Large-scale product recognition is one of the major applications of computer vision and machine learning in the e-commerce domain. Since the number of products is typically much larger than the number of categories of products, image-based product recognition is often cast as a visual search rather than a classification problem. It is also one of the instances of super fine-grained recognition, where there are many products with slight or subtle visual differences. It has always been a challenge to create a benchmark dataset for training and evaluation on various visual search solutions in a real-world setting. This motivated creation of eProduct, a dataset consisting of 2.5 million product images towards accelerating development in the areas of self-supervised learning, weakly-supervised learning, and multimodal learning, for fine-grained recognition. We present eProduct as a training set and an evaluation set, where the training set contains 1.3M+ listing images with titles and hierarchical category labels, for model development, and the evaluation set includes 10,000 query and 1.1 million index images for visual search evaluation. We will present eProduct's construction steps, provide analysis about its diversity and cover the performance of baseline models trained on it.
Recent face recognition experiments on a major benchmark LFW show stunning performance--a number of algorithms achieve near to perfect score, surpassing human recognition rates. In this paper, we advocate evaluations at the million scale (LFW includes only 13K photos of 5K people). To this end, we have assembled the MegaFace dataset and created the first MegaFace challenge. Our dataset includes One Million photos that capture more than 690K different individuals. The challenge evaluates performance of algorithms with increasing numbers of distractors (going from 10 to 1M) in the gallery set. W…
FingerVeinSyn-5M: A Million-Scale Dataset and Benchmark for Finger Vein Recognition
School of Cyber Science and Engineering, Southeast University（网络安全科学与工程学院，东南大学）；Lee Kong Chian School of Medicine, Nanyang, Technological University Singapore（李光前医学院，南洋理工大学新加坡）；Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院）；Center for Machine Vision and Signal Analysis , University of Oulu（机器视觉与信号分析中心，奥卢大学）
Google Research（谷歌研究院）；Georgia Institute of Technology（佐治亚理工学院）
Large-scale multi-modal pre-training models such as CLIP and PaLI exhibit strong generalization on various visual domains and tasks. However, existing image classification benchmarks often evaluate recognition on a specific domain (e.g., outdoor images) or a specific task (e.g., classifying plant species), which falls short of evaluating whether pre-trained foundational models are universal visual recognizers. To address this, we formally present the task of Open-domain Visual Entity recognitioN (OVEN), where a model need to link an image onto a Wikipedia entity with respect to a text query. W…
Visual Place Recognition (VPR) is generally concerned with localizing outdoor images. However, localizing indoor scenes that contain part of an outdoor scene can be of large value for a wide range of applications. In this paper, we introduce Inside Out Visual Place Recognition (IOVPR), a task aiming to localize images based on outdoor scenes visible through windows. For this task we present the new large-scale dataset Amsterdam-XXXL, with images taken in Amsterdam, that consists of 6.4 million panoramic street-view images and 1000 user-generated indoor queries. Additionally, we introduce a new…
In this paper we introduce the TorontoCity benchmark, which covers the full greater Toronto area (GTA) with 712.5 $km^2$ of land, 8439 $km$ of road and around 400,000 buildings. Our benchmark provides different perspectives of the world captured from airplanes, drones and cars driving around the city. Manually labeling such a large scale dataset is infeasible. Instead, we propose to utilize different sources of high-precision maps to create our ground truth. Towards this goal, we develop algorithms that allow us to align all data sources with the maps while requiring minimal human supervision.…
University of Southern Denmark（南丹麦大学）；University of Bristol（布里斯托尔大学）
Methods for linking individuals across historical data sets, typically in combination with AI based transcription models, are developing rapidly. Probably the single most important identifier for linking is personal names. However, personal names are prone to enumeration and transcription errors and although modern linking methods are designed to handle such challenges, these sources of errors are critical and should be minimized. For this purpose, improved transcription methods and large-scale databases are crucial components. This paper describes and provides documentation for HANA, a newly …
Huazhong University of Science and Technology（华中科技大学）
Ethiopic/Amharic script is one of the oldest African writing systems, which serves at least 23 languages (e.g., Amharic, Tigrinya) in East Africa for more than 120 million people. The Amharic writing system, Abugida, has 282 syllables, 15 punctuation marks, and 20 numerals. The Amharic syllabic matrix is derived from 34 base graphemes/consonants by adding up to 12 appropriate diacritics or vocalic markers to the characters. The syllables with a common consonant or vocalic markers are likely to be visually similar and challenge text recognition tasks. In this work, we presented the first compre…
German Research Center for Artificial Intelligence (DFKI GmbH)（德国人工智能研究中心）；Technische Universität Kaiserslautern（凯泽斯劳滕工业大学）；Osaka Prefecture University（大阪府立大学）
The contribution of this paper is fourfold. The first contribution is a novel, generic method for automatic ground truth generation of camera-captured document images (books, magazines, articles, invoices, etc.). It enables us to build large-scale (i.e., millions of images) labeled camera-captured/scanned documents datasets, without any human intervention. The method is generic, language independent and can be used for generation of labeled documents datasets (both scanned and cameracaptured) in any cursive and non-cursive language, e.g., English, Russian, Arabic, Urdu, etc. To assess the effe…
Recent face recognition experiments on the LFW benchmark show that face recognition is performing stunningly well, surpassing human recognition rates. In this paper, we study face recognition at scale. Specifically, we have collected from Flickr a \textbf{Million} faces and evaluated state of the art face recognition algorithms on this dataset. We found that the performance of algorithms varies--while all perform great on LFW, once evaluated at scale recognition rates drop drastically for most algorithms. Interestingly, deep learning based approach by \cite{schroff2015facenet} performs much be…
Computer vision systems are designed to work well within the context of everyday photography. However, artists often render the world around them in ways that do not resemble photographs. Artwork produced by people is not constrained to mimic the physical world, making it more challenging for machines to recognize. This work is a step toward teaching machines how to categorize images in ways that are valuable to humans. First, we collect a large-scale dataset of contemporary artwork from Behance, a website containing millions of portfolios from professional and commercial artists. We annotate …
This paper describes the details of Sighthound's fully automated vehicle make, model and color recognition system. The backbone of our system is a deep convolutional neural network that is not only computationally inexpensive, but also provides state-of-the-art results on several competitive benchmarks. Additionally, our deep network is trained on a large dataset of several million images which are labeled through a semi-automated process. Finally we test our system on several public datasets as well as our own internal test dataset. Our results show that we outperform other methods on all ben…
While there has been remarkable progress in the performance of visual recognition algorithms, the state-of-the-art models tend to be exceptionally data-hungry. Large labeled training datasets, expensive and tedious to produce, are required to optimize millions of parameters in deep network models. Lagging behind the growth in model capacity, the available datasets are quickly becoming outdated in terms of size and density. To circumvent this bottleneck, we propose to amplify human effort through a partially automated labeling scheme, leveraging deep learning with humans in the loop. Starting f…
The objective of this paper is speaker recognition under noisy and unconstrained conditions. We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset. Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice under…
Face recognition has the perception of a solved problem, however when tested at the million-scale exhibits dramatic variation in accuracies across the different algorithms. Are the algorithms very different? Is access to good/big training data their secret weapon? Where should face recognition improve? To address those questions, we created a benchmark, MF2, that requires all algorithms to be trained on same data, and tested at the million scale. MF2 is a public large-scale set with 672K identities and 4.7M photos created with the goal to level playing field for large scale face recognition. W…
Imperial College London（帝国理工学院）；RealEyes（RealEyes公司）；University of Augsburg（奥格斯堡大学）
Automatic affect recognition using visual cues is an important task towards a complete interaction between humans and machines. Applications can be found in tutoring systems and human computer interaction. A critical step towards that direction is facial feature extraction. In this paper, we propose a facial feature extractor model trained on an in-the-wild and massively collected video dataset provided by the RealEyes company. The dataset consists of a million labelled frames and 2,616 thousand subjects. As temporal information is important to the emotion recognition domain, we utilise LSTM c…
Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as well as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web cau…
Institute for Robotics and Intelligent Systems, USC（南加州大学机器人与智能系统研究所）；Information Sciences Institute, USC（南加州大学信息科学研究所）；The Open University of Israel（以色列开放大学）
Face recognition capabilities have recently made extraordinary leaps. Though this progress is at least partially due to ballooning training set sizes -- huge numbers of face images downloaded and labeled for identity -- it is not clear if the formidable task of collecting so many images is truly necessary. We propose a far more accessible means of increasing training data sizes for face recognition systems. Rather than manually harvesting and labeling more faces, we simply synthesize them. We describe novel methods of enriching an existing dataset with important facial appearance variations by…
Tsinghua University（清华大学）；XForwardAI；Imperial College London（帝国理工学院）
Face benchmarks empower the research community to train and evaluate high-performance face recognition systems. In this paper, we contribute a new million-scale recognition benchmark, containing uncurated 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol. Firstly, we collect 4M name lists and download 260M faces from the Internet. Then, a Cleaning Automatically utilizing Self-Training (CAST) pipeline is devised to purify the tremendous WebFace260M, which is efficient and…
Tsinghua University（清华大学）；XForwardAI；Imperial College London（伦敦帝国学院）
In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol. Firstly, we collect 4M name list and download 260M faces from the Internet. Then, a Cleaning Automatically utilizing Self-Training (CAST) pipeline is devised to purify the tremendous WebFace260M, which is efficient and scalable. To the best of our knowledge, the cleaned WebFace42M is the largest public face recognition training set and we ex…
State-of-the-art face recognition models show impressive accuracy, achieving over 99.8% on Labeled Faces in the Wild (LFW) dataset. Such models are trained on large-scale datasets that contain millions of real human face images collected from the internet. Web-crawled face images are severely biased (in terms of race, lighting, make-up, etc) and often contain label noise. More importantly, the face images are collected without explicit consent, raising ethical concerns. To avoid such problems, we introduce a large-scale synthetic dataset for face recognition, obtained by rendering digital face…
Recognizing the country where a picture has been taken has many potential applications, such as identification of fake news and prevention of disinformation campaigns. Previous works focused on the estimation of the geo-coordinates where a picture has been taken. Yet, recognizing in which country an image was taken could be more critical, from a semantic and forensic point of view, than estimating its spatial coordinates. In the above framework, this paper provides two contributions. First, we introduce the VIPPGeo dataset, containing 3.8 million geo-tagged images. Secondly, we used the datase…
George Washington University（乔治华盛顿大学）；Adobe Research（奥多比研究院）；Temple University（天普大学）
Recognizing a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognizing the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms. To support efforts towards this hotel recognition task, we have curated a dataset of over 1 milli…
Concordia University（康考迪亚大学）；University of Arkansas（阿肯色大学）；Carnegie Mellon University（卡内基梅隆大学）
Large-scale face recognition in-the-wild has been recently achieved matured performance in many real work applications. However, such systems are built on GPU platforms and mostly deploy heavy deep network architectures. Given a high-performance heavy network as a teacher, this work presents a simple and elegant teacher-student learning paradigm, namely ShrinkTeaNet, to train a portable student network that has significantly fewer parameters and competitive accuracy against the teacher network. Far apart from prior teacher-student frameworks mainly focusing on accuracy and compression ratios i…
SketchGraphNet: A Memory-Efficient Hybrid Graph Transformer for Large-Scale Sketch Corpora Recognition
College of Computer, Qinghai Normal University（青海师范大学计算机学院）；College of Computer, Nanjing University（南京大学计算机学院）；College of Computer, Qinghai Minzu University（青海民族大学计算机学院）
Gaozhe Technology（高哲科技）；The University of New South Wales（新南威尔士大学）；Baidu（百度）
Cereal grains are a vital part of human diets and are important commodities for people's livelihood and international trade. Grain Appearance Inspection (GAI) serves as one of the crucial steps for the determination of grain quality and grain stratification for proper circulation, storage and food processing, etc. GAI is routinely performed manually by qualified inspectors with the aid of some hand tools. Automated GAI has the benefit of greatly assisting inspectors with their jobs but has been limited due to the lack of datasets and clear definitions of the tasks. In this paper we formulate G…
Beijing University of Posts and Telecommunications（北京邮电大学）
In recent years, deep learning-based methods have shown promising results in computer vision area. However, a common deep learning model requires a large amount of labeled data, which is labor-intensive to collect and label. What's more, the model can be ruined due to the domain shift between training data and testing data. Text recognition is a broadly studied field in computer vision and suffers from the same problems noted above due to the diversity of fonts and complicated backgrounds. In this paper, we focus on the text recognition problem and mainly make three contributions toward these …
University of Southern Denmark（南丹麦大学）；University of Bristol（布里斯托大学）
Handwritten text recognition for historical documents is an important task but it remains difficult due to a lack of sufficient training data in combination with a large variability of writing styles and degradation of historical documents. While recurrent neural network architectures are commonly used for handwritten text recognition, they are often computationally expensive to train and the benefit of recurrence drastically differs by task. For these reasons, it is important to consider non-recurrent architectures. In the context of handwritten date recognition, we propose an architecture ba…
This research is the second phase in a series of investigations on developing an Optical Character Recognition (OCR) of Arabic historical documents and examining how different modeling procedures interact with the problem. The first research studied the effect of Transformers on our custom-built Arabic dataset. One of the downsides of the first research was the size of the training data, a mere 15000 images from our 30 million images, due to lack of resources. Also, we add an image enhancement layer, time and space optimization, and Post-Correction layer to aid the model in predicting the corr…
Recently, attempts have been made to collect millions of videos to train CNN models for action recognition in videos. However, curating such large-scale video datasets requires immense human labor, and training CNNs on millions of videos demands huge computational resources. In contrast, collecting action images from the Web is much easier and training on images requires much less computation. In addition, labeled web images tend to contain discriminative action poses, which highlight discriminative portions of a video's temporal progression. We explore the question of whether we can utilize w…
We survey over 100 face datasets constructed between 1976 to 2019 of 145 million images of over 17 million subjects from a range of sources, demographics and conditions. Our historical survey reveals that these datasets are contextually informed, shaped by changes in political motivations, technological capability and current norms. We discuss how such influences mask specific practices (some of which may actually be harmful or otherwise problematic) and make a case for the explicit communication of such details in order to establish a more grounded understanding of the technology's function i…
Due to the prevalence of social media websites, one challenge facing computer vision researchers is to devise methods to process and search for persons of interest among the billions of shared photos on these websites. Facebook revealed in a 2013 white paper that its users have uploaded more than 250 billion photos, and are uploading 350 million new photos each day. Due to this humongous amount of data, large-scale face search for mining web images is both important and challenging. Despite significant progress in face recognition, searching a large collection of unconstrained face images has …
E.SUN Financial Holding CO., LTD.（玉山金融控股股份有限公司）；National Kaohsiung Normal University（高雄师范大学）
Scene text recognition (STR) has been widely studied in academia and industry. Training a text recognition model often requires a large amount of labeled data, but data labeling can be difficult, expensive, or time-consuming, especially for Traditional Chinese text recognition. To the best of our knowledge, public datasets for Traditional Chinese text recognition are lacking. This paper presents a framework for a Traditional Chinese synthetic data engine which aims to improve text recognition model performance. We generated over 20 million synthetic data and collected over 7,000 manually label…
This paper addresses the problem of continuous gesture recognition from sequences of depth maps using convolutional neutral networks (ConvNets). The proposed method first segments individual gestures from a depth sequence based on quantity of movement (QOM). For each segmented gesture, an Improved Depth Motion Map (IDMM), which converts the depth sequence into one image, is constructed and fed to a ConvNet for recognition. The IDMM effectively encodes both spatial and temporal information and allows the fine-tuning with existing ConvNet models for classification without introducing millions of…
Image or object recognition is an important task in computer vision. With the hight-speed processing power on modern platforms and the availability of mobile phones everywhere, millions of photos are uploaded to the internet per minute, it is critical to establish a generic framework for fast and accurate image processing for automatic recognition and information retrieval. In this paper, we proposed an efficient image recognition and matching method that is originally derived from Naive Bayesian classification method to construct a probabilistic model. Our method support real-time performance…
Boston University（波士顿大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）
Solving multi-label recognition (MLR) for images in the low-label regime is a challenging task with many real-world applications. Recent work learns an alignment between textual and visual spaces to compensate for insufficient image labels, but loses accuracy because of the limited amount of available MLR annotations. In this work, we utilize the strong alignment of textual and visual features pretrained with millions of auxiliary image-text pairs and propose Dual Context Optimization (DualCoOp) as a unified framework for partial-label MLR and zero-shot MLR. DualCoOp encodes positive and negat…
Scripps Institution of Oceanography（斯克里普斯海洋研究所）；University of California - San Diego（加州大学圣地亚哥分校）；Woods Hole Oceanographic Institution（伍兹霍尔海洋研究所）
Planktonic organisms are of fundamental importance to marine ecosystems: they form the basis of the food web, provide the link between the atmosphere and the deep ocean, and influence global-scale biogeochemical cycles. Scientists are increasingly using imaging-based technologies to study these creatures in their natural habit. Images from such systems provide an unique opportunity to model and understand plankton ecosystems, but the collected datasets can be enormous. The Imaging FlowCytobot (IFCB) at Woods Hole Oceanographic Institution, for example, is an \emph{in situ} system that has been…
XForwardAI Technology Co.,Ltd（XForwardAI科技有限公司）；Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Recently, face recognition in the wild has achieved remarkable success and one key engine is the increasing size of training data. For example, the largest face dataset, WebFace42M contains about 2 million identities and 42 million faces. However, a massive number of faces raise the constraints in training time, computing resources, and memory cost. The current research on this problem mainly focuses on designing an efficient Fully-connected layer (FC) to reduce GPU memory consumption caused by a large number of identities. In this work, we relax these constraints by resolving the redundancy p…
Australian National University（澳大利亚国立大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）
Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation. Over the last decade, human action analysis evolved from earlier schemes that are often limited to controlled environments to nowadays advanced solutions that can learn from millions of videos and apply to almost all daily activities. Given the broad range of applications from video surveillance to human-computer interaction, scientific milestones in action recognition are achieved more rapidly, eventually lead…
Centre de Visió per Computador, Universitat Autònoma de Barcelona（巴塞罗那自治大学计算机视觉中心）；Xerox Research Center Europe（施乐欧洲研究中心）；German Aerospace Center（德国航空航天中心）
Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supe…
Face verification is a relatively easy task with the help of discriminative features from deep neural networks. However, it is still a challenge to recognize faces on millions of identities while keeping high performance and efficiency. The challenge 2 of MS-Celeb-1M is a classification task. However, the number of identities is too large and it is not that elegant to treat the task as an image classification task. We treat the classification task as similarity search and do experiments on different similarity search strategies. Similarity search strategy accelerates the speed of searching and…
Universitat de València（瓦伦西亚大学）；EUMETSAT（欧洲气象卫星应用组织）
Landmark recognition and matching is a critical step in many Image Navigation and Registration (INR) models for geostationary satellite services, as well as to maintain the geometric quality assessment (GQA) in the instrument data processing chain of Earth observation satellites. Matching the landmark accurately is of paramount relevance, and the process can be strongly impacted by the cloud contamination of a given landmark. This paper introduces a complete pattern recognition methodology able to detect the presence of clouds over landmarks using Meteosat Second Generation (MSG) data. The met…
Massachusetts Institute of Technology（麻省理工学院）；Universitat Oberta de Catalunya（加泰罗尼亚开放大学）
The rise of multi-million-item dataset initiatives has enabled data-hungry machine learning algorithms to reach near-human semantic classification at tasks such as object and scene recognition. Here we describe the Places Database, a repository of 10 million scene photographs, labeled with scene semantic categories and attributes, comprising a quasi-exhaustive list of the types of environments encountered in the world. Using state of the art Convolutional Neural Networks, we provide impressive baseline performances at scene classification. With its high-coverage and high-diversity of exemplars…
Center for Visual Information Technology, IIIT Hyderabad（海得拉巴国际信息技术研究所视觉信息技术中心）
Building robust recognizers for Arabic has always been challenging. We demonstrate the effectiveness of an end-to-end trainable CNN-RNN hybrid architecture in recognizing Arabic text in videos and natural scenes. We outperform previous state-of-the-art on two publicly available video text datasets - ALIF and ACTIV. For the scene text recognition task, we introduce a new Arabic scene text dataset and establish baseline results. For scripts like Arabic, a major challenge in developing robust recognizers is the lack of large quantity of annotated data. We overcome this by synthesising millions of…
In this paper, we design a benchmark task and provide the associated datasets for recognizing face images and link them to corresponding entity keys in a knowledge base. More specifically, we propose a benchmark task to recognize one million celebrities from their face images, by using all the possibly collected face images of this individual on the web as training data. The rich information provided by the knowledge base helps to conduct disambiguation and improve the recognition accuracy, and contributes to various real-world applications, such as image captioning and news video analysis. As…
Stanford University（斯坦福大学）；University of Michigan（密歇根大学）；Massachusetts Institute of Technology（麻省理工学院）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of t…
Chinese University of Hong Kong（香港中文大学）；Indiana University（印第安纳大学）
To launch black-box attacks against a Deep Neural Network (DNN) based Face Recognition (FR) system, one needs to build \textit{substitute} models to simulate the target model, so the adversarial examples discovered from substitute models could also mislead the target model. Such \textit{transferability} is achieved in recent studies through querying the target model to obtain data for training the substitute models. A real-world target, likes the FR system of law enforcement, however, is less accessible to the adversary. To attack such a system, a substitute model with similar quality as the t…
Most of the previous methods for table recognition rely on training datasets containing many richly annotated table images. Detailed table image annotation, e.g., cell or text bounding box annotation, however, is costly and often subjective. In this paper, we propose a weakly supervised model named WSTabNet for table recognition that relies only on HTML (or LaTeX) code-level annotations of table images. The proposed model consists of three main parts: an encoder for feature extraction, a structure decoder for generating table structure, and a cell decoder for predicting the content of each cel…
Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of using large volumes of web videos for pre-training video models for the task of action recognition. Our primary empirical finding is that pre-training at a very large scale (over 65 million videos), despite on noisy social-media videos and hashtags, substantially improves the state-of-the-art on three challenging public action recognition datasets. Further,…
