Generating high quality music that complements the visual content of a video is a challenging task. Most existing visual conditioned music generation systems generate symbolic music data, such as MIDI files, instead of raw audio waveform. Given the limited availability of symbolic music data, such methods can only generate music for a few instruments or for specific types of visual input. In this paper, we propose a novel approach called V2Meow that can generate high-quality music audio that aligns well with the visual semantics of a diverse range of video input types. Specifically, the proposed music generation system is a multi-stage autoregressive model which is trained with a number of O(100K) music audio clips paired with video frames, which are mined from in-the-wild music videos, and no parallel symbolic music data is involved. V2Meow is able to synthesize high-fidelity music audio waveform solely conditioned on pre-trained visual features extracted from an arbitrary silent video clip, and it also allows high-level control over the music style of generation examples via supporting text prompts in addition to the video frames conditioning. Through both qualitative and quantitative evaluations, we demonstrate that our model outperforms several existing music generation systems in terms of both visual-audio correspondence and audio quality.

Understanding users' intentions in e-commerce platforms requires commonsense knowledge. In this paper, we present FolkScope, an intention knowledge graph construction framework to reveal the structure of humans' minds about purchasing items. As commonsense knowledge is usually ineffable and not expressed explicitly, it is challenging to perform information extraction. Thus, we propose a new approach that leverages the generation power of large language models~(LLMs) and human-in-the-loop annotation to semi-automatically construct the knowledge graph. LLMs first generate intention assertions via e-commerce-specific prompts to explain shopping behaviors, where the intention can be an open reason or a predicate falling into one of 18 categories aligning with ConceptNet, e.g., IsA, MadeOf, UsedFor, etc. Then we annotate plausibility and typicality labels of sampled intentions as training data in order to populate human judgments to all automatic generations. Last, to structurize the assertions, we propose pattern mining and conceptualization to form more condensed and abstract knowledge. Extensive evaluations and studies demonstrate that our constructed knowledge graph can well model e-commerce knowledge and have many potential applications.

Artistic pieces can be studied from several perspectives, one example being their reception among readers over time. In the present work, we approach this interesting topic from the standpoint of literary works, particularly assessing the task of predicting whether a book will become a best seller. Dissimilarly from previous approaches, we focused on the full content of books and considered visualization and classification tasks. We employed visualization for the preliminary exploration of the data structure and properties, involving SemAxis and linear discriminant analyses. Then, to obtain quantitative and more objective results, we employed various classifiers. Such approaches were used along with a dataset containing (i) books published from 1895 to 1924 and consecrated as best sellers by the Publishers Weekly Bestseller Lists and (ii) literary works published in the same period but not being mentioned in that list. Our comparison of methods revealed that the best-achieved result -- combining a bag-of-words representation with a logistic regression classifier -- led to an average accuracy of 0.75 both for the leave-one-out and 10-fold cross-validations. Such an outcome suggests that it is unfeasible to predict the success of books with high accuracy using only the full content of the texts. Nevertheless, our findings provide insights into the factors leading to the relative success of a literary work.

Answering factual questions with temporal intent over knowledge graphs (temporal KGQA) attracts rising attention in recent years. In the generation of temporal queries, existing KGQA methods ignore the fact that some intrinsic connections between events can make them temporally related, which may limit their capability. We systematically analyze the possible interpretation of temporal constraints and conclude the interpretation structures as the Semantic Framework of Temporal Constraints, SF-TCons. Based on the semantic framework, we propose a temporal question answering method, SF-TQA, which generates query graphs by exploring the relevant facts of mentioned entities, where the exploring process is restricted by SF-TCons. Our evaluations show that SF-TQA significantly outperforms existing methods on two benchmarks over different knowledge graphs.

This document presents some early explorations of applying Softly Masked Language Modelling (SMLM) to symbolic music generation. SMLM can be seen as a generalisation of masked language modelling (MLM), where instead of each element of the input set being either known or unknown, each element can be known, unknown or partly known. We demonstrate some results of applying SMLM to constrained symbolic music generation using a transformer encoder architecture. Several audio examples are available at https://erl-j.github.io/smlm-web-supplement/

More AI-generated music mimicking a famous artist has made the rounds -- while making lots of money for the scammer passing it off as genuine. A collection of fake Frank Ocean songs sold for a reported $13,000 CAD ($9,722 in US dollars) last month on a music-leaking forum devoted to the Grammy-winning singer, according to Vice. If the story sounds familiar, it's essentially a recycling of last month's AI Drake / The Weeknd fiasco. It's also caused headaches for Spotify, which recently pulled not just Fake Drake but tens of thousands of other AI-generated tracks after receiving complaints from Universal Music. The scammer, who used the handle mourningassasin, told Vice they hired someone to make "around nine" Ocean songs using "very high-quality vocal snippets" of the Thinkin Bout You singer's voice.

AI-generated music has been in the spotlight lately, between a track that seemingly featured vocals from Drake and The Weeknd gaining traction to Spotify reportedly removing thousands of songs over concerns that people were using them to game the system. Now, Google is wading further into that space as the company is opening up access to its text-to-music AI, which is called MusicLM. Google detailed the system back in January when it published research on MusicLM. The generative AI landscape has shifted dramatically this year, however, and now Google feels comfortable enough to let the public try MusicLM. "We've been working with musicians like Dan Deacon and hosting workshops to see how this technology can empower the creative process," Google Research product manager Hema Manickavasagam and Google Labs product manager Kristin Yim wrote in a blog post.

Sen. John Kennedy, R-La., joined'America's Newsroom' to discuss the significance of Sen. Feinstein's absence amid the push to confirm Biden's judicial nominees. OpenAI CEO Sam Altman will testify before Congress next week, a major step for lawmakers seeking to understand and regulate the fast-moving industry of artificial intelligence. Altman's company is the developer behind ChatGPT, the AI chatbot that captured the nation's attention late last year, with Americans using it for everything from medical advice to cheating on homework. The AI guru will appear before the Senate Judiciary subcommittee on privacy, technology, and the law on Tuesday. "Artificial intelligence will be transformative in ways we can't even imagine, with implications for Americans' elections, jobs, and security," Sen. Josh Hawley, R-Mo., said in a statement ahead of the hearing.

Kurt "The Cyberguy" Knutsson explains how scientists managed to turn dead birds into drones that can potentially spy on people. Remember the satirical "Birds Aren't Real" conspiracy theory that took the internet by storm, claiming that birds were not real animals – instead, government surveillance drones? Well, you might want to hold onto your feathers because it seems researchers have accidentally turned this seemingly outlandish concept into a reality. What are these "Bird Drones"? In a groundbreaking project published by the American Institute of Aeronautics and Astronautics, a group of scientists explain how they managed to turn dead birds into drones that can potentially spy on people.

At a startup farm outside of Oakland, a young man reads on his phone in a dim bedroom. He's not scrolling through social-media feeds or playing games; he's trying to learn about caring for his livestock. A Siri-like voice-over says, "I found one article on how to take care of baby chicks." On the floor, a large blue bucket sits under the warm glow of a heat lamp, with about a dozen fluffy chicks inside. "Failure to maintain a warm environment will quickly prove to be fatal," the digital voice explains.