Related papers: Progressive Homeostatic and Plastic Prompt Tuning …
Prompt engineering is a powerful tool used to enhance the performance of pre-trained models on downstream tasks. For example, providing the prompt "Let's think step by step" improved GPT-3's reasoning accuracy to 63% on MutiArith while…
Visual speech recognition is the task to decode the speech content from a video based on visual information, especially the movements of lips. It is also referenced as lipreading. Motivated by two problems existing in lipreading, words with…
Continual learning aims to learn a model from a continuous stream of data, but it mainly assumes a fixed number of data and tasks with clear task boundaries. However, in real-world scenarios, the number of input data and tasks is constantly…
Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed architecture has been…
Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most existing object…
Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync…
Weakly-supervised audio-visual video parsing (AVVP) seeks to detect audible, visible, and audio-visual events without temporal annotations. Previous work has emphasized refining global predictions through contrastive or collaborative…
Prompt tuning offers a parameter-efficient way to adapt large pre-trained language models to new tasks, but most existing approaches are designed for single-task settings, failing to share knowledge across related tasks. We propose…
Recently, vision transformer based multimodal learning methods have been proposed to improve the robustness of face anti-spoofing (FAS) systems. However, multimodal face data collected from the real world is often imperfect due to missing…
Prompt learning is an effective way to exploit the potential of large-scale pre-trained foundational models. Continuous prompts parameterize context tokens in prompts by turning them into differentiable vectors. Deep continuous prompts…
This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer…
Visual Planning for Assistance (VPA) aims to predict a sequence of user actions required to achieve a specified goal based on a video showing the user's progress. Although recent advances in multimodal large language models (MLLMs) have…
Prompt-learning-based multi-modal trackers have made strong progress by using lightweight visual adapters to inject auxiliary-modality cues into frozen foundation models. However, they still underutilize two essentials: modality-specific…
Audio-visual learning seeks to enhance the computer's multi-modal perception leveraging the correlation between the auditory and visual modalities. Despite their many useful downstream tasks, such as video retrieval, AR/VR, and…
Multi-step LLM pipelines can solve complex tasks, but jointly optimizing prompts across steps remains challenging due to missing step-level supervision and inter-step dependency. We propose ADOPT, an adaptive dependency-guided joint prompt…
Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, existing approaches often fail to capture the complex,…
While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively…
Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos. Recent works focus on learning the cross-modal alignment between…
In expressive and controllable Text-to-Speech (TTS), explicit prosodic features significantly improve the naturalness and controllability of synthesised speech. However, manual prosody annotation is labor-intensive and inconsistent. To…