Large-scale Video Dataset Research Articles

Self-Supervised Pose Adaptation for Cross-Domain Image Animation

Image animation is to animate a still image of the object of interest using poses extracted from another video sequence. Through training on a large-scale video dataset, most existing approaches aim to explore disentangled appearance and pose representations of training frames. Then, the desired output with a specific appearance and pose can be synthesized via recombining learned representations. However, in some real-world applications, test images may lack the corresponding video ground-truth or follow a different distribution than the distribution of the training video frames (i.e., different domains), which largely limit the performance of existing methods. In this paper, we propose domain-independent pose representations that are compatible with and accessible by still images from a different domain. Specifically, we devise a two-stage self-supervised pose adaptation framework for general image animation tasks. A domain-independent pose adaptation generative adversarial network (DIPA-GAN) and a shuffle-patch generative adversarial network (Shuffle-patch GAN) are proposed to penalize the rationality of the synthesized frame's pose and appearance, respectively. Finally, experiments evaluated on various image animation tasks, which include same/cross-domain moving objects, facial expression transfer and human pose retargeting, demonstrate the superiority of the proposed framework over prior literature. Impact Statement —Image animation is a popular technology in video production. Benefiting from the rapid development of artificial intelligence (AI), recent image animation algorithms have been widely used in real-world applications, such as virtual AI news anchor, virtual try-on, and face swapping. However, most existing methods are designed for specific cases. To animate a new portrait, users are asked to collect hundreds of images of the same person and train a new model. The technology proposed in this paper overcomes these training limitations and generalizes image animations. In the challenging cross-domain facial expression transfer task, the user study demonstrated that our technology achieved more than 20% increase in animation success rate. The proposed technology could benefit users in a wide variety of industries including movie production, virtual reality, social media and online retail.

Large-scale video semantic recognition based on consistency of segment-level and video-level predictions

Segment-level video semantic recognition, which known to be an important task in video analysis, attempts to identify the semantic concepts in short video clips.Labeling video segments is difficult because there is an extremely large number of segments and there are no network tags; consequently, only a portion of the video segments are labeled. Determining how to improve the accuracy of semantic recognition of fragmented videos with limited semantic labels is a key challenge in video semantic recognition.This paper proposes a video semantic recognition algorithm based on the consistency of video- and segment-level predictions. The proposed algorithm introduces the constraint of consistency between complete video semantics and fragmentary video semantics. The proposed algorithm can be applied to filter the video segment semantic results to improve recognition accuracy. The proposed algorithm achieved 82.62% mean average precision on the video segment semantic recognition task using the large-scale video dataset YouTube-8M and ranked second in the third YouTube-8M competition.

Model-Guided Multi-Path Knowledge Aggregation for Aerial Saliency Prediction

As an emerging vision platform, a drone can look from many abnormal viewpoints which brings many new challenges into the classic vision task of video saliency prediction. To investigate these challenges, this paper proposes a large-scale video dataset for aerial saliency prediction, which consists of ground-truth salient object regions of 1,000 aerial videos, annotated by 24 subjects. To the best of our knowledge, it is the first large-scale video dataset that focuses on visual saliency prediction on drones. Based on this dataset, we propose a Model-guided Multi-path Network (MM-Net) that serves as a baseline model for aerial video saliency prediction. Inspired by the annotation process in eye-tracking experiments, MM-Net adopts multiple information paths, each of which is initialized under the guidance of a classic saliency model. After that, the visual saliency knowledge encoded in the most representative paths is selected and aggregated to improve the capability of MM-Net in predicting spatial saliency in aerial scenarios. Finally, these spatial predictions are adaptively combined with the temporal saliency predictions via a spatiotemporal optimization algorithm. Experimental results show that MM-Net outperforms ten state-of-the-art models in predicting aerial video saliency.

Active Video Hashing via Structure Information Learning for Activity Analysis

When attempting to analyze and understand large-scale video datasets, choosing training videos using active learning can significantly reduce the annotation costs associated with supervised learning without sacrificing the accuracy of classifiers. However, to further reduce the computational overhead of exhaustive comparisons between low-level visual feature with high dimensions, we have developed a novel video hashing coding model based on an active learning framework. The model optimizes mean average precision in a straightforward way by explicitly considering the structure information in video clips when learning the optimal hash functions. The structure information considered includes the temporal consistency between successive frames and the local visual patterns shared by videos with same semantic labels. Rather than relying on the similarity between paired videos, we use a ranking-based loss function to directly optimize mean average precision. Then, combined with the active learning component, we jointly evaluate the unlabeled training videos according to the uncertainty and average precision values with an efficient algorithm based on structured SVM. Extensive experimental results over several benchmark datasets demonstrate that our approach produces significantly higher search accuracy than traditional query refinement schemes.

Modeling Generalized Rate-Distortion Functions

Many multimedia applications require precise understanding of the rate-distortion characteristics measured by the function relating visual quality to media attributes, for which we term it the generalized rate-distortion (GRD) function. In this study, we explore the GRD behavior of compressed digital videos in a three-dimensional space of bitrate, resolution, and viewing device/condition. Our analysis on a large-scale video dataset reveals that empirical parametric models are systematically biased while exhaustive search methods require excessive computation time to depict the GRD surfaces. By exploiting the properties that all GRD functions share, we develop an Robust Axial-Monotonic Clough-Tocher (RAMCT) interpolation method to model the GRD function. This model allows us to accurately reconstruct the complete GRD function of a source video content from a moderate number of measurements. To further reduce the computational cost, we present a novel sampling scheme based on a probabilistic model and an information measure. The proposed sampling method constructs a sequence of quality queries by minimizing the overall informativeness in the remaining samples. Experimental results show that the proposed algorithm significantly outperforms state-of-the-art approaches in accuracy and efficiency. Finally, we demonstrate the usage of the proposed model in three applications: rate-distortion curve prediction, per-title encoding profile generation, and video encoder comparison.

Clothescounter: A framework for star-oriented clothes mining from videos

This paper presents a novel framework, ClothesCounter, which aims to automatically identify clothes worn by certain stars in videos. At first, several deep convolutional neural networks (CNN) models were utilized to preprocess video data in order to detect clothing images from original video frames, including human body detection, human posture selection, human pose estimation, face verification, and clothing detection. We then propose a method for extracting features of clothing images based on triplet loss that can map clothing images into a compact feature space. In the learned feature space, we present a two-stage clustering algorithm that does not require the number of clusters. Our framework was examined in a large-scale video dataset. Experimental results demonstrate the feasibility and effectiveness of our proposed method.

Memory Augmented Deep Recurrent Neural Network for Video Question Answering.

Video question answering (VideoQA) is a very important but challenging multimedia task, which automatically analyzes questions and videos and generates accurate answers. However, research on VideoQA is still in its infancy. In this article, we propose a novel memory augmented deep recurrent neural network (MA-DRNN) model for VideoQA, which features a new method for encoding videos and questions, and memory augmentation using the emerging differentiable neural computer (DNC). Specifically, we encode textual (questions) information before visual (videos) information, which leads to better visual-textual representations. Moreover, we leverage DNC (with an external memory) for storing and retrieving useful information in questions and videos, and modeling the long-term visual-textual dependence. To evaluate the proposed model, we conducted extensive experiments using the VTW data set and MSVD-QA data set, which are both Widely used large-scale video data sets for language-level understanding. The experimental results have well validated the proposed model and showed that it outperforms the state-of-the-art in terms of various accuracy-related metrics.

Chimpanzee face recognition from videos in the wild using deep learning.

Video recording is now ubiquitous in the study of animal behavior, but its analysis on a large scale is prohibited by the time and resources needed to manually process large volumes of data. We present a deep convolutional neural network (CNN) approach that provides a fully automated pipeline for face detection, tracking, and recognition of wild chimpanzees from long-term video records. In a 14-year dataset yielding 10 million face images from 23 individuals over 50 hours of footage, we obtained an overall accuracy of 92.5% for identity recognition and 96.2% for sex recognition. Using the identified faces, we generated co-occurrence matrices to trace changes in the social network structure of an aging population. The tools we developed enable easy processing and annotation of video datasets, including those from other species. Such automated analysis unveils the future potential of large-scale longitudinal video archives to address fundamental questions in behavior and conservation.

Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles

Self-supervised tasks such as colorization, inpainting and zigsaw puzzle have been utilized for visual representation learning for still images, when the number of labeled images is limited or absent at all. Recently, this worthwhile stream of study extends to video domain where the cost of human labeling is even more expensive. However, the most of existing methods are still based on 2D CNN architectures that can not directly capture spatio-temporal information for video applications. In this paper, we introduce a new self-supervised task called as Space-Time Cubic Puzzles to train 3D CNNs using large scale video dataset. This task requires a network to arrange permuted 3D spatio-temporal crops. By completing Space-Time Cubic Puzzles, the network learns both spatial appearance and temporal relation of video frames, which is our final goal. In experiments, we demonstrate that our learned 3D representation is well transferred to action recognition tasks, and outperforms state-of-the-art 2D CNN-based competitors on UCF101 and HMDB51 datasets.

Synthetic defocus and look-ahead autofocus for casual videography

In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often crave cinematic focus, but fail to achieve it. We either sacrifice shallow DOF, as in smartphone videos; or we struggle to deliver accurate focus, as in videos from larger cameras. This paper is about a new approach in the pursuit of cinematic focus for casual videography. We present a system that synthetically renders refocusable video from a deep DOF video shot with a smartphone, and analyzes future video frames to deliver context-aware autofocus for the current frame. To create refocusable video, we extend recent machine learning methods designed for still photography, contributing a new dataset for machine training, a rendering model better suited to cinema focus, and a filtering solution for temporal coherence. To choose focus accurately for each frame, we demonstrate autofocus that looks at upcoming video frames and applies AI-assist modules such as motion, face, audio and saliency detection. We also show that autofocus benefits from machine learning and a large-scale video dataset with focus annotation, where we use our RVR-LAAF GUI to create this sizable dataset efficiently. We deliver, for example, a shallow DOF video where the autofocus transitions onto each person before she begins to speak. This is impossible for conventional camera autofocus because it would require seeing into the future.

Implicit and Explicit Concept Relations in Deep Neural Networks for Multi-Label Video/Image Annotation

In this paper, we propose a deep convolutional neural network (DCNN) architecture that addresses the problem of video/image concept annotation by exploiting concept relations at two different levels. At the first level, we build on ideas from multi-task learning, and propose an approach to learn concept-specific representations that are sparse, linear combinations of representations of latent concepts. By enforcing the sharing of the latent concept representations, we exploit the implicit relations between the target concepts. At a second level, we build on ideas from structured output learning and propose the introduction, at training time, of a new cost term that explicitly models the correlations between the concepts. By doing so, we explicitly model the structure in the output space (i.e., the concept labels). Both of the above are implemented using standard convolutional layers and are incorporated in a single DCNN architecture that can then be trained end-to-end with standard back-propagation. Experiments on four large-scale video and image data sets show that the proposed DCNN improves concept annotation accuracy and outperforms the related state-of-the-art methods.

Exploiting Images for Video Recognition: Heterogeneous Feature Augmentation via Symmetric Adversarial Learning

Training deep models of video recognition usually requires sufficient labeled videos in order to achieve good performance without over-fitting. However, it is quite labor-intensive and time-consuming to collect and annotate a large amount of videos. Moreover, training deep neural networks on large-scale video datasets always demands huge computational resources which further hold back many researchers and practitioners. To resolve that, collecting and training on annotated images are much easier. However, thoughtlessly applying images to help recognize videos may result in noticeable performance degeneration due to the well-known domain shift and feature heterogeneity. This proposes a novel symmetric adversarial learning approach for heterogeneous image-to-video adaptation, which augments deep image and video features by learning domain-invariant representations of source images and target videos. Primarily focusing on an unsupervised scenario where the labeled source images are accompanied by unlabeled target videos in the training phrase, we present a data-driven approach to respectively learn the augmented features of images and videos with superior transformability and distinguishability. Starting with learning a common feature space (called image-frame feature space) between images and video frames, we then build new symmetric generative adversarial networks (Sym-GANs) where one GAN maps image-frame features to video features and the other maps video features to image-frame features. Using the Sym-GANs, the source image feature is augmented with the generated video-specific representation to capture the motion dynamics while the target video feature is augmented with the image-specific representation to take the static appearance information. Finally, the augmented features from the source domain are fed into a network with fully connected layers for classification. Thanks to an end-to-end training procedure of the Sym-GANs and the classification network, our approach achieves better results than other state-of-the-arts, which is clearly validated by experiments on two video datasets, i.e., the UCF101 and HMDB51 datasets.

Moments in Time Dataset: One Million Videos for Event Understanding.

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.

A Novel Lightweight Approach for Video Retrieval on Mobile Augmented Reality Environment

Mobile Augmented Reality merges the virtual objects with real world on mobile devices, while video retrieval brings out the similar looking videos from the large-scale video dataset. Since mobile augmented reality application demands the real-time interaction and operation, we need to process and interact in real-time. Furthermore, augmented reality based virtual objects can be poorly textured. In order to resolve the above mentioned issues, in this research, we propose a novel, fast and robust approach for retrieving videos on the mobile augmented reality environment using an image and video queries. In the beginning, Top-K key-frames are extracted from the videos which significantly increases the efficiency. Secondly, we introduce a novel frame based feature extraction method, namely Pyramid Ternary Histogram of Oriented Gradient (PTHOG) to extract the shape feature from the virtual objects in an effective and efficient manner. Thirdly, we utilize the Double-Bit Quantization (DBQ) based hashing to accomplish the nearest neighbor search efficiently, which produce the candidate list of videos. Lastly, the similarity measure is performed to re-rank the videos which are obtained from the candidate list. An extensive experimental analysis is performed in order to verify our claims.

A Benchmark Dataset and Saliency-Guided Stacked Autoencoders for Video-Based Salient Object Detection.

Image-based salient object detection (SOD) has been extensively studied in past decades. However, video-based SOD is much less explored due to the lack of large-scale video datasets within which salient objects are unambiguously defined and annotated. Toward this end, this paper proposes a video-based SOD dataset that consists of 200 videos. In constructing the dataset, we manually annotate all objects and regions over 7650 uniformly sampled keyframes and collect the eye-tracking data of 23 subjects who free-view all videos. From the user data, we find that salient objects in a video can be defined as objects that consistently pop-out throughout the video, and objects with such attributes can be unambiguously annotated by combining manually annotated object/region masks with eye-tracking data of multiple subjects. To the best of our knowledge, it is currently the largest dataset for video-based salient object detection. Based on this dataset, this paper proposes an unsupervised baseline approach for video-based SOD by using saliency-guided stacked autoencoders. In the proposed approach, multiple spatiotemporal saliency cues are first extracted at the pixel, superpixel, and object levels. With these saliency cues, stacked autoencoders are constructed in an unsupervised manner that automatically infers a saliency score for each pixel by progressively encoding the high-dimensional saliency cues gathered from the pixel and its spatiotemporal neighbors. In experiments, the proposed unsupervised approach is compared with 31 state-of-the-art models on the proposed dataset and outperforms 30 of them, including 19 image-based classic (unsupervised or non-deep learning) models, six image-based deep learning models, and five video-based unsupervised models. Moreover, benchmarking results show that the proposed dataset is very challenging and has the potential to boost the development of video-based SOD.

Object and motion cues based collaborative approach for human activity localization and recognition in unconstrained videos

This paper addresses the problem of activity localization and recognition in large scale video datasets by the collaborative use of holistic and motion based information (called motion cues). The concept of salient objects is used to obtain the holistic information while the motion cues are obtained by affine motion model and optical flow. The motion cues compensate the camera motion and localize the object of interest in a set of object proposals. Furthermore, the holistic information and motion cues are fused to get a reliable object of interest. In recognition phase, the holistic and motion based features are extracted from the object of interest for the training and testing of classifier. The extreme learning machine is adopted as a classifier to reduce the training and testing time and increase the classification accuracy. The effectiveness of the proposed approach is tested on UCF sports dataset. The detailed experimentation reveals that the proposed approach performs better than state-of-the-art action localization and recognition approaches.

Do less and achieve more: Training CNNs for action recognition utilizing action images from the Web

Recently, attempts have been made to collect millions of videos to train Convolutional Neural Network (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. Through extensive experiments, we explore the question of whether we can utilize web action images to train better CNN models for action recognition in videos. We collect 23.8K manually filtered images from the Web that depict the 101 actions in the UCF101 action video dataset. We show that by utilizing web action images along with videos in training, significant performance boosts of CNN models can be achieved. We also investigate the scalability of the process by leveraging crawled web images (unfiltered) for UCF101 and ActivityNet. Using unfiltered images we can achieve performance improvements that are on-par with using filtered images. This means we can further reduce annotation labor and easily scale-up to larger problems. We also shed light on an artifact of finetuning CNN models that reduces the effective parameters of the CNN and show that using web action images can significantly alleviate this problem.

Cloud-Based Actor Identification With Batch-Orthogonal Local-Sensitive Hashing and Sparse Representation

Recognizing and retrieving multimedia content with movie/TV series actors, especially querying actor-specific videos in large scale video datasets, has attracted much attention in both the video processing and computer vision research field. However, many existing methods have low efficiency both in training and testing processes and also a less than satisfactory performance. Considering these challenges, in this paper, we propose an efficient cloud-based actor identification approach with batch-orthogonal local-sensitive hashing (BOLSH) and multi-task joint sparse representation classification. Our approach is featured by the following: 1) videos from movie/TV series are segmented into shots with the cloud-based shot boundary detection; 2) while faces in each shot are detected and tracked, the cloud-based BOLSH is then implemented on these faces for feature description; 3) the sparse representation is then adopted for actor identification in each shot; and 4) finally, a simple application, actor-specific shots retrieval is realized to verify our approach. We conduct extensive experiments and empirical evaluations on a large scale dataset, to demonstrate the satisfying performance of our approach considering both accuracy and efficiency.

DPcode: Privacy-Preserving Frequent Visual Patterns Publication on Cloud

Nowadays, cloud has become a promising multimedia data processing and sharing platform. Many institutes and companies plan to outsource and share their large-scale video and image datasets on cloud for scientific research and public interest. Among various video applications, the discovery of frequent visual patterns over graphical data is an exploratory and important technique. However, the privacy concerns over the leakage of sensitive information contained in the videos/images impedes the further implementation. Although the frequent visual patterns mining (FVPM) algorithm aggregates summary over individual frames and seems not to pose privacy threat, the private information contained in individual frames still may be leaked from the statistical result. In this paper, we study the problem of privacy-preserving publishing of graphical data FVPM on cloud. We propose the first differentially private frequent visual patterns mining algorithm for graphical data, named DPcode. We propose a novel mechanism that integrates the privacy-preserving visual word conversion with the differentially private mechanism under the noise allocation strategy of the sparse vector technique. The optimized algorithms properly allocate the privacy budgets among different phases in FPM algorithm over images and reduce the corresponding data distortion. Extensive experiments are conducted based on datasets commonly used in visual mining algorithms. The results show that our approach achieves high utility while satisfying a practical privacy requirement.

Efficient processing of video containment queries by using composite ordinal features

Video containment queries find the videos that have similar sequence of frames to query video clips. Applying sequence matching to all possible subsequences for video containment queries is computationally expensive for large volumes of video data. In this paper, we propose an efficient candidate segment selection scheme, which selects only a small set of subsequences to be matched to the query sequence, by using a cluster of similar frames, called a frame cluster. We also propose a new type of the ordinal feature, called a composite ordinal feature that allows multiple ranks to certain cells. In experiments with large scale video data sets, we show our method improves the query response time by efficiently selecting a set of subsequences for sequence matching.