相关论文: Automated Time-frequency Domain Audio Crossfades u…
Rapid advancements in artificial intelligence have significantly enhanced generative tasks involving music and images, employing both unimodal and multimodal approaches. This research develops a model capable of generating music that…
Applications that allow sharing of user-created short videos exploded in popularity in recent years. A typical short video application allows a user to swipe away the current video being watched and start watching the next video in a video…
In this paper we study minimum cut and maximum flow problems on planar graphs, both in static and in dynamic settings. First, we present an algorithm that given an undirected planar graph computes the minimum cut between any two given…
Recently, the rectified flow (RF) has emerged as the new state-of-the-art among flow-based diffusion models due to its high efficiency advantage in straight path sampling, especially with the amazing images generated by a series of RF…
Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and onset and offset timestamps. This enables precise control…
This paper develops an optimal acceleration/speed profile for a single autonomous vehicle crossing multiple signalized intersections without stopping in free flow mode. The design objective is to produce both time and energy efficient…
This work addresses the challenge of streamed video depth estimation, which expects not only per-frame accuracy but, more importantly, cross-frame consistency. We argue that sharing contextual information between frames or clips is pivotal…
A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency in existing methods. For instance, flow matching based models rely on modeling instantaneous velocity,…
Estimating frequency moments of data streams is a very well studied problem and tight bounds are known on the amount of space that is necessary and sufficient when the stream is adversarially ordered. Recently, motivated by various…
Time-frequency scattering is a mathematical transformation of sound waves. Its core purpose is to mimick the way the human auditory system extracts information from its environment. In the context of improving the artificial intelligence of…
We prove an approximate max-multiflow min-multicut theorem for bounded treewidth graphs. In particular, we show the following: Given a treewidth-$r$ graph, there exists a (fractional) multicommodity flow of value $f$, and a multicut of…
We present rectified flow, a surprisingly simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributions \pi_0 and \pi_1, hence providing a unified solution to…
Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such…
A common way of partitioning graphs is through minimum cuts. One drawback of classical minimum cut methods is that they tend to produce small groups, which is why more balanced variants such as normalized and ratio cuts have seen more…
Through legislation and technical advances users gain more control over how their data is processed, and they expect online services to respect their privacy choices and preferences. However, data may be processed for many different…
We introduce MusicFlow, a cascaded text-to-music generation model based on flow matching. Based on self-supervised representations to bridge between text descriptions and music audios, we construct two flow matching networks to model the…
Transitions are widely used in data videos to seamlessly connect data-driven charts or connect visualizations and non-data-driven motion graphics. To inform the transition designs in data videos, we conduct a content analysis based on more…
We learn audio representations by solving a novel self-supervised learning task, which consists of predicting the phase of the short-time Fourier transform from its magnitude. A convolutional encoder is used to map the magnitude spectrum of…
The short-time Fourier transform (STFT) provides the foundation of binary-mask based audio source separation approaches. In computing a spectrogram, the STFT window size parameterizes the trade-off between time and frequency resolution.…
Advances in the image-based diagnostics of complex biological and manufacturing processes have brought unsupervised image segmentation to the forefront of enabling automated, on the fly decision making. However, most existing unsupervised…