Topic
Closed captioning
About: Closed captioning is a research topic. Over the lifetime, 3011 publications have been published within this topic receiving 64494 citations. The topic is also known as: CC.
Papers published on a yearly basis
Papers
More filters
••
14 Jul 2004TL;DR: A new highly interactive program to teach American sign language (ASL) for K-3 mathematics by 3D animation to increase the opportunity for deaf children to learn arithmetic via interactive media and the effectiveness of ASL K-8 mathematics teachers.
Abstract: We present a new highly interactive program to teach American sign language (ASL) for K-3 mathematics by 3D animation. We aim at increasing: (1) the opportunity for deaf children to learn arithmetic via interactive media; (2) the effectiveness of (hearing) parents in teaching arithmetic to their deaf children; (3) the effectiveness of ASL K-8 mathematics teachers. Using state-of-the-art 3D computer animation technology we have created a learning tool to be used for K-8 classroom and home learning, and for closed captioning in interactive media and Internet.
18 citations
•
24 May 2013TL;DR: In this paper, a real-time captioning system for speech is described, where workers are asked to transcribe all or portions of what they receive and then the transcriptions received from each worker are aligned and combined to create a resulting caption.
Abstract: Methods and systems for captioning speech in real-time are provided. Embodiments utilize captionists, who may be non-expert captionists, to transcribe a speech using a worker interface. Each worker is provided with the speech or portions of the speech, and is asked to transcribe all or portions of what they receive. The transcriptions received from each worker are aligned and combined to create a resulting caption. Automated speech recognition systems may be integrated by serving in the role of one or more workers, or integrated in other ways. Workers may work locally (able to hear the speech) and/or workers may work remotely, the speech being provided to them as an audio stream. Worker performance may be measured and used to provide feedback into the system such that overall performance is improved.
18 citations
•
TL;DR: This paper proposes a novel attention model, namely Adaptive Attention Time (AAT), to align the source and the target adaptively for image captioning, and empirically shows that AAT improves over state-of-the-art methods on the task ofimage captioning.
Abstract: Recent neural models for image captioning usually employ an encoder-decoder framework with an attention mechanism. However, the attention mechanism in such a framework aligns one single (attended) image feature vector to one caption word, assuming one-to-one mapping from source image regions and target caption words, which is never possible. In this paper, we propose a novel attention model, namely Adaptive Attention Time (AAT), to align the source and the target adaptively for image captioning. AAT allows the framework to learn how many attention steps to take to output a caption word at each decoding step. With AAT, an image region can be mapped to an arbitrary number of caption words while a caption word can also attend to an arbitrary number of image regions. AAT is deterministic and differentiable, and doesn't introduce any noise to the parameter gradients. In this paper, we empirically show that AAT improves over state-of-the-art methods on the task of image captioning. Code is available at this https URL.
18 citations
••
01 Apr 2011
TL;DR: Considerations for coding and transport of stereoscopic 3-D video, options for dual-channel encoding as well as frame-compatible delivery and an overview of3-D eyewear issues are discussed.
Abstract: This paper discusses considerations for coding and transport of stereoscopic 3-D video, options for dual-channel encoding as well as frame-compatible delivery. A description of the use of digital interfaces for stereoscopic 3-D delivery from set-top boxes (STBs) to displays is included along with an overview of 3-D eyewear issues. Complexities such as rendering captions without introducing depth conflicts and future directions are also discussed.
18 citations
•
AT&T1
TL;DR: In this article, a system that incorporates teachings of the subject disclosure may include, for example, determining that a commercial segment of media content, including a video portion and an audio portion, contains neither metadata nor close captioning information.
Abstract: A system that incorporates teachings of the subject disclosure may include, for example, determining that a commercial segment of media content, including a video portion and an audio portion, contains neither metadata nor close captioning information. I response to determining that the commercial segment contains neither metadata nor close captioning information, advertised program content is identified based on the video portion, the audio portion or both. Alternative media content is identified based on the advertised program content. Other embodiments are disclosed.
18 citations