相关论文: Narrative Action Evaluation with Prompt-Guided Mul…

Building reliable speech systems often requires combining multiple modalities, like audio and visual cues. While such multimodal solutions frequently lead to improvements in performance and may even be critical in certain cases, they come…

Multi-modal learning, particularly among imaging and linguistic modalities, has made amazing strides in many high-level fundamental visual understanding problems, ranging from language grounding to dense event captioning. However, much of…

Driven by large-scale contrastive vision-language pre-trained models such as CLIP, recent advancements in the image-text matching task have achieved remarkable success in representation learning. Due to image-level visual-language…

Interactive and embodied tasks pose at least two fundamental challenges to existing Vision & Language (VL) models, including 1) grounding language in trajectories of actions and observations, and 2) referential disambiguation. To tackle…

Human beings have rich ways of emotional expressions, including facial action, voice, and natural languages. Due to the diversity and complexity of different individuals, the emotions expressed by various modalities may be semantically…

Recently, prompt-tuning has attracted growing interests in event argument extraction (EAE). However, the existing prompt-tuning methods have not achieved satisfactory performance due to the lack of consideration of entity information. In…

In line with the latest research, the task of identifying helpful reviews from a vast pool of user-generated textual and visual data has become a prominent area of study. Effective modal representations are expected to possess two key…

The missing modality problem poses a fundamental challenge in multimodal sentiment analysis, significantly degrading model accuracy and generalization in real world scenarios. Existing approaches primarily improve robustness through prompt…

We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions. Based on the dataset, we set up multi-choice and open-ended QA tasks…

Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and…

While neural networks have excelled in video action recognition tasks, their black-box nature often obscures the understanding of their decision-making processes. Recent approaches used inherently interpretable models to analyze video…

In this paper, we propose an effective yet efficient model PAIE for both sentence-level and document-level Event Argument Extraction (EAE), which also generalizes well when there is a lack of training data. On the one hand, PAIE utilizes…

In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios such as describing content depicted in images or videos. However, comparatively less attention has…

In recent years, large-scale pre-trained multimodal models (LMMs) generally emerge to integrate the vision and language modalities, achieving considerable success in multimodal tasks, such as text-image classification. The growing size of…

The field of multimodal robot navigation in indoor environments has garnered significant attention in recent years. However, as tasks and methods become more advanced, the action decision systems tend to become more complex and operate as…

In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…

Visual question answering by using information from multiple modalities has attracted more and more attention in recent years. However, it is a very challenging task, as the visual content and natural language have quite different…

Advances in multimodal models have greatly improved how interactions relevant to various tasks are modeled. Today's multimodal models mainly focus on the correspondence between images and text, using this for tasks like image-text matching.…

Foundation models have ushered in a new era for multimodal video understanding by enabling the extraction of rich spatiotemporal and semantic representations. In this work, we introduce a novel graph-based framework that integrates a…

This paper presents our system for the Multi-Task Learning (MTL) Challenge in the 4th Affective Behavior Analysis in-the-wild (ABAW) competition. We explore the research problems of this challenge from three aspects: 1) For obtaining…