A5088022579- Advanced Image and Video Retrieval Techniques
- Multimodal Machine Learning Applications
- Image Retrieval and Classification Techniques
- Data Management and Algorithms
- Advanced Data Compression Techniques
- Speech and Audio Processing
- Video Analysis and Summarization
- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Speech Recognition and Synthesis
- Algorithms and Data Compression
- Domain Adaptation and Few-Shot Learning
- Web Data Mining and Analysis
HTW Berlin - University of Applied Sciences
2023-2024
Kyungpook National University
2002
As datasets and the dimensionality of feature vectors continue to grow, Approximate Nearest Neighbor Search (ANNS) in large multimedia databases becomes increasingly relevant. Graph-based approaches have demonstrated offer best trade-off between retrieval precision search time. Despite their ability deliver times several orders magnitude faster than exact techniques, existing methods suffer from slow constructions speeds or high memory requirements. This paper presents a continuous refining...
Building on our success with the Vibro video search system in Video Browser Showdown, we are beginning a new effort by applying technologies to Lifelog Search Challenge for first time. Our approach is treat lifelog data collected given day as frames of continuous clip. While have essentially adopted text-to-image and image-to-image from Vibro, introduced various metadata filters complement capabilities. goal increase efficiency image searches within dataset integrating these improvements....
Recent advances in computer vision research led to large foundation models that generalize a broad range of image domains and perform exceptionally well various based tasks. However, content-based image-to-image retrieval is often overlooked this context. This paper investigates the effectiveness different on two challenging nearest neighbor search-based tasks: zero-shot k-NN classification. A benchmark for evaluating performance encoders their pre-training methods established, where...
Due to the size of today's image collections it can be challenging fully understand their content. Recent technological advances have enabled efficient visual search. These systems use joint and textual feature vectors identify similar images based on queries or text descriptions. Despite effectiveness, high-dimensional lead long search times for large collections. In this demonstration, we propose a solution that significantly reduces increases efficiency system. By combining two separate...
The classification error of vector quantization (VQ) is a major factor which affects the performance speech recognition. most common VQ algorithms are Linde-Buzo-Gray (LBG) algorithm and K-means algorithm, proposed by Linde et al. in 1980, have advantages being simple concept implementation with low computational costs. However using these degrades recognizer. We propose an alternative method for Korean continuous hidden Markov model (CHMM). CHMM classifies signal space into clusters each...