Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In this paper, we introduce MovieNet -- a holistic dataset for movie understanding. MovieNet contains 1,100 movies with a large amount of multi-modal data, e.g. trailers, photos, plot descriptions, etc. Besides, different aspects of manual annotations are provided in MovieNet, including 1.1M characters with bounding boxes and identities, 42K scene boundaries, 2.5K aligned description sentences, 65K tags of place and action, and 92K tags of cinematic style. To the best of our knowledge, MovieNet is the largest dataset with richest annotations for comprehensive movie understanding. Based on MovieNet, we set up several benchmarks for movie understanding from different angles. Extensive experiments are executed on these benchmarks to show the immeasurable value of MovieNet and the gap of current approaches towards comprehensive movie understanding. We believe that such a holistic dataset would promote the researches on story-based long video understanding and beyond. MovieNet will be published in compliance with regulations at https://movienet.github.io.
论文检索
输入标题、作者或关键词，从 1,358 篇学术成果中精准定位
Inference & Application","We formalize concepts around geometric occlusion in 2D images (i.e., ignoring semantics), and propose a novel unified formulation of both occlusion boundaries and occlusion orientations via a pixel-pair occlusion relation. The former provides a way to generate large-scale accurate occlusion datasets while, based on the latter, we propose a novel method for task-independent pixel-level occlusion relationship estimation from single images. Experiments on a variety of datasets demonstrate that our method outperforms existing ones on this task. To further illustrate the value of our formulation, we also propose a new depth map refinement method that consistently improve the performance of state-of-the-art monocular depth estimation methods.
In this paper, we propose an efficient and effective dense hybrid recurrent multi-view stereo net with dynamic consistency checking, namely $D^{2}$HC-RMVSNet, for accurate dense point cloud reconstruction. Our novel hybrid recurrent multi-view stereo net consists of two core modules: 1) a light DRENet (Dense Reception Expanded) module to extract dense feature maps of original size with multi-scale context information, 2) a hybrid HRU-LSTM (Hybrid Recurrent U-LSTM) to regularize 3D matching volume into predicted depth map, which efficiently aggregates different scale information by coupling LSTM and U-Net architecture. To further improve the accuracy and completeness of reconstructed point clouds, we leverage a dynamic consistency checking strategy instead of prefixed parameters and strategies widely adopted in existing methods for dense point cloud reconstruction. In doing so, we dynamically aggregate geometric consistency matching error among all the views. Our method ranks extbf{$1^{st}$} on the complex outdoor extsl{Tanks and Temples} benchmark over all the methods. Extensive experiments on the in-door extsl{DTU} dataset show our method exhibits competitive performance to the state-of-the-art method while dramatically reduces memory consumption, which costs only $19.4\%$ of R-MVSNet memory consumption. The codebase is available at \hyperlink{https://github.com/yhw-yhw/D2HC-RMVSNet}{https://github.com/yhw-yhw/D2HC-RMVSNet}.
Recent methods for 6D pose estimation of objects assume either textured 3D models or real images that cover the entire range of target poses. However, it is difficult to obtain textured 3D models and annotate the poses of objects in real scenarios. This paper proposes a method, Neural Object Learning (NOL), that creates synthetic images of objects in arbitrary poses by combining only a few observations from cluttered images. A novel refinement step is proposed to align inaccurate poses of objects in source images, which results in better quality images. Evaluations performed on two public datasets show that the rendered images created by NOL lead to state-of-the-art performance in comparison to methods that use 13 times the number of real images. Evaluations on our new dataset show multiple objects can be trained and recognized simultaneously using a sequence of a fixed scene.
Humans can robustly recognize and localize objects by integrating visual and auditory cues. While machines are able to do the same now with images, less work has been done with sounds. This work develops an approach for dense semantic labelling of sound-making objects, purely based on binaural sounds. We propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a $360^{
This paper considers the generic problem of dense alignment between two images, whether they be two frames of a video, two widely different views of a scene, two paintings depicting similar content, etc. Whereas each such task is typically addressed with a domain-specific solution, we show that a simple unsupervised approach performs surprisingly well across a range of tasks. Our main insight is that parametric and non-parametric alignment methods have complementary strengths. We propose a two-stage process: first, a feature-based parametric coarse alignment using one or more homographies, followed by non-parametric fine pixel-wise alignment. Coarse alignment is performed using RANSAC on off-the-shelf deep features. Fine alignment is learned in an unsupervised way by a deep network which optimizes a standard structural similarity metric (SSIM) between the two images, plus cycle-consistency. Despite its simplicity, our method shows competitive results on a range of tasks and datasets, including unsupervised optical flow on KITTI, dense correspondences on Hpatches, two-view geometry estimation on YFCC100M, localization on Aachen Day-Night, and, for the first time, fine alignment of artworks on the Brughel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/RANSAC-Flow .
Mesh autoencoders are commonly used for dimensionality reduction, sampling and mesh modeling. We propose a general-purpose DEep MEsh Autoencoder \hbox{(DEMEA)} which adds a novel embedded deformation layer to a graph-convolutional mesh autoencoder. The embedded deformation layer (EDL) is a differentiable deformable geometric proxy which explicitly models point displacements of non-rigid deformations in a lower dimensional space and serves as a local rigidity regularizer. DEMEA decouples the parameterization of the deformation from the final mesh resolution since the deformation is defined over a lower dimensional embedded deformation graph. We perform a large-scale study on four different datasets of deformable objects. Reasoning about the local rigidity of meshes using EDL allows us to achieve higher-quality results for highly deformable objects, compared to directly regressing vertex positions. We demonstrate multiple applications of DEMEA, including non-rigid 3D reconstruction from depth and shading cues, non-rigid surface tracking, as well as the transfer of deformations over different meshes.
Training computers to understand, model, and synthesize human grasping requires a rich dataset containing complex 3D object shapes, detailed contact information, hand pose and shape, and the 3D body motion over time. While ""grasping"" is commonly thought of as a single hand stably lifting an object, we capture the motion of the entire body and adopt the generalized notion of ""whole-body grasps"". Thus, we collect a new dataset, called GRAB (GRasping Actions with Bodies), of whole-body grasps, containing full 3D shape and pose sequences of 10 subjects interacting with 51 everyday objects of varying shape and size. Given MoCap markers, we fit the full 3D body shape and pose, including the articulated face and hands, as well as the 3D object pose. This gives detailed 3D meshes over time, from which we compute contact between the body and object. This is a unique dataset, that goes well beyond existing ones for modeling and understanding how humans grasp and manipulate objects, how their full body is involved, and how interaction varies with the task. We illustrate the practical value of GRAB with an example application; we train GrabNet, a conditional generative network, to predict 3D hand grasps for unseen 3D object shapes. The dataset and code are available for research purposes at https://grab.is.tue.mpg.de.
Most of the existing Zero-Shot Learning (ZSL) approaches learn direct embeddings from global features or image parts (regions) to the semantic space, which, however, fail to capture the appearance relationships between different local regions within a single image. In this paper, to model the relations among local image regions, we incorporate the region-based relation reasoning into ZSL. Our method, termed as Region Graph Embedding Network (RGEN), is trained end-to-end from raw image data. Specifically, RGEN consists of two branches: the Constrained Part Attention (CPA) branch and the Parts Relation Reasoning (PRR) branch. CPA branch is built upon attention and produces the image regions. To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch. To train our model, we introduce both a transfer loss and a balance loss to contrast class similarities and pursue the maximum response consistency among seen and unseen outputs, respectively. Extensive experiments on four datasets well validate the effectiveness of the proposed method under both ZSL and generalized ZSL settings.
We propose a learning-based framework for disentangling outdoor scenes into temporally-varying illumination and permanent scene factors. Inspired by the classic intrinsic image decomposition, our learning signal builds upon two insights: 1) combining the disentangled factors should reconstruct the original image, and 2) the permanent factors should stay constant across multiple temporal samples of the same scene. To facilitate training, we assemble a city-scale dataset of outdoor timelapse imagery from Google Street View, where the same locations are captured repeatedly through time. This data represents an unprecedented scale of spatio-temporal outdoor imagery. We show that our learned disentangled factors can be used to manipulate novel images in realistic ways, such as changing lighting effects and scene geometry. Please visit factorize-a-city.github.io for animated results.
In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at other scales, and vice versa. We propose a novel architecture, namely MTI-Net, that builds upon this finding in three ways. First, it explicitly models task interactions at every scale via a multi-scale multi-modal distillation unit. Second, it propagates distilled task information from lower to higher scales via a feature propagation module. Third, it aggregates the refined task features from all scales via a feature aggregation unit to produce the final per-task predictions.Extensive experiments on two multi-task dense labeling datasets show that, unlike prior work, our multi-task model delivers on the full potential of multi-task learning, that is, smaller memory footprint, reduced number of calculations, and better performance w.r.t. single-task learning. The code is made publicly available.
Semi-Supervised Learning (SSL) based on Convolutional Neural Networks (CNNs) have recently been proven as powerful tools for standard tasks such as image classification when there is not a sufficient amount of labeled data available during the training. In this work, we consider the general setting of the SSL problem for image classification, where the labeled and unlabeled data come from the same underlying distribution. We propose a new SSL method that adopts a hierarchical Optimal Transport (OT) technique to find a mapping from empirical unlabeled measures to corresponding labeled measures by leveraging the minimum amount of transportation cost in the label space. Based on this mapping, pseudo-labels for the unlabeled data are inferred, which are then used along with the labeled data for training the CNN. We evaluated and compared our method with state-of-the-art SSL approaches on standard datasets to demonstrate the superiority of our SSL method.
Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly. It is fairly arduous due to the cross-modality translation. In this paper we circumvent this problem by focusing on parsing the content of both the input text and the synthesized image thoroughly to model the text-to-image consistency in the semantic level. Particularly, we design a memory structure to parse the textual content by exploring semantic correspondence between each word in the vocabulary to its various visual contexts across relevant images during text encoding. Meanwhile, the synthesized image is parsed to learn its semantics in an object-aware manner. Moreover, we customize a conditional discriminator to model the fine-grained correlations between words and image sub-regions to push for the text-image semantic alignment. Extensive experiments on COCO dataset manifest that our model advances the state-of-the-art performance significantly (from 35.69 to 52.73 in Inception Score).
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated by pipelines that perform object detection followed by temporal association, also known as tracking-by-detection. In this paper, we present a simultaneous detection and tracking algorithm that is simpler, faster, and more accurate than the state of the art. Our tracker, CenterTrack, applies a detection model to a pair of images and detections from the prior frame. Given this minimal input, CenterTrack localizes objects and predicts their associations with the previous frame. That's it. CenterTrack is simple, online (no peeking into the future), and real-time. It achieves $67.3\%$ MOTA on the MOT17 challenge at 17 FPS and $89.4\%$ MOTA on the KITTI tracking benchmark at 12 FPS, setting a new state of the art on both datasets. CenterTrack is easily extended to monocular 3D tracking by regressing additional 3D attributes. Using monocular video input, it achieves $28.3\%$ AMOTA@0.2 on the newly released nuScenes 3D tracking benchmark, substantially outperforming the monocular baseline on this benchmark while running at 22 FPS.
Unpaired image-to-image translation aims to translate images from the source class to target one by providing sufficient data for these classes. Current few-shot translation methods use multiple reference images to describe the target domain through extracting common features. In this paper, we focus on a more specific identity transfer problem and advocate that particular property in each individual image can also benefit generation. We accordingly propose a new multi-reference identity transfer framework by simultaneously making use of particularity and commonality of reference. It is achieved via a semantic pyramid alignment module to make proper use of geometric information for individual images, as well as an attention module to aggregate for the final transformation. Extensive experiments demonstrate the effectiveness of our framework given the promising results in a number of identity transfer applications.
In this paper, we unconventionally propose to adopt appropriate negative-margin to softmax loss for few-shot classification, which surprisingly works well for the open-set scenarios of few-shot classification. We then provide the intuitive explanation and the theoretical proof to understand why negative margin works well for few-shot classification. This claim is also demonstrated via sufficient experiments. With the negative-margin softmax loss, our approach achieves the state-of-the-art performance on all three standard benchmarks of few-shot classification. In the future, the negative margin may be applied in more general open-set scenarios that do not restrict the number of samples in novel classes.
In this paper, we study an intermediate form of supervision, i.e., single-frame supervision, for temporal action localization (TAL). To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action. This can significantly reduce the labor cost of obtaining full supervision which requires annotating the action boundary. Compared to the weak supervision that only annotates the video-level label, the single-frame supervision introduces extra temporal action signals while maintaining low annotation overhead. To make full use of such single-frame supervision, we propose a unified system called SF-Net. First, we propose to predict an actionness score for each video frame. Along with a typical category score, the actionness score can provide comprehensive information about the occurrence of a potential action and aid the temporal boundary refinement during inference. Second, we mine pseudo action and background frames based on the single-frame annotations. We identify pseudo action frames by adaptively expanding each annotated single frame to its nearby, contextual frames and we mine pseudo background frames from all the unannotated frames across multiple videos. Together with the ground-truth labeled frames, these pseudo-labeled frames are further used for training the classifier.
Current object detection frameworks mainly rely on bounding box regression to localize objects. Despite the remarkable progress in recent years, the precision of bounding box regression remains unsatisfactory, hence limiting performance in object detection. We observe that precise localization requires careful placement of each side of the bounding box. However, the mainstream approach, which focuses on predicting centers and sizes, is not the most effective way to accomplish this task, especially when there exists displacements with large variance between the anchors and the targets. In this paper, we propose an alternative approach, named as Side-Aware Boundary Localization (SABL), where each side of the bounding box is respectively localized with a dedicated network branch. To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket. We test the proposed method on both two-stage and single-stage detection frameworks. Replacing the standard bounding box regression branch with the proposed design leads to significant improvements on Faster R-CNN, RetinaNet, and Cascade R-CNN, by 3.0%, 1.7%, and 0.9%, respectively. Code is available at https://github.com/open-mmlab/mmdetection.
Novel view video synthesis aims to synthesize novel viewpoints videos given input captures of a human performance taken from multiple reference viewpoints and over consecutive time steps. Despite great advances in model-free novel view synthesis, existing methods present three limitations when applied to complex and time-varying human performance. First, these methods (and related datasets) mainly consider simple and symmetric objects. Second, they do not enforce explicit consistency across generated views. Third, they focus on static and non-moving objects. The fine-grained details of a human subject can therefore suffer from inconsistencies when synthesized across different viewpoints or time steps. To tackle these challenges, we introduce a human-specific framework that employs a learned 3D-aware representation. Specifically, we first introduce a novel siamese network that employs a gating layer for better reconstruction of the latent volumetric representation and, consequently, final visual results. Moreover, features from consecutive time steps are shared inside the network to improve temporal consistency. Second, we introduce a novel loss to explicitly enforce consistency across generated views both in space and in time. Third, we present the Multi-View Human Action (MVHA) dataset, consisting of near 1200 synthetic human performance captured from 54 viewpoints. Experiments on the MVHA, Pose-Varying Human Model and ShapeNet datasets show that our method outperforms the state-of-the-art baselines both in view generation quality and spatio-temporal consistency.
The task of large-scale retrieval-based image localization is to estimate the geographical location of a query image by recognizing its nearest reference images from a city-scale dataset. However, the general public benchmarks only provide noisy GPS labels associated with the training images, which act as weak supervisions for learning image-to-image similarities. Such label noise prevents deep neural networks from learning discriminative features for accurate localization. To tackle this challenge, we propose to self-supervise image-to-region similarities in order to fully explore the potential of difficult positive images alongside their sub-regions. The estimated image-to-region similarities can serve as extra training supervision for improving the network in generations, which could in turn gradually refine the fine-grained similarities to achieve optimal performance. Our proposed self-enhanced image-to-region similarity labels effectively deal with the training bottleneck in the state-of-the-art pipelines without any additional parameters or manual annotations in both training and inference. Our method outperforms state-of-the-arts on the standard localization benchmarks by noticeable margins and shows excellent generalization capability on multiple image retrieval datasets.