We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions, there are over 206,000 English-Chinese parallel translation pairs. Compared to the widely-used MSR-VTT dataset, VATEX is multilingual, larger, linguistically complex, and more diverse in terms of both video and natural language descriptions. We also introduce two tasks for video-and-language research based on VATEX: (1) Multilingual Video Captioning, aimed at describing a video in various languages with a compact unified captioning model, and (2) Video-guided Machine Translation, to translate a source language description into the target language using the video information as additional spatiotemporal context. Extensive experiments on the VATEX dataset show that, first, the unified multilingual model can not only produce both English and Chinese descriptions for a video more efficiently, but also offer improved performance over the monolingual models. Furthermore, we demonstrate that the spatiotemporal video context can be effectively utilized to align source and target languages and thus assist machine translation. In the end, we discuss the potentials of using VATEX for other video-and-language research.
CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；PeopleAI, Inc., China（中国PeopleAI公司）
Multi-modal information is essential to describe what has happened in a video. In this work, we represent videos by various appearance, motion and audio information guided with video topic. By following multi-stage training strategy, our experiments show steady and significant improvement on the VATEX benchmark. This report presents an overview and comparative analysis of our system designed for both Chinese and English tracks on VATEX Captioning Challenge 2019.
This paper describes the Imperial College London team's submission to the 2019' VATEX video captioning challenge, where we first explore two sequence-to-sequence models, namely a recurrent (GRU) model and a transformer model, which generate captions from the I3D action features. We then investigate the effect of dropping the encoder and the attention mechanism and instead conditioning the GRU decoder over two different vectorial representations: (i) a max-pooled action feature vector and (ii) the output of a multi-label classifier trained to predict visual entities from the action features. Ou…
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI；University of Oxford（牛津大学）
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (MultiHowTo100M) for pre-training. Experimen…
Video-text retrieval has many real-world applications such as media analytics, surveillance, and robotics. This paper presents the 1st place solution to the video retrieval track of the ICCV VALUE Challenge 2021. We present a simple yet effective approach to jointly tackle two video-text retrieval tasks (video retrieval and video corpus moment retrieval) by leveraging the model trained only on the video retrieval task. In addition, we create an ensemble model that achieves the new state-of-the-art performance on all four datasets (TVr, How2r, YouCook2r, and VATEXr) presented in the VALUE Chall…
Renmin University of China（中国人民大学）；University of Adelaide（阿德莱德大学）
This notebook paper presents our model in the VATEX video captioning challenge. In order to capture multi-level aspects in the video, we propose to integrate both temporal and spatial attentions for video captioning. The temporal attentive module focuses on global action movements while spatial attentive module enables to describe more fine-grained objects. Considering these two types of attentive modules are complementary, we thus fuse them via a late fusion strategy. The proposed model significantly outperforms baselines and achieves 73.4 CIDEr score on the testing set which ranks the second…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Science and Technology Beijing（北京科技大学）；Wuhan University（武汉大学）
This report describes our solution for the VATEX Captioning Challenge 2020, which requires generating descriptions for the videos in both English and Chinese languages. We identified three crucial factors that improve the performance, namely: multi-view features, hybrid reward, and diverse ensemble. Based on our method of VATEX 2019 challenge, we achieved significant improvements this year with more advanced model architectures, combination of appearance and motion features, and careful hyper-parameters tuning. Our method achieves very competitive results on both of the Chinese and English vid…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
We introduce mTVR, a large-scale multilingual video moment retrieval dataset, containing 218K English and Chinese queries from 21.8K TV show video clips. The dataset is collected by extending the popular TVR dataset (in English) with paired Chinese queries and subtitles. Compared to existing moment retrieval datasets, mTVR is multilingual, larger, and comes with diverse annotations. We further propose mXML, a multilingual moment retrieval model that learns and operates on data from both languages, via encoder parameter sharing and language neighborhood constraints. We demonstrate the effective…
Kandian Content AI Lab, Platform and Content Group, Tencent（腾讯平台与内容集团看点内容AI实验室）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）
This report describes our solution to the VALUE Challenge 2021 in the captioning task. Our solution, named CLIP4Caption++, is built on X-Linear/X-Transformer, which is an advanced model with encoder-decoder architecture. We make the following improvements on the proposed CLIP4Caption++: We employ an advanced encoder-decoder model architecture X-Transformer as our main framework and make the following improvements: 1) we utilize three strong pre-trained CLIP models to extract the text-related appearance visual features. 2) we adopt the TSN sampling strategy for data enhancement. 3) we involve t…
National Institute of Technology Silchar（西尔查国家理工学院）
Video captioning is process of summarising the content, event and action of the video into a short textual form which can be helpful in many research areas such as video guided machine translation, video sentiment analysis and providing aid to needy individual. In this paper, a system description of the framework used for VATEX-2020 video captioning challenge is presented. We employ an encoder-decoder based approach in which the visual features of the video are encoded using 3D convolutional neural network (C3D) and in the decoding phase two Long Short Term Memory (LSTM) recurrent networks are…
University of Maryland, College Park（马里兰大学帕克分校）；ShareChat
We present 3MASSIV, a multilingual, multimodal and multi-aspect, expertly-annotated dataset of diverse short videos extracted from short-video social media platform - Moj. 3MASSIV comprises of 50k short videos (20 seconds average duration) and 100K unlabeled videos in 11 different languages and captures popular short video trends like pranks, fails, romance, comedy expressed via unique audio-visual formats like self-shot videos, reaction videos, lip-synching, self-sung songs, etc. 3MASSIV presents an opportunity for multimodal and multilingual semantic understanding on these unique videos by a…
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）；PeopleAI, Inc.（人民人工智能有限公司）；State Key Laboratory of Communication Content Cognition, People’s Daily Online（人民网传播内容认知国家重点实验室）；Aerospace Information Research Institute, CAS（中国科学院空天信息创新研究院）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Taking full advantage of the information from both vision and language is critical for the video captioning task. Existing models lack adequate visual representation due to the neglect of interaction between object, and sufficient training for content-related words due to long-tailed problems. In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy. Specifically, we propose an object relational graph (ORG) based encoder, which captures more detailed interaction features to enrich visual representation. Meanwhile, we design a …
University of Bucharest（布加勒斯特大学）；MBZ University of Artificial Intelligence（MBZ人工智能大学）；Linköping University（利德大学）；University of Central Florida（佛罗里达中央大学）
Guangzhou Institute of Technology, Xidian University（西安电子科技大学广州研究院）；Alibaba Group（阿里巴巴集团）
Video-text retrieval is an important yet challenging task in vision-language understanding, which aims to learn a joint embedding space where related video and text instances are close to each other. Most current works simply measure the video-text similarity based on video-level and text-level embeddings. However, the neglect of more fine-grained or local information causes the problem of insufficient representation. Some works exploit the local details by disentangling sentences, but overlook the corresponding videos, causing the asymmetry of video-text representation. To address the above l…
Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis. We present methods addressing the problem of automatic video highlight prediction based on joint visual features and textual analysis of the real-world audience discourse with complex slang, in both English and traditional Chinese. We present a novel dataset based on League of Legends championships recorded from North American and Taiwanese Twitch.tv channels (will be released for further research), and demonstrate strong results on these using multimodal, character-level CNN-RNN model arch…
Istituto Italiano di Tecnologia (IIT)（意大利技术研究院）；University of Insubria（因苏布里亚大学）；University of Engineering and Technology Taxila（塔克西拉工程技术大学）；Information Technology University（信息技术大学）
Recent years have seen a surge in finding association between faces and voices within a cross-modal biometric application along with speaker recognition. Inspired from this, we introduce a challenging task in establishing association between faces and voices across multiple languages spoken by the same set of persons. The aim of this paper is to answer two closely related questions: "Is face-voice association language independent?" and "Can a speaker be recognised irrespective of the spoken language?". These two questions are very important to understand effectiveness and to boost development …
The Multimedia and Computer Vision Lab of the University of Augsburg participated in the VTT task only. We use the VATEX and TRECVID-VTT datasets for training our VTT models. We base our model on the Transformer approach for both of our submitted runs. For our second model, we adapt the X-Linear Attention Networks for Image Captioning which does not yield the desired bump in scores. For both models, we train on the complete VATEX dataset and 90% of the TRECVID-VTT dataset for pretraining while using the remaining 10% for validation. We finetune both models with self-critical sequence training,…
Can You Count to Nine? A Human Evaluation Benchmark for Counting Limits in Modern Text-to-Video Models
Guilin University of Electronic Technology（桂林电子科技大学）；The Ohio State University（俄亥俄州立大学）；University of Arizona（亚利桑那大学）；The University of Hong Kong（香港大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；The Simons Institute for the Theory of Computing（西蒙斯理论计算研究所）
Microsoft（微软）；Microsoft Research Asia（微软亚洲研究院）；Southwest Jiaotong University（西南交通大学）；ShanghaiTech University（上海科技大学）
In this paper, we present GEM as a General Evaluation benchmark for Multimodal tasks. Different from existing datasets such as GLUE, SuperGLUE, XGLUE and XTREME that mainly focus on natural language tasks, GEM is a large-scale vision-language benchmark, which consists of GEM-I for image-language tasks and GEM-V for video-language tasks. Comparing with existing multimodal datasets such as MSCOCO and Flicker30K for image-language tasks, YouCook2 and MSR-VTT for video-language tasks, GEM is not only the largest vision-language dataset covering image-language tasks and video-language tasks at the …
Negation is a common linguistic skill that allows human to express what we do NOT want. Naturally, one might expect video retrieval to support natural-language queries with negation, e.g., finding shots of kids sitting on the floor and not playing with a dog. However, the state-of-the-art deep learning based video retrieval models lack such ability, as they are typically trained on video description datasets such as MSR-VTT and VATEX that lack negated descriptions. Their retrieved results basically ignore the negator in the sample query, incorrectly returning videos showing kids playing with d…
Tongji University（同济大学）；Hong Kong Polytechnic University（香港理工大学）
Translating visual data into natural language is essential for machines to understand the world and interact with humans. In this work, a comprehensive study is conducted on video paragraph captioning, with the goal to generate paragraph-level descriptions for a given video. However, current researches mainly focus on detecting objective facts, ignoring the needs to establish the logical associations between sentences and to discover more accurate emotions related to video contents. Such a problem impairs fluent and abundant expressions of predicted captions, which are far below human language…
MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos
Human Language Technology Center of Excellence（人类语言技术卓越中心）；Johns Hopkins University（约翰斯·霍普金斯大学）；Georgetown University（乔治城大学）；George Mason University（乔治梅森大学）；University of Rochester（罗切斯特大学）
A Culturally-diverse Multilingual Multimodal Video Benchmark & Model
Mohamed bin Zayed University of Artificial Intelligence（莫德赫·本·扎耶德人工智能大学）；University of Central Florida（中央佛罗里达大学）；Islamic University of Technology（伊斯兰技术大学）；Air University（空军大学）；ETH Zurich（苏黎世联邦理工学院）；Technische Universität München（慕尼黑技术大学）；National Institute of Informatics（国家信息研究所）；Australian National University（澳大利亚国立大学）；Linköping University（利尔贝里大学）
Overview of the NLPCC 2025 Shared Task 4: Multi-modal, Multilingual, and Multi-hop Medical Instructional Video Question Answering Challenge
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；School of Computer Science and Technology, Beijing Institute of Technology（计算机科学与技术学院，北京理工大学）；School of Engineering, Westlake University（工程学院，西湖大学）
We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video features and multi-modal interaction between videos and languages from a large-scale video-text dataset. Different from them, we leverage pretrained image-language model, simplify it as a two-stage framework with co-learning of image-text and enhancing temporal relations between video frames and video-text respectively, make it able to train on comparatively small…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；UT Austin（德克萨斯大学奥斯汀分校）；IBM Research AI（IBM研究院人工智能部门）；Columbia University（哥伦比亚大学）；NYU（纽约大学）
In this paper, we explore self-supervised audio-visual models that learn from instructional videos. Prior work has shown that these models can relate spoken words and sounds to visual content after training on a large-scale dataset of videos, but they were only trained and evaluated on videos in English. To learn multilingual audio-visual representations, we propose a cascaded approach that leverages a model trained on English videos and applies it to audio-visual data in other languages, such as Japanese videos. With our cascaded approach, we show an improvement in retrieval performance of ne…
Video-to-Text (VTT) is the task of automatically generating descriptions for short audio-visual video clips, which can support visually impaired people to understand scenes of a YouTube video for instance. Transformer architectures have shown great performance in both machine translation and image captioning, lacking a straightforward and reproducible application for VTT. However, there is no comprehensive study on different strategies and advice for video description generation including exploiting the accompanying audio with fully self-attentive networks. Thus, we explore promising approache…
ABMAMBA: Multimodal Large Language Model with Aligned Hierarchical Bidirectional Scan for Efficient Video Captioning
Keio University（庆应义塾大学）；National Institute of Informatics（国立信息学研究所）；National Institute of Informatics Research and Development Center for Large Language Models（国立信息学研究所大型语言模型研发中心）
Tel Aviv University（特拉维夫大学）；Technion（以色列理工学院）；NetApp
We present a method for matching a text sentence from a given corpus to a given video clip and vice versa. Traditionally video and text matching is done by learning a shared embedding space and the encoding of one modality is independent of the other. In this work, we encode the dataset data in a way that takes into account the query's relevant information. The power of the method is demonstrated to arise from pooling the interaction data between words and frames. Since the encoding of the video clip depends on the sentence compared to it, the representation needs to be recomputed for each pot…
University of Sfax（斯法克斯大学）；National School of Engineers（国家工程师学院）
The amount of audio-visual information has increased dramatically with the advent of High Speed Internet. Furthermore, technological advances in recent years in the field of information technology, have simplified the use of video data in various fields by the general public. This made it possible to store large collections of video documents into computer systems. To enable efficient use of these collections, it is necessary to develop tools to facilitate access to these documents and handling them. In this paper we propose a method for indexing and retrieval of video sequences in a video dat…
University of Electronic Science and Technology of China（电子科技大学）；Southwest Jiaotong University（西南交通大学）
Generating consecutive descriptions for videos, i.e., Video Captioning, requires taking full advantage of visual representation along with the generation process. Existing video captioning methods focus on making an exploration of spatial-temporal representations and their relationships to produce inferences. However, such methods only exploit the superficial association contained in the video itself without considering the intrinsic visual commonsense knowledge that existed in a video dataset, which may hinder their capabilities of knowledge cognitive to reason accurate descriptions. To addre…
