CVPR 2017 论文列表

Collecting fully annotated image datasets is challenging and expensive. Many types of weak supervision have been explored: weak manual annotations, web search results, temporal continuity, ambient sound and others. We focus on one particular unexplored mode: visual questions that are asked about images. The key observation that inspires our work is that the question itself provides useful information about the image (even without the answer being available). For instance, the question "what is the breed of the dog?" informs the AI that the animal in the scene is a dog and that there is only one dog present. We make three contributions: (1) providing an extensive qualitative and quantitative analysis of the information contained in human visual questions, (2) proposing two simple but surprisingly effective modifications to the standard visual question answering models that allow them to make use of weak supervision in the form of unanswered questions associated with images and (3) demonstrating that a simple data augmentation strategy inspired by our insights results in a 7.1% improvement on the standard VQA benchmark.

Finding what is and what is not a salient object can be helpful in developing better features and models in salient object detection (SOD). In this paper, we investigate the images that are selected and discarded in constructing a new SOD dataset and find that many similar candidates, complex shape and low objectness are three main attributes of many non-salient objects. Moreover, objects may have diversified attributes that make them salient. As a result, we propose a novel salient object detector by ensembling linear exemplar regressors. We first select reliable foreground and background seeds using the boundary prior and then adopt locally linear embedding (LLE) to conduct manifold-preserving foregroundness propagation. In this manner, a foregroundness map can be generated to roughly pop-out salient objects and suppress non-salient ones with many similar candidates. Moreover, we extract the shape, foregroundness and attention descriptors to characterize the extracted object proposals, and a linear exemplar regressor is trained to encode how to detect salient proposals in a specific image. Finally, various linear exemplar regressors are ensembled to form a single detector that adapts to various scenarios. Extensive experimental results on 5 dataset and the new SOD dataset show that our approach outperforms 9 state-of-art methods.

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 discriminative localization technique to reject false alarms in retrieved videos and identify relevant spatio-temporal volumes within retrieved videos. Although the entire procedure does not require any additional supervision, the segmentation annotations obtained from videos are sufficiently strong to learn a model for semantic segmentation. The proposed algorithm substantially outperforms existing methods based on the same level of supervision and is even as competitive as the approaches relying on extra annotations.

We introduce the task of Visual Dialog, which requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a question about the image, the agent has to ground the question in image, infer context from history, and answer the question accurately. Visual Dialog is disentangled enough from a specific downstream task so as to serve as a general test of machine intelligence, while being grounded in vision enough to allow objective evaluation of individual responses and benchmark progress. We develop a novel two-person chat data-collection protocol to curate a large-scale Visual Dialog dataset (VisDial). VisDial contains 1 dialog (10 question- answer pairs) on 140k images from the COCO dataset, with a total of 1.4M dialog question-answer pairs. We introduce a family of neural encoder-decoder models for Visual Dialog with 3 encoders (Late Fusion, Hierarchical Recurrent Encoder and Memory Network) and 2 decoders (generative and discriminative), which outperform a number of sophisticated baselines. We propose a retrieval-based evaluation protocol for Visual Dialog where the AI agent is asked to sort a set of candidate answers and evaluated on metrics such as mean-reciprocal-rank of human response. We quantify gap between machine and human performance on the Visual Dialog task via human studies. Our dataset, code, and trained models will be released publicly at https://visualdialog.org. Putting it all together, we demonstrate the first 'visual chatbot'!

Video frame interpolation typically involves two steps: motion estimation and pixel synthesis. Such a two-step approach heavily depends on the quality of motion estimation. This paper presents a robust video frame interpolation method that combines these two steps into a single process. Specifically, our method considers pixel synthesis for the interpolated frame as local convolution over two input frames. The convolution kernel captures both the local motion between the input frames and the coefficients for pixel synthesis. Our method employs a deep fully convolutional neural network to estimate a spatially-adaptive convolution kernel for each pixel. This deep neural network can be directly trained end to end using widely available video data without any difficult-to-obtain ground-truth data like optical flow. Our experiments show that the formulation of video interpolation as a single convolution process allows our method to gracefully handle challenges like occlusion, blur, and abrupt brightness change and enables high-quality video frame interpolation.

Person re-identification is an open and challenging problem in computer vision. Existing approaches have concentrated on either designing the best feature representation or learning optimal matching metrics in a static setting where the number of cameras are fixed in a network. Most approaches have neglected the dynamic and open world nature of the re-identification problem, where a new camera may be temporarily inserted into an existing system to get additional information. To address such a novel and very practical problem, we propose an unsupervised adaptation scheme for re-identification models in a dynamic camera network. First, we formulate a domain perceptive re-identification method based on geodesic flow kernel that can effectively find the best source camera (already installed) to adapt with a newly introduced target camera, without requiring a very expensive training phase. Second, we introduce a transitive inference algorithm for re-identification that can exploit the information from best source camera to improve the accuracy across other camera pairs in a network of multiple cameras. Extensive experiments on four benchmark datasets demonstrate that the proposed approach significantly outperforms the state-of-the-art unsupervised learning based alternatives whilst being extremely efficient to compute.

Text instance as one category of self-described objects provides valuable information for understanding and describing cluttered scenes. In this paper, we explore the task of unambiguous text localization and retrieval, to accurately localize a specific targeted text instance in a cluttered image given a natural language description that refers to it. To address this issue, first a novel recurrent Dense Text Localization Network (DTLN) is proposed to sequentially decode the intermediate convolutional representations of a cluttered scene image into a set of distinct text instance detections. Our approach avoids repeated detections at multiple scales of the same text instance by recurrently memorizing previous detections, and effectively tackles crowded text instances in close proximity. Second, we propose a Context Reasoning Text Retrieval (CRTR) model, which jointly encodes text instances and their context information through a recurrent network, and ranks localized text bounding boxes by a scoring function of context compatibility. Quantitative evaluations on standard scene text localization benchmarks and a newly collected scene text retrieval dataset demonstrate the effectiveness and advantages of our models for both scene text localization and retrieval.

Efficient estimation of depth from pairs of stereo images is one of the core problems in computer vision. We efficiently solve the specialized problem of stereo matching under active illumination using a new learning-based algorithm. This type of 'active' stereo i.e. stereo matching where scene texture is augmented by an active light projector is proving compelling for designing depth cameras, largely due to improved robustness when compared to time of flight or traditional structured light techniques. Our algorithm uses an unsupervised greedy optimization scheme that learns features that are discriminative for estimating correspondences in infrared images. The proposed method optimizes a series of sparse hyperplanes that are used at test time to remap all the image patches into a compact binary representation in O(1). The proposed algorithm is cast in a PatchMatch Stereo-like framework, producing depth maps at 500Hz. In contrast to standard structured light methods, our approach generalizes to different scenes, does not require tedious per camera calibration procedures and is not adversely affected by interference from overlapping sensors. Extensive evaluations show we surpass the quality and overcome the limitations of current depth sensing technologies.

Training object class detectors typically requires a large set of images with objects annotated by bounding boxes. However, manually drawing bounding boxes is very time consuming. In this paper we greatly reduce annotation time by proposing center-click annotations: we ask annotators to click on the center of an imaginary bounding box which tightly encloses the object instance. We then incorporate these clicks into existing Multiple Instance Learning techniques for weakly supervised object localization, to jointly localize object bounding boxes over all training images. Extensive experiments on PASCAL VOC 2007 and MS COCO show that: (1) our scheme delivers high-quality detectors, performing substantially better than those produced by weakly supervised techniques, with a modest extra annotation effort; (2) these detectors in fact perform in a range close to those trained from manually drawn bounding boxes; (3) as the center-click task is very fast, our scheme reduces total annotation time by 9x to 18x.

One characteristic that sets humans apart from modern learning-based computer vision algorithms is the ability to acquire knowledge about the world and use that knowledge to reason about the visual world. Humans can learn about the characteristics of objects and the relationships that occur between them to learn a large variety of visual concepts, often with few examples. This paper investigates the use of structured prior knowledge in the form of knowledge graphs and shows that using this knowledge improves performance on image classification. We build on recent work on end-to-end learning on graphs, introducing the Graph Search Neural Network as a way of efficiently incorporating large knowledge graphs into a vision classification pipeline. We show in a number of experiments that our method outperforms standard neural network baselines for multi-label classification.

Non-line-of-sight (NLOS) imaging utilizes the full 5D light transient measurements to reconstruct scenes beyond the camera's field of view. Mathematically, this requires solving an elliptical tomography problem that unmixes the shape and albedo from spatially-multiplexed measurements of the NLOS scene. In this paper, we propose a new approach for NLOS imaging by studying the properties of first-returning photons from three-bounce light paths. We show that the times of flight of first-returning photons are dependent only on the geometry of the NLOS scene and each observation is almost always generated from a single NLOS scene point. Exploiting these properties, we derive a space carving algorithm for NLOS scenes. In addition, by assuming local planarity, we derive an algorithm to localize NLOS scene points in 3D and estimate their surface normals. Our methods do not require either the full transient measurements or solving the hard elliptical tomography problem. We demonstrate the effectiveness of our methods through simulations as well as real data captured from a SPAD sensor.

Visual narrative is often a combination of explicit information and judicious omissions, relying on the viewer to supply missing details. In comics, most movements in time and space are hidden in the "gutters" between panels. To follow the story, readers logically connect panels together by inferring unseen actions through a process called "closure". While computers can now describe the content of natural images, in this paper we examine whether they can understand the closure-driven narratives conveyed by stylized artwork and dialogue in comic book panels. We collect a dataset, COMICS, that consists of over 1.2 million panels (120 GB) paired with automatic textbox transcriptions. An in-depth analysis of COMICS demonstrates that neither text nor image alone can tell a comic book story, so a computer must understand both modalities to keep up with the plot. We introduce three cloze-style tasks that ask models to predict narrative and character-centric aspects of a panel given n preceding panels as context. Various deep neural architectures underperform human baselines on these tasks, suggesting that COMICS contains fundamental challenges for both vision and language.

We propose a novel measure for template matching named Deformable Diversity Similarity -- based on the diversity of feature matches between a target image window and the template. We rely on both local appearance and geometric information that jointly lead to a powerful approach for matching. Our key contribution is a similarity measure, that is robust to complex deformations, significant background clutter, and occlusions. Empirical evaluation on the most up-to-date benchmark shows that our method outperforms the current state-of-the-art in its detection accuracy while improving computational complexity.

Vision and language understanding has emerged as a subject undergoing intense study in Artificial Intelligence. Among many tasks in this line of research, visual question answering (VQA) has been one of the most successful ones, where the goal is to learn a model that understands visual content at region-level details and finds their associations with pairs of questions and answers in the natural language form. Despite the rapid progress in the past few years, most existing work in VQA have focused primarily on images. In this paper, we focus on extending VQA to the video domain and contribute to the literature in three important ways. First, we propose three new tasks designed specifically for video VQA, which require spatio-temporal reasoning from videos to answer questions correctly. Next, we introduce a new large-scale dataset for video VQA named TGIF-QA that extends existing VQA work with our new tasks. Finally, we propose a dual-LSTM based approach with both spatial and temporal attention, and show its effectiveness over conventional VQA techniques through empirical evaluations.

We present a method for synthesizing a frontal, neutral-expression image of a person's face, given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous generative approaches, our encoding feature vector is largely invariant to lighting, pose, and facial expression. Exploiting this invariance, we train our decoder network using only frontal, neutral-expression photographs. Since these photographs are well aligned, we can decompose them into a sparse set of landmark points and aligned texture maps. The decoder then predicts landmarks and textures independently and combines them using a differentiable image warping operation. The resulting images can be used for a number of applications, such as analyzing facial attributes, exposure and white balance adjustment, or creating a 3-D avatar.

In this paper, we study the problem of semantic annotation on 3D models that are represented as shape graphs. A functional view is taken to represent localized information on graphs, so that annotations such as part segment or keypoint are nothing but 0-1 indicator vertex functions. Compared with images that are 2D grids, shape graphs are irregular and non-isomorphic data structures. To enable the prediction of vertex functions on them by convolutional neural networks, we resort to spectral CNN method that enables weight sharing by parametrizing kernels in the spectral domain spanned by graph Laplacian eigenbases. Under this setting, our network, named SyncSpecCNN, strives to overcome two key challenges: how to share coefficients and conduct multi-scale analysis in different parts of the graph for a single shape, and how to share information across related but different shapes that may be represented by very different graphs. Towards these goals, we introduce a spectral parametrization of dilated convolutional kernels and a spectral transformer network. Experimentally we tested SyncSpecCNN on various tasks, including 3D shape part segmentation and keypoint prediction. State-of-the-art performance has been achieved on all benchmark datasets.

The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-to-apples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN (Ren et al., 2015), R-FCN (Dai et al., 2016) and SSD (Liu et al., 2016) systems, which we view as "meta-architectures" and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.

The performance of image retrieval has been improved tremendously in recent years through the use of deep feature representations. Most existing methods, however, aim to retrieve images that are visually similar or semantically relevant to the query, irrespective of spatial configuration. In this paper, we develop a spatial-semantic image search technology that enables users to search for images with both semantic and spatial constraints by manipulating concept text-boxes on a 2D query canvas. We train a convolutional neural network to synthesize appropriate visual features that captures the spatial-semantic constraints from the user canvas query. We directly optimize the retrieval performance of the visual features when training our deep neural network. These visual features then are used to retrieve images that are both spatially and semantically relevant to the user query. The experiments on large-scale datasets such as MS-COCO and Visual Genome show that our method outperforms other baseline and state-of-the-art methods in spatial-semantic image search.

Shape models provide a compact parameterization of a class of shapes, and have been shown to be important to a variety of vision problems, including object detection, tracking, and image segmentation. Learning generative shape models from grid-structured representations, aka silhouettes, is usually hindered by (1) data likelihoods with intractable marginals and posteriors, (2) high-dimensional shape spaces with limited training samples (and the associated risk of overfitting), and (3) estimation of hyperparameters relating to model complexity that often entails computationally expensive grid searches. In this paper, we propose a Bayesian treatment that relies on direct probabilistic formulation for learning generative shape models in the silhouettes space. We propose a variational approach for learning a latent variable model in which we make use of, and extend, recent works on variational bounds of logistic-Gaussian integrals to circumvent intractable marginals and posteriors. Spatial coherency and sparsity priors are also incorporated to lend stability to the optimization problem by regularizing the solution space while avoiding overfitting in this high-dimensional, low-sample-size scenario. We deploy a type-II maximum likelihood estimate of the model hyperparameters to avoid grid searches. We demonstrate that the proposed model generates realistic samples, generalizes to unseen examples, and is able to handle missing regions and/or background clutter, while comparing favorably with recent, neural-network-based approaches.