相关论文: Universal Layout Emulation for Long-Term Database …

An increasing amount of information today is generated, exchanged, and stored digitally. This also includes long-lived and highly sensitive information (e.g., electronic health records, governmental documents) whose integrity and…

In modern application areas for software systems --- like eHealth, the Internet-of-Things, and Edge Computing --- data is encoded in heterogeneous, tree-shaped data-formats, it must be processed in real-time, and it must be ephemeral, i.e.,…

The amount of digital data is rapidly growing. There is an increasing use of a wide range of computer systems, from mobile devices to large-scale data centers, and important for reliable operation of all computer systems is mitigating the…

This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function…

This paper presents VideoStreaming, an advanced vision-language large model (VLLM) for video understanding, that capably understands arbitrary-length video with a constant number of video tokens streamingly encoded and adaptively selected.…

We propose UnCLe, the first standardized benchmark for Unsupervised Continual Learning of a multimodal 3D reconstruction task: Depth completion aims to infer a dense depth map from a pair of synchronized RGB image and sparse depth map. We…

The fine-grained surface reconstruction of different organs from 3D medical imaging can provide advanced diagnostic support and improved surgical planning. However, the representation of the organs is often limited by the resolution, with a…

Spectral Embedding (SE) has often been used to map data points from non-linear manifolds to linear subspaces for the purpose of classification and clustering. Despite significant advantages, the subspace structure of data in the original…

We examine the problem of creating an encoded distributed storage representation of a data object for a network of mobile storage nodes so as to achieve the optimal recovery delay. A source node creates a single data object and disseminates…

Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead.…

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models…

We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors.…

In this paper, we study error-correcting codes for the storage of data in synthetic deoxyribonucleic acid (DNA). We investigate a storage model where data is represented by an unordered set of $M$ sequences, each of length $L$. Errors…

We present UMI-3D, a multimodal extension of the Universal Manipulation Interface (UMI) for robust and scalable data collection in embodied manipulation. While UMI enables portable, wrist-mounted data acquisition, its reliance on monocular…

Medical ultrasound videos are widely used for medical inspections, disease diagnosis and surgical planning. High-fidelity lesion area and target organ segmentation constitutes a key component of the computer-assisted surgery workflow. The…

Continual learning denotes machine learning methods which can adapt to new environments while retaining and reusing knowledge gained from past experiences. Such methods address two issues encountered by models in non-stationary…

Long-video understanding has emerged as a crucial capability in real-world applications such as video surveillance, meeting summarization, educational lecture analysis, and sports broadcasting. However, it remains computationally…

The rise in loosely-structured data available through text, images, and other modalities has called for new ways of querying them. Multimedia Information Retrieval has filled this gap and has witnessed exciting progress in recent years.…

Many cultural institutions have made large digitized visual collections available online, often under permissible re-use licences. Creating interfaces for exploring and searching these collections is difficult, particularly in the absence…

Running AI models on smart edge devices can unlock versatile user experiences, but presents challenges due to limited compute and the need to handle multiple tasks simultaneously. This requires a vision encoder with small size but powerful…