Related papers: MemPromptTSS: Persistent Prompt Memory for Iterati…

The demand for low-power inference and training of deep neural networks (DNNs) on edge devices has intensified the need for algorithms that are both scalable and energy-efficient. While spiking neural networks (SNNs) allow for efficient…

Few-Shot Video Object Segmentation (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. However, this task was seldom explored. In this work, based on IPMT, a state-of-the-art…

Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework. However, the modality incompleteness in multi-modal…

In the era of information explosion, spatio-temporal data mining serves as a critical part of urban management. Considering the various fields demanding attention, e.g., traffic state, human activity, and social event, predicting multiple…

The goal of interactive image segmentation is to delineate specific regions within an image via visual or language prompts. Low-latency and high-quality interactive segmentation with diverse prompts remain challenging for existing…

Streaming recognition and segmentation of multi-party conversations with overlapping speech is crucial for the next generation of voice assistant applications. In this work we address its challenges discovered in the previous work on…

Introducing explicit constraints on the structural predictions has been an effective way to improve the performance of semantic segmentation models. Existing methods are mainly based on insufficient hand-crafted rules that only partially…

The Segment Anything Model (SAM) excels at general image segmentation but has limited ability to understand natural language, which restricts its direct application in Referring Expression Segmentation (RES). Toward this end, we propose…

Memory profiling captures programs' dynamic memory behavior, assisting programmers in debugging, tuning, and enabling advanced compiler optimizations like speculation-based automatic parallelization. As each use case demands its unique…

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and…

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…

Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…

The development of machine learning models for CT imaging depends on the availability of large, high-quality, and diverse annotated datasets. Although large volumes of CT images and reports are readily available in clinical picture…

Single-point annotation is increasingly prominent in visual tasks for labeling cost reduction. However, it challenges tasks requiring high precision, such as the point-prompted instance segmentation (PPIS) task, which aims to estimate…

Recent advances in promptable segmentation, such as the Segment Anything Model (SAM), have enabled flexible, high-quality mask generation across a wide range of visual domains. However, SAM and similar models remain fundamentally…

In recent years, large-scale pre-trained multimodal models (LMM) generally emerge to integrate the vision and language modalities, achieving considerable success in various natural language processing and computer vision tasks. The growing…

Recent advances in fine-tuning large language models (LLMs) have greatly enhanced their usage in domain-specific tasks. Despite the success, fine-tuning continues to rely on repeated and lengthy prompts, which escalate computational…

Time series, spatial data, and images are natural applications of Neural Processes. However, when such data exhibit strong periodicity and quasi-periodicity, existing methods often suffer from underfitting and generalise poorly beyond the…

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial…