The objective of this paper is an automatic Audio Description (AD) model that ingests movies and outputs AD in text form. Generating high-quality movie AD is challenging due to the dependency of the descriptions on context, and the limited amount of training data available. In this work, we leverage the power of pretrained foundation models, such as GPT and CLIP, and only train a mapping network that bridges the two models for visually-conditioned text generation. In order to obtain high-quality AD, we make the following four contributions: (i) we incorporate context from the movie clip, AD from previous clips, as well as the subtitles; (ii) we address the lack of training data by pretraining on large-scale datasets, where visual or contextual information is unavailable, e.g. text-only AD without movies or visual captioning datasets without context; (iii) we improve on the currently available AD datasets, by removing label noise in the MAD dataset, and adding character naming information; and (iv) we obtain strong results on the movie AD task compared with previous methods.
CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong（香港中文大学-商汤科技联合实验室）
Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In this paper, we introduce MovieNet -- a holistic dataset for movie understanding. MovieNet contains 1,100 movies with a large amount of multi-modal data, e.g. trailers, photos, plot descriptions, etc. Besides, different aspects of manual annotations are provided in MovieNet, including 1.1M characters with bounding boxes and identities, 42K scene boundaries, 2.5K aligned description sentences, 65K tags of place and actio…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；ICSI（国际计算机科学研究所）；UC Berkeley（加州大学伯克利分校）；Disney Research（迪士尼研究中心）；École Polytechnique de Montréal（蒙特利尔理工学院）；Université de Sherbrooke（舍布鲁克大学）；Twitter（推特）；Université de Montréal（蒙特利尔大学）
Audio Description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. In total the Large Scale Movie Description Challenge (LSMDC) con…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Generating descriptions for videos has many applications including assisting blind people and human-robot interaction. The recent advances in image captioning as well as the release of large-scale movie description datasets such as MPII Movie Description allow to study this task in more depth. Many of the proposed methods for image captioning rely on pre-trained object classifier CNNs and Long-Short Term Memory recurrent networks (LSTMs) for generating descriptions. While image description focuses on objects, we argue that it is important to distinguish verbs, objects, and places in the challe…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Descriptive video service (DVS) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their peers. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed DVS, which is temporally aligned to full length HD movies. In addition we also collected the aligned movie scripts which have been used in prior work and compare the two different sources of descriptions. In total the Movie Descript…
Our objective in this work is long range understanding of the narrative structure of movies. Instead of considering the entire movie, we propose to learn from the `key scenes' of the movie, providing a condensed look at the full storyline. To this end, we make the following three contributions: (i) We create the Condensed Movies Dataset (CMD) consisting of the key scenes from over 3K movies: each key scene is accompanied by a high level semantic description of the scene, character face-tracks, and metadata about the movie. The dataset is scalable, obtained automatically from YouTube, and is fr…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；UC Berkeley（加州大学伯克利分校）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Learning how to generate descriptions of images or videos received major interest both in the Computer Vision and Natural Language Processing communities. While a few works have proposed to learn a grounding during the generation process in an unsupervised way (via an attention mechanism), it remains unclear how good the quality of the grounding is and whether it benefits the description quality. In this work we propose a movie description model which learns to generate description and jointly ground (localize) the mentioned characters as well as do visual co-reference resolution between pairs…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））；Adobe Research（奥多比研究院）
The recent and increasing interest in video-language research has driven the development of large-scale datasets that enable data-intensive machine learning techniques. In comparison, limited effort has been made at assessing the fitness of these datasets for the video-language grounding task. Recent works have begun to discover significant limitations in these datasets, suggesting that state-of-the-art techniques commonly overfit to hidden dataset biases. In this work, we present MAD (Movie Audio Descriptions), a novel benchmark that departs from the paradigm of augmenting existing video data…
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
The use of Recurrent Neural Networks for video captioning has recently gained a lot of attention, since they can be used both to encode the input video and to generate the corresponding description. In this paper, we present a recurrent video encoding scheme which can discover and leverage the hierarchical structure of the video. Unlike the classical encoder-decoder approach, in which a video is encoded continuously by a recurrent layer, we propose a novel LSTM cell, which can identify discontinuity points between frames or segments and modify the temporal connections of the encoding layer acc…
The Ohio State University（俄亥俄州立大学）；University of Florida（佛罗里达大学）；Air Force Research Lab（空军研究实验室）
Learning visual feature representations for video analysis is a daunting task that requires a large amount of training samples and a proper generalization framework. Many of the current state of the art methods for video captioning and movie description rely on simple encoding mechanisms through recurrent neural networks to encode temporal visual information extracted from video data. In this paper, we introduce a novel multitask encoder-decoder framework for automatic semantic description and captioning of video sequences. In contrast to current approaches, our method relies on distinct decod…
Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；University of California, Berkeley（加州大学伯克利分校）
Standard video and movie description tasks abstract away from person identities, thus failing to link identities across sentences. We propose a multi-sentence Identity-Aware Video Description task, which overcomes this limitation and requires to re-identify persons locally within a set of consecutive clips. We introduce an auxiliary task of Fill-in the Identity, that aims to predict persons' IDs consistently within a set of clips, when the video descriptions are given. Our proposed approach to this task leverages a Transformer architecture allowing for coherent joint prediction of multiple IDs…
To understand movies, humans constantly reason over the dialogues and actions shown in specific scenes and relate them to the overall storyline already seen. Inspired by this behaviour, we design ROLL, a model for knowledge-based video story question answering that leverages three crucial aspects of movie understanding: dialog comprehension, scene reasoning, and storyline recalling. In ROLL, each of these tasks is in charge of extracting rich and diverse information by 1) processing scene dialogues, 2) generating unsupervised video scene descriptions, and 3) obtaining external knowledge in a w…
University of Rochester（罗切斯特大学）；Yahoo Research（雅虎研究院）；AiCure
With the recent popularity of animated GIFs on social media, there is need for ways to index them with rich metadata. To advance research on animated GIF understanding, we collected a new dataset, Tumblr GIF (TGIF), with 100K animated GIFs from Tumblr and 120K natural language descriptions obtained via crowdsourcing. The motivation for this work is to develop a testbed for image sequence description systems, where the task is to generate natural language descriptions for animated GIFs or video clips. To ensure a high quality dataset, we developed a series of novel quality controls to validate …
Université de Montréal（蒙特利尔大学）；École Polytechnique de Montéral（蒙特利尔综合理工学院）；Université de Sherbrooke（舍布鲁克大学）
In this work, we introduce a dataset of video annotated with high quality natural language phrases describing the visual content in a given segment of time. Our dataset is based on the Descriptive Video Service (DVS) that is now encoded on many digital media products such as DVDs. DVS is an audio narration describing the visual elements and actions in a movie for the visually impaired. It is temporally aligned with the movie and mixed with the original movie soundtrack. We describe an automatic DVS segmentation and alignment method for movies, that enables us to scale up the collection of a DV…
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）
Current movie captioning architectures are not capable of mentioning characters with their proper name, replacing them with a generic "someone" tag. The lack of movie description datasets with characters' visual annotations surely plays a relevant role in this shortage. Recently, we proposed to extend the M-VAD dataset by introducing such information. In this paper, we present an improved version of the dataset, namely M-VAD Names, and its semi-automatic annotation procedure. The resulting dataset contains 63k visual tracks and 34k textual mentions, all associated with character identities. To…
UT Austin（得克萨斯大学奥斯汀分校）；UC Berkeley（加州大学伯克利分校）；Boston University（波士顿大学）
This paper investigates how linguistic knowledge mined from large text corpora can aid the generation of natural language descriptions of videos. Specifically, we integrate both a neural language model and distributional semantics trained on large text corpora into a recent LSTM-based architecture for video description. We evaluate our approach on a collection of Youtube videos as well as two large movie description datasets showing significant improvements in grammaticality while modestly improving descriptive quality.
CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation
The Hong Kong University of Science and Technology（香港科学与技术大学）；Lehigh University（莱斯大学）；Fudan University（复旦大学）；Emory University（埃默里大学）；University of Central Florida（中央佛罗里达大学）
National Taiwan University（国立台湾大学）；Microsoft（微软）；Mobile Drive Technology（摩比驱动科技）
Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep cognition to reason intentions, motivation, or causality remains challenging. Existing datasets that aim to examine video reasoning capability focus on visual signals such as actions, objects, relations, or could be answered utilizing text bias. Observing this, we propose a novel task, along with a new dataset: Trope Understanding in Movies and Animations (TrUM…
We present Affect2MM, a learning method for time-series emotion prediction for multimedia content. Our goal is to automatically capture the varying emotions depicted by characters in real-life human-centric situations and behaviors. We use the ideas from emotion causation theories to computationally model and determine the emotional state evoked in clips of movies. Affect2MM explicitly models the temporal causality using attention-based methods and Granger causality. We use a variety of components like facial features of actors involved, scene understanding, visual aesthetics, action/situation…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of California, Berkeley（加州大学伯克利分校）；University of Massachusetts, Lowell（马萨诸塞大学洛厄尔分校）；International Computer Science Institute, Berkeley（伯克利国际计算机科学研究所）
Real-world videos often have complex dynamics; and methods for generating open-domain video descriptions should be sensitive to temporal structure and allow both input (sequence of frames) and output (sequence of words) of variable length. To approach this problem, we propose a novel end-to-end sequence-to-sequence model to generate captions for videos. For this we exploit recurrent neural networks, specifically LSTMs, which have demonstrated state-of-the-art performance in image caption generation. Our LSTM model is trained on video-sentence pairs and learns to associate a sequence of video f…
The Allen Institute for AI（艾伦人工智能研究所）；Carnegie Mellon University（卡内基梅隆大学）；Inria（法国国家信息与自动化研究所）；University of Washington（华盛顿大学）
Computer vision has a great potential to help our daily lives by searching for lost keys, watering flowers or reminding us to take a pill. To succeed with such tasks, computer vision methods need to be trained from real and diverse examples of our daily dynamic scenes. While most of such scenes are not particularly exciting, they typically do not appear on YouTube, in movies or TV broadcasts. So how do we collect sufficiently many diverse but boring samples representing our lives? We propose a novel Hollywood in Homes approach to collect such data. Instead of shooting videos in the lab, we ens…
École Normale Supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague（捷克布拉格技术大学捷克信息学、机器人学与控制论研究所）；Inria（法国国家信息与自动化研究所）；CIIRC（捷克信息学、机器人学与控制论研究所）
Joint understanding of video and language is an active research area with many applications. Prior work in this domain typically relies on learning text-video embeddings. One difficulty with this approach, however, is the lack of large-scale annotated video-caption datasets for training. To address this issue, we aim at learning text-video embeddings from heterogeneous data sources. To this end, we propose a Mixture-of-Embedding-Experts (MEE) model with ability to handle missing input modalities during training. As a result, our framework can learn improved text-video embeddings simultaneously…
INRIA（法国国家信息与自动化研究所）；Columbia University（哥伦比亚大学）；ENS / PSL Research University（巴黎高等师范学院/巴黎文理研究大学）；CNRS（法国国家科学研究中心）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）
Suppose that we are given a set of videos, along with natural language descriptions in the form of multiple sentences (e.g., manual annotations, movie scripts, sport summaries etc.), and that these sentences appear in the same temporal order as their visual counterparts. We propose in this paper a method for aligning the two modalities, i.e., automatically providing a time stamp for every sentence. Given vectorial features for both video and text, we propose to cast this task as a temporal assignment problem, with an implicit linear mapping between the two feature modalities. We formulate this…
