35 accepted papers
Weakly-supervised Video Anomaly Detection (wVAD) aims to detect abnormal events using only binary labels, making it challenging to capture both the diversity of anomalies and their shared semantic cues. Existing methods either focus on a generic anomaly pattern, achieving strong generalization but w
Large Reasoning Models (LRMs) have advanced automated multi-step reasoning, but their ability to generate complex Chain-of-Thought (CoT) trajectories introduces severe privacy risks, as sensitive information may be deeply embedded throughout the reasoning process. Existing Large Language Models (LLM
Electronic synthesizer sounds are controlled by parameter settings that yield complex timbral characteristics and ADSR envelopes, making synthesizer-style audio transfer particularly challenging. Recent approaches to timbre transfer often rely on spectral objectives or implicit style matching, offer…
While automatic music transcription is well-established in music information retrieval, most models are limited to transcribing pitch and timing information from audio, and thus omit crucial expressive and instrument-specific nuances. One example is playing technique on the violin, which affords its…
Change captioning aims to describe differences between a pair of images using natural language. However, learning effective difference representations is highly challenging due to distractors such as illumination and viewpoint changes. To address this, we propose a change-entity-guided disentangleme…
Video Anomaly Detection (VAD) aims to identify abnormal frames from discrete events within video sequences. Existing VAD methods suffer from heavy annotation burdens in fully-supervised paradigm, insensitivity to subtle anomalies in semi-supervised paradigm, and vulnerability to noise in weakly-supe…
Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, moment segmentation, and step-captioning. The pioneering work chooses the pre-trained CLIP-based model for video retrieval,…
Many deep learning models have achieved dominant performance on the offline beat tracking task. However, online beat tracking, in which only the past and present input features are available, still remains challenging. In this paper, we propose BEAt tracking Streaming Transformer (BEAST), an online…
Multi-change captioning aims to describe complex and coupled changes within an image pair in natural language. Compared with single-change captioning, this task requires the model to have higher-level cognition ability to reason an arbitrary number of changes. In this paper, we propose a novel conte…
"Change captioning aims to succinctly describe the semantic change between a pair of similar images, while being immune to distractors (illumination and viewpoint changes). Under these distractors, unchanged objects often appear pseudo changes about location and scale, and certain objects might over…
The selection of violin fingerings is influenced by factors such as musical context, skill level, and personal taste. Current deep-learningbased models, relying solely on symbolic data, are able to generate playable fingerings but struggle to capture the personal nuances of musical performance, whic…
Diffusion models (DMs) have demonstrated remarkable proficiency in producing images based on textual prompts. Numerous methods have been proposed to ensure these models generate safe images. Early methods attempt to incorporate safety filters into models to mitigate the risk of generating harmful im…
Weakly-supervised Video Anomaly Detection (wVAD) aims to detect frame-level anomalies using only video-level labels in training. Due to the limitation of coarse-grained labels Multi-Instance Learning (MIL) is prevailing in wVAD. However MIL suffers from insufficiency of binary supervision to model d…
Note-level automatic music transcription is one of the most representative music information retrieval (MIR) tasks and has been studied for various instruments to understand music. However, due to the lack of high-quality labeled data, transcription of many instruments is still a challenging task. I…
In a music scenario, both auditory and visual elements are essential to achieve an outstanding performance. Recent research has focused on the generation of body movements or fingering from audio in music performance. The audio-driven face generation technique in music performance is still deficient…
Decoding models seek to infer stimulus or task information from neural activity and play a central role in brain-computer interfaces. However, the high spatial resolution of fMRI means that the number of available features far exceeds the number of trials in a typical experiment. Although a common a…
Transcribing electric guitar solo in real-world performance is challenging because of the interference of background accompaniments, the strong coupling between music pitch and playing technique, and the limited resource of data annotation. To address these issues, we first propose a new guitar solo…
Change captioning aims to describe the difference between a pair of similar images. Its key challenge is how to learn a stable difference representation under pseudo changes caused by viewpoint change. In this paper, we address this by proposing a self-supervised cross-view representation reconstruc…
The over-smoothing issue is a well-known challenge for Graph Convolutional Networks (GCN). Specifically, it is often observed that increasing the depth of GCN ends up in a trivial embedding subspace where the difference among node embeddings belonging to the same cluster tends to vanish. This paper…
One of the major challenges in Automatic Drum Transcription (ADT) research is the lack of large-scale labeled dataset featuring audio with polyphonic mixtures; this limitation around data availability greatly impedes the progress of data-driven approaches in the context of ADT. To tackle this issue,…
Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore different message-passing mechanisms, and require manual enumeration to determine the proper message-passing depth. Inspired…
Generating body movements based on given music audio recordings is an emerging research topic. This problem remains challenging particularly for string instruments, considering the fact that the relationship between the musical note sequences and the body movement sequences in string instruments doe…
One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse persp…
In crowd counting datasets, the location labels are costly, yet, they are not taken into the evaluation metrics. Besides, existing multi-task approaches employ high-level tasks to improve counting accuracy. This research tendency increases the demand for more annotations. In this paper, we propose a…
Melody extraction in polyphonic musical audio is important for music signal processing. In this paper, we propose a novel streamlined encoder/decoder network that is designed for the task. We make two technical contributions. First, drawing inspiration from a state-of-the-art model for semantic pixe…
Existing state-of-the-art salient object detection networks rely on aggregating multi-level features of pre-trained convolutional neural networks (CNNs). However, compared to high-level features, low-level features contribute less to performance. Meanwhile, they raise more computational cost because…
The multi-instrument transcription task refers to joint recognition of instrument and pitch of every event in polyphonic music signals generated by one or more classes of music instruments. In this paper, we leverage multi-object semantic segmentation techniques to solve this problem. We design a ti…
Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aw…
Spectral features are limited in modeling musical signals with multiple concurrent pitches due to the challenge to suppress the interference of the harmonic peaks from one pitch to another. In this paper, we show that using multiple features represented in both the frequency and time domains with de…
Expressive singing voice correction is an appealing but challenging problem. A robust time-warping algorithm which synchronizes two singing recordings can provide a promising solution. We thereby propose to address the problem by canonical time warping (CTW) which aligns amateur singing recordings t…
A patch-based convolutional neural network (CNN) model presented in this paper for vocal melody extraction in polyphonic music is inspired from object detection in image processing. The input of the model is a novel time-frequency representation which enhances the pitch contours and suppresses the h…
In this paper, we propose an audio mosaicing method that converts Pop songs into a specific music style called “chiptune,” or “8-bit music.” The goal is to reproduce Pop songs by using the sound of the chips on the old game consoles in 1980s/1990s. The proposed method goes through a procedure that f…
In this paper, we discuss the multipitch streaming (MPS) problem for a multi-source audio signal having interweaving pitch contours. We propose two approaches to tackle this challenge, one relates to a feature extracted from the energy levels distributed in multi-channel recordings for better charac…
Automatic music transcription is usually approached by using a time-frequency (TF) representation such as the short-time Fourier transform (STFT) spectrogram or the constant-Q transform. In this paper, we propose a novel yet simple TF representation that capitalizes the effectiveness of spectral flu…
A new algorithm is proposed for robust principal component analysis with predefined sparsity patterns. The algorithm is then applied to separate the singing voice from the instrumental accompaniment using vocal activity information. To evaluate its performance, we construct a new publicly available…