Related papers: Logos as a Well-Tempered Pre-train for Sign Langua…
People with vocal and hearing disabilities use sign language to express themselves using visual gestures and signs. Although sign language is a solution for communication difficulties faced by deaf people, there are still problems as most…
Models of sign language have historically lagged behind those for spoken language (text and speech). Recent work has greatly improved their performance on tasks like sign language translation and isolated sign recognition. However, it…
Sign languages, used by around 70 million Deaf individuals globally, are visual languages that convey visual and contextual information. Current methods in vision-based sign language recognition (SLR) and translation (SLT) struggle with…
Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based…
Existing logo detection methods usually consider a small number of logo classes and limited images per class with a strong assumption of requiring tedious object bounding box annotations, therefore not scalable to real-world dynamic…
Self-supervised learning (SSL) to learn high-level speech representations has been a popular approach to building Automatic Speech Recognition (ASR) systems in low-resource settings. However, the common assumption made in literature is that…
Logo detection in unconstrained images is challenging, particularly when only very sparse labelled training images are accessible due to high labelling costs. In this work, we describe a model training image synthesising method capable of…
AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing signs as individual words or as complete sentences. We introduce…
Open-set semi-supervised learning (OSSL) embodies a practical scenario within semi-supervised learning, wherein the unlabeled training set encompasses classes absent from the labeled set. Many existing OSSL methods assume that these…
Zero-Shot Learning (ZSL) has rapidly advanced in recent years. Towards overcoming the annotation bottleneck in the Sign Language Recognition (SLR), we explore the idea of Zero-Shot Sign Language Recognition (ZS-SLR) with no annotated visual…
Emotion Recognition in Conversation is a core component of affective computing, while current resources of sign language emotion datasets primarily focus on isolated sentences and lack conversational context. Models trained exclusively on…
Early cancer detection is crucial for prognosis, but many cancer types lack large labelled datasets required for developing deep learning models. This paper investigates self-supervised learning (SSL) as an alternative to the standard…
Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on meta…
Sign Language Translation (SLT) is a task that has not been studied relatively much compared to the study of Sign Language Recognition (SLR). However, the SLR is a study that recognizes the unique grammar of sign language, which is…
Previous Sign Language Translation (SLT) methods achieve superior performance by relying on gloss annotations. However, labeling high-quality glosses is a labor-intensive task, which limits the further development of SLT. Although some…
Subtle hand differences make sign language recognition challenging, yet many existing methods rely on encoders pretrained on generic action datasets that poorly capture such fine-grained cues. We propose a self-supervised pretraining method…
Typically, spoken language understanding (SLU) models are trained on annotated data which are costly to gather. Aiming to reduce data needs for bootstrapping a SLU system for a new language, we present a simple but effective weight transfer…
Recent methods that integrate spatial layouts with text for document understanding in large language models (LLMs) have shown promising results. A commonly used method is to represent layout information as text tokens and interleave them…
Different from the traditional supervised learning in which each training example has only one explicit label, superset label learning (SLL) refers to the problem that a training example can be associated with a set of candidate labels, and…
Translating natural languages into sign languages is a highly complex and underexplored task. Despite growing interest in accessibility and inclusivity, the development of robust translation systems remains hindered by the limited…