The rise of generative AI is transforming the landscape of digital imagery, and exerting a significant influence on online creative communities. This has led to the emergence of AI-Generated Content (AIGC) social platforms, such as Civitai. These distinctive social platforms allow users to build and share their own generative AI models, thereby enhancing the potential for more diverse artistic expression. Designed in the vein of social networks, they also provide artists with the means to showcase their creations (generated from the models), engage in discussions, and obtain feedback, thus nurturing a sense of community. Yet, this openness also raises concerns about the abuse of such platforms, e.g., using models to disseminate deceptive deepfakes or infringe upon copyrights. To explore this, we conduct the first comprehensive empirical study of an AIGC social platform, focusing on its use for generating abusive content. As an exemplar, we construct a comprehensive dataset covering Civitai, the largest available AIGC social platform. Based on this dataset of 87K models and 2M images, we explore the characteristics of content and discuss strategies for moderation to better govern these platforms.

The nascent topic of fake news requires automatic detection methods to quickly learn from limited annotated samples. Therefore, the capacity to rapidly acquire proficiency in a new task with limited guidance, also known as few-shot learning, is critical for detecting fake news in its early stages. Existing approaches either involve fine-tuning pre-trained language models which come with a large number of parameters, or training a complex neural network from scratch with large-scale annotated datasets. This paper presents a multimodal fake news detection model which augments multimodal features using unimodal features. For this purpose, we introduce Cross-Modal Augmentation (CMA), a simple approach for enhancing few-shot multimodal fake news detection by transforming n-shot classification into a more robust (n $\times$ z)-shot problem, where z represents the number of supplementary features. The proposed CMA achieves SOTA results over three benchmark datasets, utilizing a surprisingly simple linear probing method to classify multimodal fake news with only a few training samples. Furthermore, our method is significantly more lightweight than prior approaches, particularly in terms of the number of trainable parameters and epoch times. The code is available here: \url{https://github.com/zgjiangtoby/FND_fewshot}

Automated choreography advances by generating dance from music. Current methods create skeleton keypoint sequences, not full dance videos, and cannot make specific individuals dance, limiting their real-world use. These methods also need precise keypoint annotations, making data collection difficult and restricting the use of self-made video datasets. To overcome these challenges, we introduce a novel task: generating dance videos directly from images of individuals guided by music. This task enables the dance generation of specific individuals without requiring keypoint annotations, making it more versatile and applicable to various situations. Our solution, the Dance Any Beat Diffusion model (DabFusion), utilizes a reference image and a music piece to generate dance videos featuring various dance types and choreographies. The music is analyzed by our specially designed music encoder, which identifies essential features including dance style, movement, and rhythm. DabFusion excels in generating dance videos not only for individuals in the training dataset but also for any previously unseen person. This versatility stems from its approach of generating latent optical flow, which contains all necessary motion information to animate any person in the image. We evaluate DabFusion's performance using the AIST++ dataset, focusing on video quality, audio-video synchronization, and motion-music alignment. We propose a 2D Motion-Music Alignment Score (2D-MM Align), which builds on the Beat Alignment Score to more effectively evaluate motion-music alignment for this new task. Experiments show that our DabFusion establishes a solid baseline for this innovative task. Video results can be found on our project page: https://DabFusion.github.io.

Good weight initialization serves as an effective measure to reduce the training cost of a deep neural network (DNN) model. The choice of how to initialize parameters is challenging and may require manual tuning, which can be time-consuming and prone to human error. To overcome such limitations, this work takes a novel step towards building a weight generator to synthesize the neural weights for initialization. We use the image-to-image translation task with generative adversarial networks (GANs) as an example due to the ease of collecting model weights spanning a wide range. Specifically, we first collect a dataset with various image editing concepts and their corresponding trained weights, which are later used for the training of the weight generator. To address the different characteristics among layers and the substantial number of weights to be predicted, we divide the weights into equal-sized blocks and assign each block an index. Subsequently, a diffusion model is trained with such a dataset using both text conditions of the concept and the block indexes. By initializing the image translation model with the denoised weights predicted by our diffusion model, the training requires only 43.3 seconds. Compared to training from scratch (i.e., Pix2pix), we achieve a 15x training time acceleration for a new concept while obtaining even better image generation quality.

Digital image manipulation has become increasingly accessible and realistic with the advent of generative AI technologies. Recent developments allow for text-guided inpainting, making sophisticated image edits possible with minimal effort. This poses new challenges for digital media forensics. For example, diffusion model-based approaches could either splice the inpainted region into the original image, or regenerate the entire image. In the latter case, traditional image forgery localization (IFL) methods typically fail. This paper introduces the Text-Guided Inpainting Forgery (TGIF) dataset, a comprehensive collection of images designed to support the training and evaluation of image forgery localization and synthetic image detection (SID) methods. The TGIF dataset includes approximately 80k forged images, originating from popular open-source and commercial methods; SD2, SDXL, and Adobe Firefly. Using this data, we benchmark several state-of-the-art IFL and SID methods. Whereas traditional IFL methods can detect spliced images, they fail to detect regenerated inpainted images. Moreover, traditional SID may detect the regenerated inpainted images to be fake, but cannot localize the inpainted area. Finally, both types of methods fail when exposed to stronger compression, while they are less robust to modern compression algorithms, such as WEBP. As such, this work demonstrates the inefficiency of state-of-the-art detectors on local manipulations performed by modern generative approaches, and aspires to help with the development of more capable IFL and SID methods. The dataset can be downloaded at https://github.com/IDLabMedia/tgif-dataset.

Recent work integrating Large Language Models (LLMs) has led to significant improvements in the Knowledge Base Question Answering (KBQA) task. However, we posit that existing KBQA datasets that either have simple questions, use synthetically generated logical forms, or are based on small knowledge base (KB) schemas, do not capture the true complexity of KBQA tasks. To address this, we introduce the SPINACH dataset, an expert-annotated KBQA dataset collected from forum discussions on Wikidata's "Request a Query" forum with 320 decontextualized question-SPARQL pairs. Much more complex than existing datasets, SPINACH calls for strong KBQA systems that do not rely on training data to learn the KB schema, but can dynamically explore large and often incomplete schemas and reason about them. Along with the dataset, we introduce the SPINACH agent, a new KBQA approach that mimics how a human expert would write SPARQLs for such challenging questions. Experiments on existing datasets show SPINACH's capability in KBQA, achieving a new state of the art on the QALD-7, QALD-9 Plus and QALD-10 datasets by 30.1%, 27.0%, and 10.0% in F1, respectively, and coming within 1.6% of the fine-tuned LLaMA SOTA model on WikiWebQuestions. On our new SPINACH dataset, SPINACH agent outperforms all baselines, including the best GPT-4-based KBQA agent, by 38.1% in F1.

This exploration has yielded important findings in political sciences (Mintz et al., 2022), sociology (Bericat, 2016; Turner & Stets, 2006), economics (Loewenstein, 2000), anthropology (Lutz & White, 1986), organizational research (Diener et al., 2020) as well other fields of social (Kleef, 2018) and psychological sciences (Derks et al., 2008). While investigating this role of emotions, many researchers concentrate on the question of whether an emotion is present, focusing on the categorical aspects of emotions (Fritz et al., 2009; Saarimäki et al., 2016; Siedlecka & Denson, 2019; Tanaka-Matsumi et al., 1995). However, beyond the sole presence or absence of emotions, there is also their intensity, which was early recognized as necessary to understand human behaviors (Brehm, 1999; Plutchik, 1965). People often describe emotions like anger, sadness, or happiness in varying degrees, from none at all to very intense, and research indicates that emotion intensity is crucial in cognitive processing, social behavior, and communication within groups (Frijda et al., 1992; Niedenthal & Brauer, 2012; Reisenzein, 1994).

While the use of machine learning for the detection of propaganda techniques in text has garnered considerable attention, most approaches focus on "black-box" solutions with opaque inner workings. Interpretable approaches provide a solution, however, they depend on careful feature engineering and costly expert annotated data. Additionally, language features specific to propagandistic text are generally the focus of rhetoricians or linguists, and there is no data set labeled with such features suitable for machine learning. This study codifies 22 rhetorical and linguistic features identified in literature related to the language of persuasion for the purpose of annotating an existing data set labeled with propaganda techniques. To help human experts annotate natural language sentences with these features, RhetAnn, a web application, was specifically designed to minimize an otherwise considerable mental effort. Finally, a small set of annotated data was used to fine-tune GPT-3.5, a generative large language model (LLM), to annotate the remaining data while optimizing for financial cost and classification accuracy. This study demonstrates how combining a small number of human annotated examples with GPT can be an effective strategy for scaling the annotation process at a fraction of the cost of traditional annotation relying solely on human experts. The results are on par with the best performing model at the time of writing, namely GPT-4, at 10x less the cost. Our contribution is a set of features, their properties, definitions, and examples in a machine-readable format, along with the code for RhetAnn and the GPT prompts and fine-tuning procedures for advancing state-of-the-art interpretable propaganda technique detection.

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of text-based speaker identification (SpeakerID) has received limited attention, lacking large-scale, diverse datasets for effective model training. Addressing these gaps, we present a novel, large-scale dataset derived from the MediaSum corpus, encompassing transcripts from a wide range of media sources. We propose novel transformer-based models tailored for SpeakerID, leveraging contextual cues within dialogues to accurately attribute speaker names. Through extensive experiments, our best model achieves a great precision of 80.3\%, setting a new benchmark for SpeakerID. The data and code are publicly available here: \url{https://github.com/adobe-research/speaker-identification}

Universal sound separation (USS) is a task of separating mixtures of arbitrary sound sources. Typically, universal separation models are trained from scratch in a supervised manner, using labeled data. Self-supervised learning (SSL) is an emerging deep learning approach that leverages unlabeled data to obtain task-agnostic representations, which can benefit many downstream tasks. In this paper, we propose integrating a self-supervised pre-trained model, namely the audio masked autoencoder (A-MAE), into a universal sound separation system to enhance its separation performance. We employ two strategies to utilize SSL embeddings: freezing or updating the parameters of A-MAE during fine-tuning. The SSL embeddings are concatenated with the short-time Fourier transform (STFT) to serve as input features for the separation model. We evaluate our methods on the AudioSet dataset, and the experimental results indicate that the proposed methods successfully enhance the separation performance of a state-of-the-art ResUNet-based USS model.