Related papers: EDSL: An Encoder-Decoder Architecture with Symbol-…

Few-Shot Sequence Labeling (FSSL) is a canonical paradigm for the tagging models, e.g., named entity recognition and slot filling, to generalize on an emerging, resource-scarce domain. Recently, the metric-based meta-learning framework has…

Existing emotional speech synthesis methods often utilize an utterance-level style embedding extracted from reference audio, neglecting the inherent multi-scale property of speech prosody. We introduce ED-TTS, a multi-scale emotional speech…

Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assume the degradation is fixed and known a priori. When the real…

Semantic segmentation is a classic and fundamental computer vision problem dedicated to assigning each pixel with its corresponding class. Some recent methods introduce edge-based information for improving the segmentation performance.…

Lens Distortion Encoding System (LDES) allows for a distortion-accurate workflow, with a seamless interchange of high quality motion picture images regardless of the lens source. This system is similar in a concept to the Academy Color…

Detecting local features, such as corners, segments or blobs, is the first step in the pipeline of many Computer Vision applications. Its speed is crucial for real-time applications. In this paper we present ELSED, the fastest line segment…

Different from traditional video retrieval, sign language retrieval is more biased towards understanding the semantic information of human actions contained in video clips. Previous works typically only encode RGB videos to obtain…

Entity resolution (ER) is a key data integration problem. Despite the efforts in 70+ years in all aspects of ER, there is still a high demand for democratizing ER - humans are heavily involved in labeling data, performing feature…

Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently. Due to the limited labelled data, SSMIS methods mainly focus on effectively leveraging unlabeled data to enhance the segmentation performance.…

In this paper, we demonstrate a computationally efficient new approach based on deep learning (DL) techniques for analysis, design, and optimization of electromagnetic (EM) nanostructures. We use the strong correlation among features of a…

Multimodal emotion recognition (MER) aims to identify human emotions by combining data from various modalities such as language, audio, and vision. Despite the recent advances of MER approaches, the limitations in obtaining extensive…

We introduce the SEER (Span-based Emotion Evidence Retrieval) Benchmark to test Large Language Models' (LLMs) ability to identify the specific spans of text that express emotion. Unlike traditional emotion recognition tasks that assign a…

Encoder-decoder architectures are prominent building blocks of state-of-the-art solutions for tasks across multiple fields where deep learning (DL) or foundation models play a key role. Although there is a growing community working on the…

Predicting multiple functions labeled with Enzyme Commission (EC) numbers from the enzyme sequence is of great significance but remains a challenge due to its sparse multi-label classification nature, i.e., each enzyme is typically…

Encoder-decoder models have made great progress on handwritten mathematical expression recognition recently. However, it is still a challenge for existing methods to assign attention to image features accurately. Moreover, those…

Medical image annotation typically requires expert knowledge and hence incurs time-consuming and expensive data annotation costs. To alleviate this burden, we propose a novel learning scenario, Exemplar Learning (EL), to explore automated…

Edge detection serves as a critical foundation for numerous computer vision applications, including object detection, semantic segmentation, and image editing, by extracting essential structural cues that define object boundaries and…

Recently, Dense Retrieval (DR) has become a promising solution to document retrieval, where document representations are used to perform effective and efficient semantic search. However, DR remains challenging on long documents, due to the…

Recognizing an activity with a single reference sample using metric learning approaches is a promising research field. The majority of few-shot methods focus on object recognition or face-identification. We propose a metric learning…

Over the last two decades, Electron Energy Loss Spectroscopy (EELS) imaging with a scanning transmission electron microscope (STEM) has emerged as a technique of choice for visualizing complex chemical, electronic, plasmonic, and phononic…