Related papers: Zero-Shot Audio-Visual Editing via Cross-Modal Del…
Recent advances in audio-synchronized visual animation enable control of video content using audios from specific classes. However, existing methods rely heavily on expensive manual curation of high-quality, class-specific training videos,…
In this paper, we introduce a novel problem of audio-visual event localization in unconstrained videos. We define an audio-visual event as an event that is both visible and audible in a video segment. We collect an Audio-Visual Event(AVE)…
Audio-visual video parsing (AVVP) aims to recognize audio and visual event labels with precise temporal boundaries, which is quite challenging since audio or visual modality might include only one event label with only the overall video…
Weakly-supervised audio-visual video parsing (AVVP) seeks to detect audible, visible, and audio-visual events without temporal annotations. Previous work has emphasized refining global predictions through contrastive or collaborative…
Audio to Video generation is an interesting problem that has numerous applications across industry verticals including film making, multi-media, marketing, education and others. High-quality video generation with expressive facial movements…
The diffusion-based generative models have achieved remarkable success in text-based image generation. However, since it contains enormous randomness in generation progress, it is still challenging to apply such models for real-world visual…
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the…
Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by relying on low-similarity or random inputs, obscure overfitting.…
Training deep learning models for video classification from audio-visual data commonly requires immense amounts of labeled training data collected via a costly process. A challenging and underexplored, yet much cheaper, setup is few-shot…
This work addresses the lack of multimodal generative models capable of producing high-quality videos with spatially aligned audio. While recent advancements in generative models have been successful in video generation, they often overlook…
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…
We propose a zero-shot approach to image harmonization, aiming to overcome the reliance on large amounts of synthetic composite images in existing methods. These methods, while showing promising results, involve significant training…
Zero-shot 3D anomaly detection aims to identify anomalies without access to training data from target categories. However, existing methods mainly rely on projecting 3D observations into multi-view representations that primarily capture…
Zero-shot learning (ZSL) aims to train a model on seen classes and recognize unseen classes by knowledge transfer through shared auxiliary information. Recent studies reveal that documents from encyclopedias provide helpful auxiliary…
Decoding visual semantic representations from human brain activity is a significant challenge. While recent zero-shot decoding approaches have improved performance by leveraging aligned image-text datasets, they overlook a fundamental…
We study few-shot acoustic event detection (AED) in this paper. Few-shot learning enables detection of new events with very limited labeled data. Compared to other research areas like computer vision, few-shot learning for audio recognition…
Appearance editing according to user needs is a pivotal task in video editing. Existing text-guided methods often lead to ambiguities regarding user intentions and restrict fine-grained control over editing specific aspects of objects. To…
Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts have explored language-driven zero-shot SED by exploiting…
To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets…
Audio-visual segmentation (AVS) is a challenging task that involves accurately segmenting sounding objects based on audio-visual cues. The effectiveness of audio-visual learning critically depends on achieving accurate cross-modal alignment…