相关论文: Reinforced Label Denoising for Weakly-Supervised A…

Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels that include both the true label and irrelevant noise labels. In this paper, we propose a novel multi-level generative…

Reinforcement Learning with Verifiable Rewards (RLVR) effectively trains reasoning models that rely on abundant perfect labels, but its vulnerability to unavoidable noisy labels due to expert scarcity remains critically underexplored. In…

We present RAVEn, a self-supervised multi-modal approach to jointly learn visual and auditory speech representations. Our pre-training objective involves encoding masked inputs, and then predicting contextualised targets generated by…

Deep active learning has emerged as a powerful tool for training deep learning models within a predefined labeling budget. These models have achieved performances comparable to those trained in an offline setting. However, deep active…

In Self-Supervised Learning (SSL), Audio-Visual Correspondence (AVC) is a popular task to learn deep audio and video features from large unlabeled datasets. The key step in AVC is to randomly sample audio and video clips from the dataset…

In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good…

Unsupervised Visible-Infrared Person Re-identification (USVI-ReID) presents a formidable challenge, which aims to match pedestrian images across visible and infrared modalities without any annotations. Recently, clustered pseudo-label…

Humans have the ability to utilize visual cues, such as lip movements and visual scenes, to enhance auditory perception, particularly in noisy environments. However, current Automatic Speech Recognition (ASR) or Audio-Visual Speech…

Music discovery services let users identify songs from short mobile recordings. These solutions are often based on Audio Fingerprinting, and rely more specifically on the extraction of spectral peaks in order to be robust to a number of…

Endeavors have been made to explore Large Language Models for video analysis (Video-LLMs), particularly in understanding and interpreting long videos. However, existing Video-LLMs still face challenges in effectively integrating the rich…

Temporal grounding of natural language in untrimmed videos is a fundamental yet challenging multimedia task facilitating cross-media visual content retrieval. We focus on the weakly supervised setting of this task that merely accesses to…

Humans are adept at leveraging visual cues from lip movements for recognizing speech in adverse listening conditions. Audio-Visual Speech Recognition (AVSR) models follow similar approach to achieve robust speech recognition in noisy…

Current methods for learning visually grounded language from videos often rely on text annotation, such as human generated captions or machine generated automatic speech recognition (ASR) transcripts. In this work, we introduce the…

Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels. In this paper,…

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques…

We study the problem of learning neural text classifiers without using any labeled data, but only easy-to-provide rules as multiple weak supervision sources. This problem is challenging because rule-induced weak labels are often noisy and…

Conventional audio-visual approaches for active speaker detection (ASD) typically rely on visually pre-extracted face tracks and the corresponding single-channel audio to find the speaker in a video. Therefore, they tend to fail every time…

Visual Speech Recognition (VSR) is the task of predicting spoken words from silent lip movements. VSR is regarded as a challenging task because of the insufficient information on lip movements. In this paper, we propose an Audio Knowledge…

Deep learning models, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), have achieved state-of-the-art performance on various computer vision tasks such as object classification, detection, segmentation,…

Deep neural networks (DNNs) have a high capacity to completely memorize noisy labels given sufficient training time, and its memorization, unfortunately, leads to performance degradation. Recently, virtual adversarial training (VAT)…