中文
相关论文

相关论文: How to Teach DNNs to Pay Attention to the Visual M…

200 篇论文

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to…

计算机视觉与模式识别 · 计算机科学 2026-01-06 Dianyi Wang , Wei Song , Yikun Wang , Siyuan Wang , Kaicheng Yu , Zhongyu Wei , Jiaqi Wang

Audio-visual speaker diarization aims at detecting "who spoke when" using both auditory and visual signals. Existing audio-visual diarization datasets are mainly focused on indoor environments like meeting rooms or news studios, which are…

计算机视觉与模式识别 · 计算机科学 2022-07-19 Eric Zhongcong Xu , Zeyang Song , Satoshi Tsutsui , Chao Feng , Mang Ye , Mike Zheng Shou

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

声音 · 计算机科学 2022-03-29 Xichen Pan , Peiyu Chen , Yichen Gong , Helong Zhou , Xinbing Wang , Zhouhan Lin

The goal of Audio-Visual Segmentation (AVS) is to localize and segment the sounding source objects from video frames. Research on AVS suffers from data scarcity due to the high cost of fine-grained manual annotations. Recent works attempt…

计算机视觉与模式识别 · 计算机科学 2025-05-30 Kyungbok Lee , You Zhang , Zhiyao Duan

Recent advances in multi-modal large language models (MLLMs) have opened new possibilities for unified modeling of speech, text, images, and other modalities. Building on our prior work, this paper examines the conditions and model…

声音 · 计算机科学 2025-07-28 Yiwen Guan , Viet Anh Trinh , Vivek Voleti , Jacob Whitehill

Active speaker detection (ASD) in egocentric videos presents unique challenges due to unstable viewpoints, motion blur, and off-screen speech sources - conditions under which traditional visual-centric methods degrade significantly. We…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Yu Wang , Juhyung Ha , David J. Crandall

Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, however, the efficacy of synchronisation-based methods is…

多媒体 · 计算机科学 2025-06-24 Jason Clarke , Yoshihiko Gotoh , Stefan Goetze

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,…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Lin Zhang , Zefan Cai , Yufan Zhou , Shentong Mo , Jinhong Lin , Cheng-En Wu , Yibing Wei , Yijing Zhang , Ruiyi Zhang , Wen Xiao , Tong Sun , Junjie Hu , Pedro Morgado

Speech is one of the most effective ways of communication among humans. Even though audio is the most common way of transmitting speech, very important information can be found in other modalities, such as vision. Vision is particularly…

计算与语言 · 计算机科学 2016-11-22 Ramon Sanabria , Florian Metze , Fernando De La Torre

We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and…

计算机视觉与模式识别 · 计算机科学 2017-06-06 Yusuf Aytar , Carl Vondrick , Antonio Torralba

Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…

声音 · 计算机科学 2022-04-29 Dan Oneata , Horia Cucu

Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition…

声音 · 计算机科学 2022-07-18 Bowen Shi , Wei-Ning Hsu , Abdelrahman Mohamed

Although speaker verification has conventionally been an audio-only task, some practical applications provide both audio and visual streams of input. In these cases, the visual stream provides complementary information and can often be…

声音 · 计算机科学 2021-02-15 Leda Sarı , Kritika Singh , Jiatong Zhou , Lorenzo Torresani , Nayan Singhal , Yatharth Saraf

Audio-visual information fusion enables a performance improvement in speech recognition performed in complex acoustic scenarios, e.g., noisy environments. It is required to explore an effective audio-visual fusion strategy for audiovisual…

音频与语音处理 · 电气工程与系统科学 2020-08-07 Liangfa Wei , Jie Zhang , Junfeng Hou , Lirong Dai

Active speaker detection (ASD) is a multi-modal task that aims to identify who, if anyone, is speaking from a set of candidates. Current audio-visual approaches for ASD typically rely on visually pre-extracted face tracks (sequences of…

音频与语音处理 · 电气工程与系统科学 2022-03-08 Davide Berghi , Adrian Hilton , Philip J. B. Jackson

Audiovisual speech recognition (AVSR) combines acoustic and visual cues to improve transcription robustness under challenging conditions but remains out of reach for most under-resourced languages due to the lack of labeled video corpora…

音频与语音处理 · 电气工程与系统科学 2026-03-10 Pol Buitrago , Pol Gàlvez , Oriol Pareras , Javier Hernando

Automatic speech recognition (ASR) technologies have been significantly advanced in the past few decades. However, recognition of overlapped speech remains a highly challenging task to date. To this end, multi-channel microphone array data…

音频与语音处理 · 电气工程与系统科学 2021-08-31 Jianwei Yu , Shi-Xiong Zhang , Bo Wu , Shansong Liu , Shoukang Hu , Mengzhe Geng , Xunying Liu , Helen Meng , Dong Yu

Audio-visual speech recognition (AVSR) incorporates auditory and visual modalities to improve recognition accuracy, particularly in noisy environments where audio-only speech systems are insufficient. While previous research has largely…

音频与语音处理 · 电气工程与系统科学 2025-05-01 Sungnyun Kim , Sungwoo Cho , Sangmin Bae , Kangwook Jang , Se-Young Yun

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

音频与语音处理 · 电气工程与系统科学 2022-07-18 Yicheng Du , Aditya Arie Nugraha , Kouhei Sekiguchi , Yoshiaki Bando , Mathieu Fontaine , Kazuyoshi Yoshii

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…

计算机视觉与模式识别 · 计算机科学 2024-12-30 Yongbiao Gao , Xiangcheng Sun , Guohua Lv , Deng Yu , Sijiu Niu