Related papers: Designing an interface to optimize reading with sm…
Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is…
Real-world applications are stretching context windows to hundreds of thousand of tokens while Large Language Models (LLMs) swell from billions to trillions of parameters. This dual expansion send compute and memory costs skyrocketing,…
Video text spotting is still an important research topic due to its various real-applications. Previous approaches usually fall into the four-staged pipeline: text detection in individual images, framewisely recognizing localized text…
Cross-encoders are effective passage and document re-rankers but less efficient than other neural or classic retrieval models. A few previous studies have applied windowed self-attention to make cross-encoders more efficient. However, these…
Multimodal Large Language Models (MLLMs) have shown exceptional capabilities in vision-language tasks; however, effectively integrating image segmentation into these models remains a significant challenge. In this paper, we introduce…
Neural summarization models suffer from the fixed-size input limitation: if text length surpasses the model's maximal number of input tokens, some document content (possibly summary-relevant) gets truncated Independently summarizing windows…
Over the past decade, the demand for communication devices has increased among individuals with mobility and speech impairments. Eye-gaze tracking has emerged as a promising solution for hands-free communication; however, traditional…
Pie menus are suggested as powerful tool for eye gaze based text entry among various interfaces developed so far. If pie menus are used with multiple depth layers then multiple saccades are required per selection of item, which is…
Presenters commonly use slides as visual aids for informative talks. When presenters fail to verbally describe the content on their slides, blind and visually impaired audience members lose access to necessary content, making the…
Background/Context: Currently, the usual interface for visualizing data is based on 2-D screens. Recently, devices capable of visualizing data while immersed in VR scenes are becoming common. However, it has not been studied in detail to…
Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…
Due to increasing interest in adapting models on resource-constrained edges, parameter-efficient transfer learning has been widely explored. Among various methods, Visual Prompt Tuning (VPT), prepending learnable prompts to input space,…
In this paper, we work to bring telepresence to every desktop. Unlike commercial systems, personal 3D video conferencing systems must render high-quality videos while remaining financially and computationally viable for the average…
In this paper we address the question of how to render sequence-level networks better at handling structured input. We propose a machine reading simulator which processes text incrementally from left to right and performs shallow reasoning…
Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…
In this study, we propose two novel input processing paradigms for novel view synthesis (NVS) methods based on layered scene representations that significantly improve their runtime without compromising quality. Our approach identifies and…
In any search-based digital library (DL) systems dealing with a non-trivial number of documents, users are often required to go through a long list of short document descriptions in order to identify what they are looking for. To tackle the…
A recent technology known as transparent screens is transforming windows into displays. These smart windows are present in buses, airports and offices. They can remain transparent, as a normal window, or display relevant information that…
PageRank is a fundamental link analysis algorithm that also functions as a key representative of the performance of Sparse Matrix-Vector (SpMV) multiplication. The traditional PageRank implementation generates fine granularity random memory…
Recent end-to-end trainable methods for scene text spotting, integrating detection and recognition, showed much progress. However, most of the current arbitrary-shape scene text spotters use region proposal networks (RPN) to produce…