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.

Television Literacy: Comprehension of Program Content Using Closed Captions for the Deaf

Abstract: Recent legislation has made captioned television programs common technology; consequently, televised programs have become more accessible to a broader public. In the United States, television captions are generally in written English, yet the English-literacy rates among people who are deaf are low compared to hearing peers. This research tests the accessibility of television by assessing deaf and hearing students' comprehension of captions with and without visuals/video based on their ability to respond correctly to questions about the script and central details. Results indicate that reading grade level is highly correlated with caption comprehension test scores. Across caption conditions, comprehension test scores of students who are deaf were consistently below the scores of hearing students. The captioned video provided significantly better comprehension of the script for students who are deaf, suggesting that visual stimuli provide essential information for viewers who are deaf, which improves comprehension of televised script.

Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval

Abstract: Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval. The challenges in this area include the design of the visual architecture and the nature of the training data, in that the available large scale video-text training datasets, such as HowTo100M, are noisy and hence competitive performance is achieved only at scale through large amounts of compute. We address both these challenges in this paper. We propose an end-to-end trainable model that is designed to take advantage of both large-scale image and video captioning datasets. Our model is an adaptation and extension of the recent ViT and Timesformer architectures, and consists of attention in both space and time. The model is flexible and can be trained on both image and video text datasets, either independently or in conjunction. It is trained with a curriculum learning schedule that begins by treating images as 'frozen' snapshots of video, and then gradually learns to attend to increasing temporal context when trained on video datasets. We also provide a new video-text pretraining dataset WebVid-2M, comprised of over two million videos with weak captions scraped from the internet. Despite training on datasets that are an order of magnitude smaller, we show that this approach yields state-of-the-art results on standard downstream video-retrieval benchmarks including MSR-VTT, MSVD, DiDeMo and LSMDC.

Unified Vision-Language Pre-Training for Image Captioning and VQA

Abstract: This paper presents a unified Vision-Language Pre-training (VLP) model. The model is unified in that (1) it can be fine-tuned for either vision-language generation (e.g., image captioning) or understanding (e.g., visual question answering) tasks, and (2) it uses a shared multi-layer transformer network for both encoding and decoding, which differs from many existing methods where the encoder and decoder are implemented using separate models. The unified VLP model is pre-trained on a large amount of image-text pairs using the unsupervised learning objectives of two tasks: bidirectional and sequence-to-sequence (seq2seq) masked vision-language prediction. The two tasks differ solely in what context the prediction conditions on. This is controlled by utilizing specific self-attention masks for the shared transformer network. To the best of our knowledge, VLP is the first reported model that achieves state-of-the-art results on both vision-language generation and understanding tasks, as disparate as image captioning and visual question answering, across three challenging benchmark datasets: COCO Captions, Flickr30k Captions, and VQA 2.0. The code and the pre-trained models are available at this https URL.

Dynamic captioning: video accessibility enhancement for hearing impairment

Abstract: There are more than 66 million people su®ering from hearing impairment and this disability brings them di±culty in the video content understanding due to the loss of audio information. If scripts are available, captioning technology can help them in a certain degree by synchronously illustrating the scripts during the playing of videos. However, we show that the existing captioning techniques are far from satisfactory in assisting hearing impaired audience to enjoy videos. In this paper, we introduce a video accessibility enhancement scheme with a Dynamic Captioning approach, which explores a rich set of technologies including face detection and recognition, visual saliency analysis, text-speech alignment, etc. Different from the existing methods that are categorized as static captioning here, dynamic captioning puts scripts at suitable positions to help hearing impaired audience better recognize the speaking characters. In addition, it progressively highlights the scripts word-by-word via aligning them with the speech signal and illustrates the variation of voice volume. In this way, the special audience can better track the scripts and perceive the moods that are conveyed by the variation of volume. We implement the technology on 20 video clips and conduct an in-depth study with 60 real hearing impaired users, and results have demonstrated the effectiveness and usefulness of the video accessibility enhancement scheme.

MAM-RNN: Multi-level Attention Model Based RNN for Video Captioning

Abstract: Visual information is quite important for the task of video captioning. However, in the video, there are a lot of uncorrelated content, which may cause interference to generate a correct caption. Based on this point, we attempt to exploit the visual features which are most correlated to the caption. In this paper, a Multi-level Attention Model based Recurrent Neural Network (MAM-RNN) is proposed, where MAM is utilized to encode the visual feature and RNN works as the decoder to generate the video caption. During generation, the proposed approach is able to adaptively attend to the salient regions in the frame and the frames correlated to the caption. Practically, the experimental results on two benchmark datasets, i.e., MSVD and Charades, have shown the excellent performance of the proposed approach.