Related papers: Advanced Sign Language Video Generation with Compr…
Our aim is to develop a unified model for sign language understanding, that performs sign language translation (SLT) and sign-subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken…
Temporal sentence grounding in videos(TSGV), which aims to localize one target segment from an untrimmed video with respect to a given sentence query, has drawn increasing attentions in the research community over the past few years.…
Sign Language Translation (SLT) is a challenging task due to its cross-domain nature, involving the translation of visual-gestural language to text. Many previous methods employ an intermediate representation, i.e., gloss sequences, to…
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…
Generating a video given the first several static frames is challenging as it anticipates reasonable future frames with temporal coherence. Besides video prediction, the ability to rewind from the last frame or infilling between the head…
Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored. We study symbolic graphics programming, where the goal is…
Sign Language (SL) enables two-way communication for the deaf and hard-of-hearing community, yet many sign languages remain under-resourced in the AI space. Sign Language Instruction Generation (SLIG) produces step-by-step textual…
Existing text-to-video diffusion models rely solely on text-only encoders for their pretraining. This limitation stems from the absence of large-scale multimodal prompt video datasets, resulting in a lack of visual grounding and restricting…
The objective of this work is to align asynchronous subtitles in sign language videos with limited labelled data. To achieve this goal, we propose a novel framework with the following contributions: (1) we leverage fundamental grammatical…
Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…
This paper introduces the unsupervised learning problem of playable video generation (PVG). In PVG, we aim at allowing a user to control the generated video by selecting a discrete action at every time step as when playing a video game. The…
Spatio-Temporal video grounding (STVG) focuses on retrieving the spatio-temporal tube of a specific object depicted by a free-form textual expression. Existing approaches mainly treat this complicated task as a parallel frame-grounding…
We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…
Video captioning, i.e. the task of generating captions from video sequences creates a bridge between the Natural Language Processing and Computer Vision domains of computer science. The task of generating a semantically accurate description…
Sign Language Translation (SLT) aims to convert sign language (SL) videos into spoken language text, thereby bridging the communication gap between the sign and the spoken community. While most existing works focus on translating a single…
We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation methods struggle with complex motions: LLM-based code synthesis fails to express fine,…
Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…
Modeling disease progression is crucial for improving the quality and efficacy of clinical diagnosis and prognosis, but it is often hindered by a lack of longitudinal medical image monitoring for individual patients. To address this…
Controllable ultra-long video generation is a fundamental yet challenging task. Although existing methods are effective for short clips, they struggle to scale due to issues such as temporal inconsistency and visual degradation. In this…
Recent advances in text-to-video generation, particularly with autoregressive models, have enabled the synthesis of high-quality videos depicting individual scenes. However, extending these models to generate long, cross-scene videos…