Related papers: Zero-Shot Fake Video Detection by Audio-Visual Con…
Learning how objects sound from video is challenging, since they often heavily overlap in a single audio channel. Current methods for visually-guided audio source separation sidestep the issue by training with artificially mixed video…
In industrial anomaly detection (IAD), accurately identifying defects amidst diverse anomalies and under varying imaging conditions remains a significant challenge. Traditional approaches often struggle with high false-positive rates,…
The identification of source cameras from videos, though it is a highly relevant forensic analysis topic, has been studied much less than its counterpart that uses images. In this work we propose a method to identify the source camera of a…
Accurate video moment retrieval (VMR) requires universal visual-textual correlations that can handle unknown vocabulary and unseen scenes. However, the learned correlations are likely either biased when derived from a limited amount of…
Deepfake videos are causing growing concerns among communities due to their ever-increasing realism. Naturally, automated detection of forged Deepfake videos is attracting a proportional amount of interest of researchers. Current methods…
General-purpose ID, or travel, document image- and video-based verification systems have yet to achieve good enough performance to be considered a solved problem. There are several factors that negatively impact their performance, including…
Video forgery attack threatens the surveillance system by replacing the video captures with unrealistic synthesis, which can be powered by the latest augment reality and virtual reality technologies. From the machine perception aspect,…
Video recognition models are typically trained on fixed taxonomies which are often too coarse, collapsing distinctions in object, manner or outcome under a single label. As tasks and definitions evolve, such models cannot accommodate…
Quarter sampling is a novel sensor design that allows for an acquisition of higher resolution images without increasing the number of pixels. When being used for video data, one out of four pixels is measured in each frame. Effectively,…
Dense video captioning, a task of localizing meaningful moments and generating relevant captions for videos, often requires a large, expensive corpus of annotated video segments paired with text. In an effort to minimize the annotation…
With the continuous development of deep learning-based speech conversion and speech synthesis technologies, the cybersecurity problem posed by fake audio has become increasingly serious. Previously proposed models for defending against fake…
Large-scale text-to-video diffusion models have demonstrated an exceptional ability to synthesize diverse videos. However, due to the lack of extensive text-to-video datasets and the necessary computational resources for training, directly…
The escalating quality of video generated by advanced video generation methods results in new security challenges, while there have been few relevant research efforts: 1) There is no open-source dataset for generated video detection, 2) No…
Detecting relevant changes is a fundamental problem of video surveillance. Because of the high variability of data and the difficulty of properly annotating changes, unsupervised methods dominate the field. Arguably one of the most critical…
Evaluation of automatic video summaries is a challenging problem. In the past years, some evaluation methods are presented that utilize only a single feature like color feature to detect similarity between automatic video summaries and…
Given an untrimmed video and a language query depicting a specific temporal moment in the video, video grounding aims to localize the time interval by understanding the text and video simultaneously. One of the most challenging issues is an…
Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due to various practical concerns, e.g., data privacy or new surveillance deployments.…
State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…
Recent one-shot video tuning methods, which fine-tune the network on a specific video based on pre-trained text-to-image models (e.g., Stable Diffusion), are popular in the community because of the flexibility. However, these methods often…
The growing demand for surveillance in public spaces presents significant challenges due to the shortage of human resources. Current AI-based video surveillance systems heavily rely on core computer vision models that require extensive…