Related papers: Hierarchical Feature Alignment for Gloss-Free Sign…
Sign languages are multi-channel languages that communicate information through not just the hands (manual signals) but also facial expressions and upper body movements (non-manual signals). However, since automatic sign language…
It has recently been discovered that using a pre-trained vision-language model (VLM), e.g., CLIP, to align a whole query image with several finer text descriptions generated by a large language model can significantly enhance zero-shot…
Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate then summarize or summarize then translate.…
Video-language embeddings are a promising avenue for injecting semantics into visual representations, but existing methods capture only short-term associations between seconds-long video clips and their accompanying text. We propose HierVL,…
We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation in a fully self-supervised manner. Recent pre-training methods in NLP focus on learning either bottom or top-level…
Automatic sign language processing is gaining popularity in Natural Language Processing (NLP) research (Yin et al., 2021). In machine translation (MT) in particular, sign language translation based on glosses is a prominent approach. In…
Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which…
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual…
Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignment and…
Continuous sign language recognition (SLR) deals with unaligned video-text pair and uses the word error rate (WER), i.e., edit distance, as the main evaluation metric. Since it is not differentiable, we usually instead optimize the learning…
This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…
Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level structure. Prior methods often improve this ability through…
The recent development of Video-based Large Language Models (VideoLLMs), has significantly advanced video summarization by aligning video features and, in some cases, audio features with Large Language Models (LLMs). Each of these VideoLLMs…
Recent advancement of large language models (LLMs) has led to significant breakthroughs across various tasks, laying the foundation for the development of LLM-based speech translation systems. Existing methods primarily focus on aligning…
Multilingual automatic speech recognition (ASR) systems have garnered attention for their potential to extend language coverage globally. While self-supervised learning (SSL) models, like MMS, have demonstrated their effectiveness in…
The zero-shot open-vocabulary challenge in image classification is tackled by pretrained vision-language models like CLIP, which benefit from incorporating class-specific knowledge from large language models (LLMs) like ChatGPT. However,…
Cross-lingual summarization (CLS) aims to generate a summary for the source text in a different target language. Currently, instruction-tuned large language models (LLMs) excel at various English tasks. However, unlike languages such as…
Instructional videos are a common source for learning text-video or even multimodal representations by leveraging subtitles extracted with automatic speech recognition systems (ASR) from the audio signal in the videos. However, in contrast…
Many continuous sign language recognition (CSLR) studies adopt transformer-based architectures for sequence modeling due to their powerful capacity for capturing global contexts. Nevertheless, vanilla self-attention, which serves as the…
Spoken Language Models (SLMs) aim to learn linguistic competence directly from speech using discrete units, widening access to Natural Language Processing (NLP) technologies for languages with limited written resources. However, progress…