calculates their…
Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and…
Dataset distillation (DD) condenses large datasets into compact yet informative substitutes, preserving performance comparable to the original dataset while reducing storage, transmission costs, and computational consumption. However,…
Version identification systems aim to detect different renditions of the same underlying musical composition (loosely called cover songs). By learning to encode entire recordings into plain vector embeddings, recent systems have made…
Despite the remarkable progress achieved by recent efficient methods in accelerating multimodal understanding, they still suffer from noticeable performance degradation. Their emphasis on the high compression ratio of a single visual clue…
In video-text retrieval, most existing methods adopt the dual-encoder architecture for fast retrieval, which employs two individual encoders to extract global latent representations for videos and texts. However, they face challenges in…
Recent advancements in information retrieval have highlighted the potential of integrating visual and textual information, yet effective reranking for image-text documents remains challenging due to the modality gap and scarcity of aligned…
The surge of digital documents in various formats, including less standardized documents such as business reports and environmental assessments, underscores the growing importance of Document Understanding. While Large Language Models…
In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…
Recent research has found that knowledge distillation can be effective in reducing the size of a network and in increasing generalization. A pre-trained, large teacher network, for example, was shown to be able to bootstrap a student model…
Understanding visually situated language requires interpreting complex layouts of textual and visual elements. Pre-processing tools, such as optical character recognition (OCR), can map document image inputs to textual tokens, then large…
End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small…
The recent rapid growth of visual generative models trained on vast web-scale datasets has created significant tension with data privacy regulations and copyright laws, such as GDPR's ``Right to be Forgotten.'' This necessitates machine…
Knowledge distillation (KD) is a widely adopted and effective method for compressing models in object detection tasks. Particularly, feature-based distillation methods have shown remarkable performance. Existing approaches often ignore the…
Online high-definition (HD) map construction is an important and challenging task in autonomous driving. Recently, there has been a growing interest in cost-effective multi-view camera-based methods without relying on other sensors like…
Image virtual try-on aims to fit a garment image (target clothes) to a person image. Prior methods are heavily based on human parsing. However, slightly-wrong segmentation results would lead to unrealistic try-on images with large…
Audio-visual representation learning is crucial for advancing multimodal speech processing tasks, such as lipreading and audio-visual speech recognition. Recently, speech foundation models (SFMs) have shown remarkable generalization…
Recently, efficient Multimodal Large Language Models (MLLMs) have gained significant attention as a solution to their high computational complexity, making them more practical for real-world applications. In this regard, the knowledge…
Transformer-based large language models (LLMs) rely on contextual embeddings which generate different (continuous) representations for the same token depending on its surrounding context. Nonetheless, words and tokens typically have a…