ECCV 2018 Papers

License plate recognition (LPR) is a fundamental component of various intelligent transport systems, which is always expected to be accurate and efficient enough. In this paper, we propose a novel LPR framework consisting of semantic segmentation and character counting, towards achieving human-level performance. Benefiting from innovative structure, our method can recognize a whole license plate once rather than conducting character detection or sliding window followed by per-character recognition. Moreover, our method can achieve higher recognition accuracy due to more effectively exploiting global information and avoiding sensitive character detection, and is time-saving due to eliminating one-by-one character recognition. Finally, we experimentally verify the effectiveness of the proposed method on two public datasets (AOLP and Media Lab) and our License Plate Dataset. The results demonstrate our method significantly outperforms the previous state-of-the-art methods, and achieves the accuracies of more than 99% for almost all settings.

Most current license plate (LP) detection and recognition approaches are evaluated on a small and usually unrepresentative dataset since there are no publicly available large diverse datasets. In this paper, we introduce CCPD, a large and comprehensive LP dataset. All images are taken manually by workers of a roadside parking management company and are annotated carefully. To our best knowledge, CCPD is the largest publicly available LP dataset to date with over 250k unique car images, and the only one provides vertices location annotations. With CCPD, we present a novel network model which can predict the bounding box and recognize the corresponding LP number simultaneously with high speed and accuracy. Through comparative experiments, we demonstrate our model outperforms current object detection and recognition approaches in both accuracy and speed. In real-world applications, our model recognizes LP numbers directly from relatively high-resolution images at over 61 fps and 98.5% accuracy.

Accurately localising object proposals is an important precondition for high detection rate for the state-of-the-art object detection frameworks. The accuracy of an object detection method has been shown highly related to the average recall (AR) of the proposals. In this work, we propose an advanced object proposal network in favour of translation-invariance for objectness classification, translation-variance for bounding box regression, large effective receptive fields for capturing global context and scale-invariance for dealing with a range of object sizes from extremely small to large. The design of the network architecture aims to be simple while being effective and with real-time performance. Without bells and whistles the proposed object proposal network significantly improves AR at 1,000 proposals by 35% and 45% on PASCAL VOC and COCO dataset respectively and has a fast inference time of 44.8 ms for input image size of 640x640. Empirical studies have also shown that the proposed method is class-agnostic to be generalised for general object proposal.

Image-based virtual try-on systems for fitting new in-shop clothes into a person image have attracted increasing research attention, yet is still challenging. A desirable pipeline should not only transform the target clothes into the most fitting shape seamlessly but also preserve well the clothes identity in the generated image, that is, the key characteristics (e.g. texture, logo, embroidery) that depict the original clothes. However, previous image-conditioned generation works fail to meet these critical requirements towards the plausible virtual try-on performance since they fail to handle large spatial misalignment between the input image and target clothes. Prior work explicitly tackled spatial deformation using shape context matching, but failed to preserve clothing details due to its coarse-to-fine strategy. In this work, we propose a new fully-learnable Characteristic-Preserving Virtual Try-On Network(CP-VTON) for addressing all real-world challenges in this task. First, CP-VTON learns a thin-plate spline transformation for transforming the in-shop clothes into fitting the body shape of the target person via a new Geometric Matching Module (GMM) rather than computing correspondences of interest points as prior works did. Second, to alleviate boundary artifacts of warped clothes and make the results more realistic, we employ a Try-On Module that learns a composition mask to integrate the warped clothes and the rendered image to ensure smoothness. Extensive experiments on a fashion dataset demonstrate our CP-VTON achieves the state-of-the-art virtual try-on performance both qualitatively and quantitatively.

This paper is on image and face super-resolution. The vast majority of prior work for this problem focus on how to increase the resolution of low-resolution images which are artificially generated by simple bilinear down-sampling (or in a few cases by blurring followed by down-sampling). We show that such methods fail to produce good results when applied to real-world low-resolution, low quality images. To circumvent this problem, we propose a two-stage process which firstly trains a High-to-Low Generative Adversarial Network (GAN) to learn how to degrade and downsample high-resolution images requiring, during training, only extit{unpaired} high and low-resolution images. Once this is achieved, the output of this network is used to train a Low-to-High GAN for image super-resolution using this time extit{paired} low- and high-resolution images. Our main result is that this network can be now used to effectively increase the quality of real-world low-resolution images. We have applied the proposed pipeline for the problem of face super-resolution where we report large improvement over baselines and prior work although the proposed method is potentially applicable to other object categories.

With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenarios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80,000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the first time to explore such issues in unconstrained scenes comprehensively. The dataset and all the experimental results are available in https://sites.google.com/site/daviddo0323/.

We introduce PixelPlayer, a system that, by leveraging large amounts of unlabeled videos, learns to locate image regions which produce sounds and separate the input sounds into a set of components that represents the sound from each pixel. Our approach capitalizes on the natural synchronization of the visual and audio modalities to learn models that jointly parse sounds and images, without requiring additional manual supervision. Experimental results on a newly collected MUSIC dataset show that our proposed Mix-and-Separate framework outperforms several baselines on source separation. Qualitative results suggest our model learns to ground sounds in vision, enabling applications such as independently adjusting the volume of sound sources.

Image partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments; or equivalently, the task of detecting closed contours in an image. Most prior work either requires seeds, one per segment; or a threshold; or formulates the task as an NP-hard signed graph partitioning problem. Here, we propose an algorithm with empirically linearithmic complexity. Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold. The algorithm itself, which we dub “mutex watershed”, is closely related to a minimal spanning tree computation. It is deterministic and easy to implement. When presented with short-range attractive and long-range repulsive cues from a deep neural network, the mutex watershed gives results that currently define the state-of-the-art in the competitive ISBI 2012 EM segmentation benchmark. These results are also better than those obtained from other recently proposed clustering strategies operating on the very same network outputs.

The growing scale of face recognition datasets empowers us to train strong convolutional networks for face recognition. While a variety of architectures and loss functions have been devised, we still have a limited understanding of the source and consequence of label noise inherent in existing datasets. We make the following contributions: 1) We contribute cleaned subsets of popular face databases, i.e., MegaFace and MS-Celeb-1M datasets, and build a new large-scale noise-controlled IMDb-Face dataset. 2) With the original datasets and cleaned subsets, we profile and analyze label noise properties of MegaFace and MS-Celeb-1M. We show that a few orders more samples are needed to achieve the same accuracy yielded by a clean subset. 3) We study the association between different types of noise, i.e., label flips and outliers, with the accuracy of face recognition models. 4) We investigate ways to improve data cleanliness, including a comprehensive user study on the influence of data labeling strategies to annotation accuracy. The IMDb-Face dataset has been released on https://github.com/fwang91/IMDb-Face.

Feed-forward CNNs trained for image transformation problems rely on loss functions that measure the similarity between the generated image and a target image. Most of the common loss functions assume that these images are spatially aligned and compare pixels at corresponding locations. However, for many tasks, aligned training pairs of images will not be available. We present an alternative loss function that does not require alignment, thus providing an effective and simple solution for a new space of problems. Our loss is based on both context and semantics -- it compares regions with similar semantic meaning, while considering the context of the entire image. Hence, for example, when transferring the style of one face to another, it will translate eyes-to-eyes and mouth-to-mouth.

Deep neural perception and control networks have become key components of self-driving vehicles. User acceptance is likely to benefit from easy-to-interpret textual explanations which allow end-users to understand what triggered a particular behavior. Explanations may be triggered by the neural controller, namely introspective explanations, or informed by the neural controller's output, namely rationalizations. We propose a new approach to introspective explanations which consists of two parts. First, we use a visual (spatial) attention model to train a convolutional network end-to-end from images to the vehicle control commands, i.e., acceleration and change of course. The controller's attention identifies image regions that potentially influence the network's output. Second, we use an attention-based video-to-text model to produce textual explanations of model actions. The attention maps of controller and explanation model are aligned so that explanations are grounded in the parts of the scene that mattered to the controller. We explore two approaches to attention alignment, strong- and weak-alignment. Finally, we explore a version of our model that generates rationalizations, and compare with introspective explanations on the same video segments. We evaluate these models on a novel driving dataset with ground-truth human explanations, the Berkeley DeepDrive eXplanation (BDD-X) dataset. Code is available at https://github.com/JinkyuKimUCB/explainable-deep-driving.

Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the representations (axis-aligned rectangles, rotated rectangles or quadrangles) adopted to describe text, existing methods may fall short when dealing with much more free-form text instances, such as curved text, which are actually very common in real-world scenarios. To tackle this problem, we propose a more flexible representation for scene text, termed as extit{TextSnake}, which is able to effectively represent text instances in horizontal, oriented and curved forms. In TextSnake, a text instance is described as a sequence of ordered, overlapping disks centered at symmetric axes, each of which is associated with potentially variable radius and orientation. Such geometry attributes are estimated via a Fully Convolutional Network (FCN) model. In experiments, the text detector based on TextSnake achieves state-of-the-art performance on Total-Text and SCUT-CTW1500, the two newly published benchmarks with special emphasis on curved text in natural images, as well as the widely-used datasets ICDAR 2015 and MSRA-TD500. Specifically, TextSnake outperforms the baseline on Total-Text by more than extit{$40%$} in F-measure.

Temporal relational reasoning, the ability to link meaningful transformations of objects or entities over time, is a fundamental property of intelligent species. In this paper, we introduce an effective and interpretable network module, the Temporal Relation Network (TRN), designed to learn and reason about temporal dependencies between video frames at multiple time scales. We evaluate TRN-equipped networks on activity recognition tasks using three recent video datasets - Something-Something, Jester, and Charades - which fundamentally depend on temporal relational reasoning. Our results demonstrate that the proposed TRN gives convolutional neural networks a remarkable capacity to discover temporal relations in videos. Through only sparsely sampled video frames, TRN-equipped networks can accurately predict human-object interactions in the Something-Something dataset and identify various human gestures on the Jester dataset with very competitive performance. TRN-equipped networks also outperform two-stream networks and 3D convolution networks in recognizing daily activities in the Charades dataset. Further analyses show that the models learn intuitive and interpretable visual common sense knowledge in videos.

A major challenge in computer vision is scaling activity understanding to the long tail of complex activities without requiring collecting large quantities of data for new actions. The task of video retrieval using natural language descriptions seeks to address this through rich, unconstrained supervision about complex activities. However, while this formulation offers hope of leveraging underlying compositional structure in activity descriptions, existing approaches typically do not explicitly model compositional reasoning. In this work, we introduce an approach for explicitly and dynamically reasoning about compositional natural language descriptions of activity in videos. We take a modular neural network approach that, given a natural language query, extracts the semantic structure to assemble a compositional neural network layout and corresponding network modules. We show that this approach is able to achieve state-of-the-art results on the DiDeMo video retrieval dataset.

A major obstacle in teaching machines to understand videos is the lack of training data, as creating temporal annotations for long videos requires a huge amount of human effort. To this end, we introduce a new large-scale baseball video dataset called the BBDB, which is produced semi-automatically by using play-by-play texts available online. The BBDB contains 4200 hours of baseball game videos with 400k temporally annotated activity segments. The new dataset has several major challenging factors compared to other datasets: 1) the dataset contains a large number of visually similar segments with different labels. 2) It can be used for many video understanding tasks including video recognition, localization, text-video alignment, video highlight generation, and data imbalance problem. To observe the potential of the BBDB, we conducted extensive experiments by running many different types of video understanding algorithms on our new dataset. The database is available at https://sites.google.com/site/eccv2018bbdb/

In this paper, we present an end-to-end learning framework for predicting task-driven visual saliency on webpages. Given a webpage, we propose a convolutional neural network to predict where people look at it under different task conditions. Inspired by the observation that given a specific task, human attention is strongly correlated with certain semantic components on a webpage (e.g., images, buttons and input boxes), our network explicitly disentangles saliency prediction into two independent sub-tasks: task-specific attention shift prediction and task-free saliency prediction. The task-specific branch estimates task-driven attention shift over a webpage from its semantic components, while the task-free branch infers visual saliency induced by visual features of the webpage. The outputs of the two branches are combined to produce the final prediction. Such a task decomposition framework allows us to efficiently learn our model from a small-scale task-driven saliency dataset with sparse labels (captured under a single task condition). Experimental results show that our method outperforms the baselines and prior works, achieving state-of-the-art performance on a newly collected benchmark dataset for task-driven webpage saliency detection.

Image downscaling is one of the most classical problems in computer vision that aims to preserve the visual appearance of the original image when it is resized to a smaller scale. Upscaling a small image back to its original size is a difficult, ill-posed problem due to information loss that arises in the downscaling process. In this paper, we present a novel operation called task-aware image downscaling to support an upscaling task. We propose an auto-encoder-based framework that enables joint learning of the downscaling network and the upscaling network to maximize the restoration performance. Our framework is efficient, and it can be generalized to handle an arbitrary image resizing operation. Experimental results show that our task-aware downscaled image, greatly improved the super-resolution performance of the previous state-of-the-art. In addition, realistic images can be recovered by recursively applying our scaling model up to an extreme scaling factor of x128. We validate our model's generalization capability by applying it to the task of image colorization.

Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras. We propose a two-stage, deep-learning approach to address all of these sources of artifacts simultaneously. We also introduce FLAT, a synthetic dataset of 2000 ToF measurements that capture all of these nonidealities, and allows to simulate different camera hardware. Using the Kinect 2 camera as a baseline, we show improved reconstruction errors over state-of-the-art methods, on both simulated and real data.

This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS2C). We observe that object candidates mined through current multiple instance learning methods are usually trapped to discriminative object parts, rather than the entire object. TS2C leverages surrounding segmentation context derived from weakly-supervised segmentation to suppress such low-quality distracting candidates and boost the high-quality ones. Specifically, TS2C is developed based on two key properties of desirable bounding boxes: 1) high purity, meaning most pixels in the box are with high object response, and 2) high completeness, meaning the box covers high object response pixels comprehensively. With such novel and computable criteria, more tight candidates can be discovered for learning a better object detector. With TS2C, we obtain 48.0% and 44.4% mAP scores on VOC 2007 and 2012 benchmarks, which are the new state-of-the-arts.