Videos on the Internet are paired with pieces of text, such as titles and descriptions. This text typically describes the most important content in the video, such as the objects in the scene and the actions being performed. Based on this observation, we propose to use text as a method for learning video representations. To accomplish this, we propose a data collection process and use it to collect 70M video clips shared publicly on the Internet, and we then train a model to pair each video with its associated text. We evaluate the model on several down-stream action recognition tasks, including Kinetics, HMDB-51, and UCF-101. We find that this approach is an effective method of pre-training video representations. Specifically, it outperforms all existing methods for self-supervised and cross-modal video representation learning.
Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of interest might only exist in arbitrary clips of untrimmed web videos, resulting in high label noises in the temporal space. To address this issue, we introduce a new method for pre-training video action recognition models using queried web videos. Instead of trying to filter out, we propose to convert the potential noises in these queried videos to useful supervi…
Arizona State University（亚利桑那州立大学）；Carnegie Mellon University（卡内基梅隆大学）；Beihang University（北京航空航天大学）；University of California, Irvine（加利福尼亚大学尔湾分校）
A system capturing the association between video frames and textual queries offer great potential for better video analysis. However, training such a system in a fully supervised way inevitably demands a meticulously curated video dataset with temporal-textual annotations. Therefore we provide a Weak-Supervised alternative with our proposed Referring Attention mechanism to learn temporal-textual association (dubbed WSRA). The weak supervision is simply a textual expression (e.g., short phrases or sentences) at video level, indicating this video contains relevant frames. The referring attention…
As tons of photos are being uploaded to public websites (e.g., Flickr, Bing, and Google) every day, learning from web data has become an increasingly popular research direction because of freely available web resources, which is also referred to as webly supervised learning. Nevertheless, the performance gap between webly supervised learning and traditional supervised learning is still very large, owning to the label noise of web data. To be exact, the labels of images crawled from public websites are very noisy and often inaccurate. Some existing works tend to facilitate learning from web dat…
Allen Institute for AI（艾伦人工智能研究所）；Google Research（谷歌研究院）
Pretraining from unlabelled web videos has quickly become the de-facto means of achieving high performance on many video understanding tasks. Features are learned via prediction of grounded relationships between visual content and automatic speech recognition (ASR) tokens. However, prior pretraining work has been limited to only instructional videos; a priori, we expect this domain to be relatively "easy:" speakers in instructional videos will often reference the literal objects/actions being depicted. We ask: can similar models be trained on more diverse video corpora? And, if so, what types …
Training deep neural networks typically requires large amounts of labeled data which may be scarce or expensive to obtain for a particular target domain. As an alternative, we can leverage webly-supervised data (i.e. results from a public search engine) which are relatively plentiful but may contain noisy results. In this work, we propose a novel two-stage approach to learn a video classifier using webly-supervised data. We argue that learning appearance features and then temporal features sequentially, rather than simultaneously, is an easier optimization for this task. We show this by first …
We present a fully data-driven method to compute depth from diverse monocular video sequences that contain large amounts of non-rigid objects, e.g., people. In order to learn reconstruction cues for non-rigid scenes, we introduce a new dataset consisting of stereo videos scraped in-the-wild. This dataset has a wide variety of scene types, and features large amounts of nonrigid objects, especially people. From this, we compute disparity maps to be used as supervision to train our approach. We propose a loss function that allows us to generate a depth prediction even with unknown camera intrinsi…
University of Oxford（牛津大学）；Xerox Research Centre Europe（施乐欧洲研究中心）
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important. Recognizing object parts and attributes has been extensively studied before, yet learning large space of such concepts remains elusive due to the high cost of providing detailed object annotations for supervision. The key contribution of this paper is an algorithm to learn the nameable parts of objects automatically, from images obtained by querying Web search engines. The key challenge is the high level of noise in the annotations; to …
We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results. The explosion of visual data on the web can potentially make visual examples of almost any object easily accessible via web search. Previous unsupervised methods have utilized either large scale sources of texture cues from the web, or shape information from data such as crowdsourced CAD models. We propose a two-stream deep learning framework that combines these cues, with o…
Archivists, textual scholars, and historians often produce digital editions of historical documents. Using markup schemes such as those of the Text Encoding Initiative and EpiDoc, these digital editions often record documents' semantic regions (such as notes and figures) and physical features (such as page and line breaks) as well as transcribing their textual content. We describe methods for exploiting this semantic markup as distant supervision for training and evaluating layout analysis models. In experiments with several model architectures on the half-million pages of the Deutsches Textar…
University of Michigan（密歇根大学）；Zhejiang University（浙江大学）
Using mathematical modeling and human subjects experiments, this research explores the extent to which emerging webcams might leak recognizable textual and graphical information gleaming from eyeglass reflections captured by webcams. The primary goal of our work is to measure, compute, and predict the factors, limits, and thresholds of recognizability as webcam technology evolves in the future. Our work explores and characterizes the viable threat models based on optical attacks using multi-frame super resolution techniques on sequences of video frames. Our models and experimental results in a…
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）
Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth spatial localization of phrases, thus it is desirable to learn from data with no or little grounding supervision. We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly. During training our approach encodes the phrase using a recurrent network language mo…
Tel Aviv University（特拉维夫大学）；Bar-Ilan University（巴伊兰大学）；NVIDIA Research（英伟达研究院）；The Allen Institute for AI（艾伦人工智能研究所）
Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding boxes. Thus, it is a significant challenge to use cheaper forms of supervision effectively. Recent work has begun to explore image captions as a source for weak supervision, but to date, in the context of object detection, captions have only been used to infer the categories of the objects in the image. In this work, we argue that captions contain much richer information about the image, including attributes of objec…
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex that takes advantage of the low-cost localized textual annotations (i.e., captions and synchronized mouse-over gestures) to reduce the annotation effort. We introduce a contrastive pre-training framework between images and captions and propose to supervise the cross-modal attention map with rendered mouse traces to provide coarse localization signals. Our learned visual features capture rich semantics (from free-form c…
POSTECH（浦项工科大学）；DGIST（大邱庆北科学技术院）；University of Michigan（密歇根大学）
We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the entire object area. Our goal is to overcome this limitation with no additional human intervention by retrieving videos relevant to target class labels from web repository, and generating segmentation labels from the retrieved videos to simulate strong supervision for semantic segmentation. During this process, we take advantage of image classification with …
Nanjing University（南京大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, …
Nanyang Technological University（南洋理工大学）；NVIDIA AI Technology Center（英伟达AI技术中心）；Amazon Rekognition（亚马逊Rekognition）
Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. On the contrary, we propose an object detection method that does not require any form of human annotation on target tasks, by exploiting freely available web images. In order to facilitate effective knowledge transfer from web images, we introduce a multi-instance multi-label domain adaption learning framework with two key innovations. Firs…
Automatically generating textual descriptions for massive unlabeled images on the web can greatly benefit realistic web applications, e.g. multimodal retrieval and recommendation. However, existing models suffer from the problem of generating ``over-generic'' descriptions, such as their tendency to generate repetitive sentences with common concepts for different images. These generic descriptions fail to provide sufficient textual semantics for ever-changing web images. Inspired by the recent success of Vision-Language Pre-training (VLP) models that learn diverse image-text concept alignment d…
SPi Technologies India Private Limited（SPi科技印度私人有限公司）
Images greatly help in understanding, interpreting and visualizing data. Adding textual description to images is the first and foremost principle of web accessibility. Visually impaired users using screen readers will use these textual descriptions to get better understanding of images present in digital contents. In this paper, we propose Chart-Text a novel fully automated system that creates textual description of chart images. Given a PNG image of a chart, our Chart-Text system creates a complete textual description of it. First, the system classifies the type of chart and then it detects a…
In this paper, we investigate an open research task of generating controllable 3D textured shapes from the given textual descriptions. Previous works either require ground truth caption labeling or extensive optimization time. To resolve these issues, we present a novel framework, TAPS3D, to train a text-guided 3D shape generator with pseudo captions. Specifically, based on rendered 2D images, we retrieve relevant words from the CLIP vocabulary and construct pseudo captions using templates. Our constructed captions provide high-level semantic supervision for generated 3D shapes. Further, in or…
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
IBM Research Zurich, Zurich, Switzerland（IBM苏黎世研究实验室，瑞士苏黎世）；ETH Zurich, Computer Vision（苏黎世联邦理工学院，计算机视觉）；ETH AI Center, Switzerland（苏黎世联邦理工学院人工智能中心，瑞士）；ETH Zurich, Photogrammetry（苏黎世联邦理工学院，摄影测量学）；Microsoft, Switzerland（微软公司，瑞士）
VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning
Beijing University of Posts and Telecommunications（北京邮电大学）；University of Hong Kong（香港大学）；Beijing Shanwei Zhixing Technology Co., Ltd.（北京尚维智行科技有限公司）；Tsinghua University（清华大学）；Beihang University（北航）
Web Image Context Extraction (WICE) consists in obtaining the textual information describing an image using the content of the surrounding webpage. A common preprocessing step before performing WICE is to render the content of the webpage. When done at a large scale (e.g., for search engine indexation), it may become very computationally costly (up to several seconds per page). To avoid this cost, we introduce a novel WICE approach that combines Graph Neural Networks (GNNs) and Natural Language Processing models. Our method relies on a graph model containing both node types and text as feature…
Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室（NLPR）多模态人工智能系统国家重点实验室（MAIS））；FiveAges
École des Ponts（巴黎桥路学院）；Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；CNRS（法国国家科学研究中心）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
We address the problem of generating diverse 3D human motions from textual descriptions. This challenging task requires joint modeling of both modalities: understanding and extracting useful human-centric information from the text, and then generating plausible and realistic sequences of human poses. In contrast to most previous work which focuses on generating a single, deterministic, motion from a textual description, we design a variational approach that can produce multiple diverse human motions. We propose TEMOS, a text-conditioned generative model leveraging variational autoencoder (VAE)…
