相关论文: MVAD: A Benchmark Dataset for Multimodal AI-Genera…

Visual voice activity detection (V-VAD) uses visual features to predict whether a person is speaking or not. V-VAD is useful whenever audio VAD (A-VAD) is inefficient either because the acoustic signal is difficult to analyze or because it…

In the contemporary digital age, the proliferation of deepfakes presents a formidable challenge to the sanctity of information dissemination. Audio deepfakes, in particular, can be deceptively realistic, posing significant risks in…

Advancements in AI-synthesized human voices have created a growing threat of impersonation and disinformation, making it crucial to develop methods to detect synthetic human voices. This study proposes a new approach to identifying…

Recognizing sounds is a key aspect of computational audio scene analysis and machine perception. In this paper, we advocate that sound recognition is inherently a multi-modal audiovisual task in that it is easier to differentiate sounds…

Recent advances in Artificial Intelligence Generated Content have led to highly realistic synthetic videos, particularly in human-centric scenarios involving speech, gestures, and full-body motion, posing serious threats to information…

Publishing open-source academic video recordings is an emergent and prevalent approach to sharing knowledge online. Such videos carry rich multimodal information including speech, the facial and body movements of the speakers, as well as…

We introduce FakeParts, a new class of deepfakes characterized by subtle, localized manipulations to specific spatial regions or temporal segments of otherwise authentic videos. Unlike fully synthetic content, these partial manipulations -…

Video-to-audio (V2A) generation leverages visual-only video features to render plausible sounds that match the scene. Importantly, the generated sound onsets should match the visual actions that are aligned with them, otherwise unnatural…

Amodal segmentation and amodal content completion require using object priors to estimate occluded masks and features of objects in complex scenes. Until now, no data has provided an additional dimension for object context: the possibility…

Automatic generation of video descriptions in natural language, also called video captioning, aims to understand the visual content of the video and produce a natural language sentence depicting the objects and actions in the scene. This…

We present IMDD-1M, the first large-scale Industrial Multimodal Defect Dataset comprising 1,000,000 aligned image-text pairs, designed to advance multimodal learning for manufacturing and quality inspection. IMDD-1M contains high-resolution…

High quality fake videos and audios generated by AI-algorithms (the deep fakes) have started to challenge the status of videos and audios as definitive evidence of events. In this paper, we highlight a few of these challenges and discuss…

Video anomaly detection (VAD) plays a critical role in public safety applications such as intelligent surveillance. However, the rarity, unpredictability, and high annotation cost of real-world anomalies make it difficult to scale VAD…

With the development of deep learning and artificial intelligence, audio synthesis has a pivotal role in the area of machine learning and shows strong applicability in the industry. Meanwhile, significant efforts have been dedicated by…

The ever growing realism and quality of generated videos makes it increasingly harder for humans to spot deepfake content, who need to rely more and more on automatic deepfake detectors. However, deepfake detectors are also prone to errors,…

This paper presents a system for detecting fake audio-visual content (i.e., video deepfake), developed for Track 2 of the DDL Challenge. The proposed system employs a two-stage framework, comprising unimodal detection and multimodal score…

Industrial Anomaly Detection (IAD) is critical for quality control, but existing methods struggle with subtle, geometric defects. Standard 2D (RGB) images are sensitive to texture and lighting but often miss fine geometric anomalies. While…

Detecting forgery videos is highly desirable due to the abuse of deepfake. Existing detection approaches contribute to exploring the specific artifacts in deepfake videos and fit well on certain data. However, the growing technique on these…

Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we establish the largest public voice dataset to date, named…

Sound effect editing-modifying audio by adding, removing, or replacing elements-remains constrained by existing approaches that rely solely on low-level signal processing or coarse text prompts, often resulting in limited flexibility and…