Related papers: Audio-Visual Class-Incremental Learning
The Audio-Visual Speaker Extraction (AVSE) algorithm employs parallel video recording to leverage two visual cues, namely speaker identity and synchronization, to enhance performance compared to audio-only algorithms. However, the visual…
The goal of Multilingual Visual Answer Localization (MVAL) is to locate a video segment that answers a given multilingual question. Existing methods either focus solely on visual modality or integrate visual and subtitle modalities.…
Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement…
Learning from audio-visual data offers many possibilities to express correspondence between the audio and visual content, similar to the human perception that relates aural and visual information. In this work, we present a method for…
Audio-Visual Segmentation (AVS) aims to produce pixel-level masks of sound producing objects in videos, by jointly learning from audio and visual signals. However, real-world environments are inherently dynamic, causing audio and visual…
This paper studies the problem of class-incremental learning (CIL), a core setting within continual learning where a model learns a sequence of tasks, each containing a distinct set of classes. Traditional CIL methods, which do not leverage…
Class-incremental learning (CIL) in medical image-guided diagnosis requires retaining prior diagnostic knowledge while adapting to newly emerging disease categories, which is critical for scalable clinical deployment. This problem is…
We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual…
People can easily imagine the potential sound while seeing an event. This natural synchronization between audio and visual signals reveals their intrinsic correlations. To this end, we propose to learn the audio-visual correlations from the…
The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the…
Audio-visual speech recognition (AVSR) research has gained a great success recently by improving the noise-robustness of audio-only automatic speech recognition (ASR) with noise-invariant visual information. However, most existing AVSR…
In class incremental learning (CIL) setting, groups of classes are introduced to a model in each learning phase. The goal is to learn a unified model performant on all the classes observed so far. Given the recent popularity of Vision…
Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations.…
Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while…
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting…
Recently audio-visual speech recognition (AVSR), which better leverages video modality as additional information to extend automatic speech recognition (ASR), has shown promising results in complex acoustic environments. However, there is…
Contrastive learning has emerged as a powerful technique in audio-visual representation learning, leveraging the natural co-occurrence of audio and visual modalities in webscale video datasets. However, conventional contrastive audio-visual…
Temporal Action Localization (TAL) has garnered significant attention in information retrieval. Existing supervised or weakly supervised methods heavily rely on labeled temporal boundaries and action categories, which are labor-intensive…
This paper proposes a single-stage training approach that semantically aligns three modalities - audio, visual, and text using a contrastive learning framework. Contrastive training has gained prominence for multimodal alignment, utilizing…