Related papers: Dynamicity and Durability in Scalable Visual Insta…

Characterizing noisy or ancient documents is a challenging problem up to now. Many techniques have been done in order to effectuate feature extraction and image indexation for such documents. Global approaches are in general less robust and…

Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One reason is that existing robustness benchmarks are limited, as they either rely on synthetic data or ignore the effects of individual nuisance factors.…

Analyzing large-scale performance logs from GPU profilers often requires terabytes of memory and hours of runtime, even for basic summaries. These constraints prevent timely insight and hinder the integration of performance analytics into…

Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this problem, framing the search as a continuous optimization. But…

In large-scale image retrieval, many indexing methods have been proposed to narrow down the searching scope of retrieval. The features extracted from images usually are of high dimensions or unfixed sizes due to the existence of key points.…

Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores…

Software development is a repetitive task, as developers usually reuse or get inspiration from existing implementations. Code search, which refers to the retrieval of relevant code snippets from a codebase according to the developer's…

Long traces and large event logs that originate from sensors and prediction models are becoming more common in our data-rich world. In such circumstances, conformance checking, a key task in process mining, can become computationally…

Previous works on multi-label image recognition (MLIR) usually use CNNs as a starting point for research. In this paper, we take pure Vision Transformer (ViT) as the research base and make full use of the advantages of Transformer with…

Answering connectivity queries is fundamental to fully dynamic graphs where edges and vertices are inserted and deleted frequently. Existing work proposes data structures and algorithms with worst-case guarantees. We propose a new data…

Large-scale vector databases for approximate nearest neighbor (ANN) search typically store a quantized dataset in main memory for fast access, and full precision data on remote disk. State-of-the-art ANN quantization methods are highly…

Vector search has been widely employed in recommender system and retrieval-augmented-generation pipelines, commonly performed with vector indexes to efficiently find similar items in large datasets. Recent growths in both data and task…

Transactional access to databases is an important abstraction allowing programmers to consider blocks of actions (transactions) as executing in isolation. The strongest consistency model is {\em serializability}, which ensures the atomicity…

Approximate Nearest Neighbor Search (ANNS) in high-dimensional space is an essential operator in many online services, such as information retrieval and recommendation. Indices constructed by the state-of-the-art ANNS algorithms must be…

Dense high dimensional vectors are becoming increasingly vital in fields such as computer vision, machine learning, and large language models (LLMs), serving as standard representations for multimodal data. Now the dimensionality of these…

Maintaining or improving the performance of Deep Neural Networks (DNNs) through fine-tuning requires labeling newly collected inputs, a process that is often costly and time-consuming. To alleviate this problem, input selection approaches…

Vision Transformers (ViTs) enable strong multi-view 3D detection but are limited by high inference latency from dense token and query processing across multiple views and large 3D regions. Existing sparsity methods, designed mainly for 2D…

Contrary to the other resources such as CPU, memory, and network, for which virtualization is efficiently achieved through direct access, disk virtualization is peculiar. In this paper, we make four contributions. Our first contribution is…

Visual analytics is essential for studying large time series due to its ability to reveal trends, anomalies, and insights. DeepVATS is a tool that merges Deep Learning (Deep) with Visual Analytics (VA) for the analysis of large time series…

Clustering in high-dimensional settings with severe feature noise remains challenging, especially when only a small subset of dimensions is informative and the final number of clusters is not specified in advance. In such regimes, partition…