Related papers: SignNet: Single Channel Sign Generation using Metr…
Recent image-to-image (I2I) translation algorithms focus on learning the mapping from a source to a target domain. However, the continuous translation problem that synthesizes intermediate results between two domains has not been…
In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that often depend on multi-stage intermediate pre-training…
Text-to-image (T2I) generation has advanced rapidly, making reliable evaluation critical as performance differences between models narrow. Existing evaluation practices typically apply uniform annotation mechanisms, such as Likert-scale or…
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without…
Semi-supervised learning is a challenging problem which aims to construct a model by learning from a limited number of labeled examples. Numerous methods have been proposed to tackle this problem, with most focusing on utilizing the…
In the past decades the set of human tasks that are solved by machines was extended dramatically. From simple image classification problems researchers now move towards solving more sophisticated and vital problems, like, autonomous driving…
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…
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently. Most leading WSSS…
Communication barriers pose significant challenges for individuals with hearing and speech impairments, often limiting their ability to effectively interact in everyday environments. This project introduces a real-time assistive technology…
Capturing and annotating Sign language datasets is a time consuming and costly process. Current datasets are orders of magnitude too small to successfully train unconstrained \acf{slt} models. As a result, research has turned to TV…
Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks like the Massive Text Embedding Benchmark (MTEB), has…
Multitask learning has shown promising performance in many applications and many multitask models have been proposed. In order to identify an effective multitask model for a given multitask problem, we propose a learning framework called…
Sign languages are visual languages, with vocabularies as rich as their spoken language counterparts. However, current deep-learning based Sign Language Production (SLP) models produce under-articulated skeleton pose sequences from…
In this paper, we propose a dual-condition diffusion pre-training model named SignDiff that can generate human sign language speakers from a skeleton pose. SignDiff has a novel Frame Reinforcement Network called FR-Net, similar to dense…
Existing Sign Language Learning applications focus on the demonstration of the sign in the hope that the student will copy a sign correctly. In these cases, only a teacher can confirm that the sign was completed correctly, by reviewing a…
Many remote sensing applications employ masking of pixels in satellite imagery for subsequent measurements. For example, estimating water quality variables, such as Suspended Sediment Concentration (SSC) requires isolating pixels depicting…
The complexity of Sign Language (SL) data processing brings many challenges. The current approach to recognition of SL signs aims to translate RGB sign language videos through pose information into Word-based ID Glosses, which serve to…
We introduce a text-to-speech(TTS) framework based on a neural transducer. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic…
Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…
Recent advances in sign language research have benefited from CNN-based backbones, which are primarily transferred from traditional computer vision tasks (\eg object identification, image recognition). However, these CNN-based backbones…