ECCV 2018 论文列表

We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set of camera views. Our method yields similar end-to-end reconstruction error to that of a probabilistic visual hull computed using significantly more (double or more) viewpoints. We use a deep prior implicitly learned by the autoencoder trained over a dataset of view-ablated multi-view video footage of a wide range of subjects and actions. This opens up the possibility of high-end volumetric performance capture in on-set and prosumer scenarios where time or cost prohibit a high witness camera count.

We present a method to populate an unknown environment with models of previously seen objects, placed in a Euclidean reference frame that is inferred causally and on-line using monocular video along with inertial sensors. The system we implement returns a sparse point cloud for the regions of the scene that are visible but not recognized as a previously seen object, and a detailed object model and its pose in the Euclidean frame otherwise. The system includes bottom-up and top-down components, whereby deep networks trained for detection provide likelihood scores for object hypotheses provided by a nonlinear filter, whose state serves as memory. Additional networks provide likelihood scores for edges, which complements detection networks trained to be invariant to small deformations. We test our algorithm on existing datasets, and also introduce the VISMA dataset, that provides ground truth pose, point-cloud map, and object models, along with time-stamped inertial measurements.

Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background. This assumption however yields undesired boundary effects and restricts aspect ratios of search samples. To handle these issues, an end-to-end deep architecture is proposed to incorporate geometric transformations into a correlation filters based network. This architecture introduces a novel spatial alignment module, which provides continuous feedback for transforming the target from the border to the center with a normalized aspect ratio. It enables correlation filters to work on well-aligned samples for better tracking. The whole architecture not only learns a generic relationship between object geometric transformations and object appearances, but also learns robust representations coupled to correlation filters in case of various geometric transformations. This lightweight architecture permits real-time speed. Experiments show our tracker effectively handles boundary effects and aspect ratio variations, achieving state-of-the-art tracking results on three benchmarks.

Videos, images, and sentences are mediums that can express the same semantics. One can imagine a picture by reading a sentence or can describe a scene with some words. However, even small changes in a sentence can cause a significant semantic inconsistency with the corresponding video/image. For example, by changing the verb of a sentence, the meaning may drastically change. There have been many efforts to encode a video/sentence and decode it as a sentence/video. In this research, we study a new scenario in which both the sentence and the video are given, but the sentence is inaccurate. A semantic inconsistency between the sentence and the video or between the words of a sentence can result in an inaccurate description. This paper introduces a new problem, called Visual Text Correction (VTC), i.e., finding and replacing an inaccurate word in the textual description of a video. We propose a deep network that can simultaneously detect an inaccuracy in a sentence, and fix it by replacing the inaccurate word(s). Our method leverages the semantic interdependence of videos and words, as well as the short-term and long-term relations of the words in a sentence. In our formulation, part of a visual feature vector for every single word is dynamically selected through a gating process. Furthermore, to train and evaluate our model, we propose an approach to automatically construct a large dataset for VTC problem. Our experiments and performance analysis demonstrates that the proposed method provides very good results and also highlights the general challenges in solving the VTC problem. To the best of our knowledge, this work is the first of its kind for the Visual Text Correction task.

Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue. For such tasks, one successful approach is to condition image-based convolutional network computation on language via Feature-wise Linear Modulation (FiLM) layers, i.e., per-channel scaling and shifting. By alternating between attending to the language input and generating FiLM layer parameters, this approach is better able to scale to settings with longer input sequences such as dialogue. We demonstrate that multi-hop FiLM generation significantly outperforms prior state-of-the-art on the GuessWhat?! visual dialogue task and matches state-of-the art on the ReferIt object retrieval task, and we provide additional qualitative analysis.

Traditional image recognition methods only consider objects belonging to already learned classes. However, since training a recognition model with every object class in the world is unfeasible, a way of getting information on unknown objects (i.e., objects whose class has not been learned) is necessary. A way for an image recognition system to learn new classes could be asking a human about objects that are unknown. In this paper, we propose a method for generating questions about unknown objects in an image, as means to get information about classes that have not been learned. Our method consists of a module for proposing objects, a module for identifying unknown objects, and a module for generating questions about unknown objects. The experimental results via human evaluation show that our method can successfully get information about unknown objects in an image dataset. Our code and dataset are available at https://github.com/mil-tokyo/vqg-unknown

The predominant approach to Visual Question Answering (VQA) demands that the model represents within its weights all of the information required to answer any question about any image. Learning this information from any real training set seems unlikely, and representing it in a reasonable number of weights doubly so. We propose instead to approach VQA as a meta learning task, thus separating the question answering method from the information required. At test time, the method is provided with a support set of example questions/answers, over which it reasons to resolve the given question. The support set is not fixed and can be extended without retraining, thereby expanding the capabilities of the model. To exploit this dynamically provided information, we adapt a state-of-the-art VQA model with two techniques from the recent meta learning literature, namely prototypical networks and meta networks. Experiments demonstrate the capability of the system to learn to produce completely novel answers (i.e. never seen during training) from examples provided at test time. In comparison to the existing state of the art, the proposed method produces qualitatively distinct results with higher recall of rare answers, and a better sample efficiency that allows training with little initial data. More importantly, it represents an important step towards vision-and-language methods that can learn and reason on-the-fly.

Scientific fields that are interested in faces have developed their own sets of concepts and procedures for understanding how a target model system (be it a person or algorithm) perceives a face under varying conditions. In computer vision, this has largely been in the form of dataset evaluation for recognition tasks where summary statistics are used to measure progress. While aggregate performance has continued to improve, understanding individual causes of failure has been difficult, as it is not always clear why a particular face fails to be recognized, or why an impostor is recognized by an algorithm. Importantly, other fields studying vision have addressed this via the use of visual psychophysics: the controlled manipulation of stimuli and careful study of the responses they evoke in a model system. In this paper, we suggest that visual psychophysics is a viable methodology for making face recognition algorithms more explainable. A comprehensive set of procedures is developed for assessing face recognition algorithm behavior, which is then deployed over state-of-the-art convolutional neural networks and more basic, yet still widely used, shallow and handcrafted feature-based approaches.

Visual dialog entails answering a series of questions grounded in an image, using dialog history as context. In addition to the challenges found in visual question answering (VQA), which can be seen as one-round dialog, visual dialog encompasses several more. We focus on one such problem called ‘visual coreference resolution’ that involves determining which words, typically noun phrases and pronouns, ‘co-refer’ to the same entity/object instance in an image. This is crucial, especially for pronouns (e.g., ‘it'), as the dialog agent must first link it to a previous coreference (e.g., ‘boat'), and only then can rely on the visual grounding of the coreference ‘boat' to reason about the pronoun `it'. Prior work (in visual dialog) models visual coreference resolution either (a) implicitly via a memory network over history, or (b) at a coarse level for the entire question; and not explicitly at a phrase level of granularity. In this work, we propose a neural module network architecture for visual dialog by introducing two novel modules---Refer and Exclude---that perform explicit, grounded, coreference resolution at a finer word level. We demonstrate the effectiveness of our model on MNIST Dialog, a visually simple yet coreference-wise complex dataset, by achieving near perfect accuracy, and on VisDial, a large and challenging visual dialog dataset on real images, where our model outperforms other approaches, and is more interpretable, grounded, and consistent qualitatively.

This paper addresses the problem of viewpoint estimation of an object in a given image. It presents five key insights and a CNN that is based on them. The network's major properties are as follows. (i) The architecture jointly solves detection, classification, and viewpoint estimation. (ii) New types of data are added and trained on. (iii) A novel loss function, which takes into account both the geometry of the problem and the new types of data, is propose. Our network allows a substantial boost in performance: from 36.1% gained by SOTA algorithms to 45.9%.

View-graph is an essential input to large-scale structure from motion (SfM) pipelines. Accuracy and efficiency of large-scale SfM is crucially dependent on the input view-graph. Inconsistent or inaccurate edges can lead to inferior or wrong reconstruction. Most SfM methods remove `undesirable' images and pairs using several fixed heuristic criteria, and propose tailor-made solutions to achieve specific reconstruction objectives such as efficiency, accuracy, or disambiguation. In contrast to these disparate solutions, we propose an optimization based formulation that can be used to achieve these different reconstruction objectives with task-specific cost modeling that uses and construct a very efficient network flow based formulation for its approximate solution. The abstraction brought on by this selection mechanism separates the challenges specific to datasets and reconstruction objectives from the standard SfM pipeline and improves its generalization. This paper mainly focuses on application of this framework with standard SfM pipeline for accurate and ghost-free reconstructions of highly ambiguous datasets. To model selection costs for this task, we introduce new disambiguation priors based on local geometry. We further demonstrate versatility of the method by using it for the general objective of accurate and efficient reconstruction of large-scale Internet datasets using costs based on well-known SfM priors.

How do humans recognize the action "opening a book"? We argue that there are two important cues: modeling temporal shape dynamics and modeling functional relationships between humans and objects. In this paper, we propose to represent videos as space-time region graphs which capture these two important cues. Our graph nodes are defined by the object region proposals from different frames in a long range video. These nodes are connected by two types of relations: (i) similarity relations capturing the long range dependencies between correlated objects and (ii) spatial-temporal relations capturing the interactions between nearby objects. We perform reasoning on this graph representation via Graph Convolutional Networks. We achieve state-of-the-art results on the Charades and Something-Something datasets. Especially for Charades with complex environments, we obtain a huge 4.4% gain when our model is applied in complex environments.

Video object segmentation is challenging yet important in a wide variety of applications for video analysis. Recent works formulate video object segmentation as a prediction task using deep nets to achieve appealing state-of-the-art performance. Due to the formulation as a prediction task, most of these methods require fine-tuning during test time, such that the deep nets memorize the appearance of the objects of interest in the given video. However, fine-tuning is time-consuming and computationally expensive, hence the algorithms are far from real time. To address this issue, we develop a novel matching based algorithm for video object segmentation. In contrast to memorization based classification techniques, the proposed approach learns to match extracted features to a provided template without memorizing the appearance of the objects. We validate the effectiveness and the robustness of the proposed method on the challenging DAVIS-2016, DAVIS-2017, Youtube-Objects and JumpCut datasets. Extensive results show that our method achieves comparable performance without fine-tuning and is much more favorable in terms of computational time.

This paper addresses the problem of video summarization. Given an input video, the goal is to select a subset of the frames to create a summary video that optimally captures the important information of the input video. With the large amount of videos available online, video summarization provides a useful tool that assists video search, retrieval, browsing, etc. In this paper, we formulate video summarization as a sequence labeling problem. Unlike existing approaches that use recurrent models, we propose fully convolutional sequence models to solve video summarization. We firstly establish a novel connection between semantic segmentation and video summarization, and then adapt popular semantic segmentation networks for video summarization. Extensive experiments and analysis on two benchmark datasets demonstrate the effectiveness of our models.

Many methods have been developed to help people find the video content they want efficiently. However, there are still some unsolved problems in this area. For example, given a query video and a reference video, how to accurately localize a segment in the reference video such that the segment semantically corresponds to the query video? We define a distinctively new task, namely extbf{video re-localization}, to address this need. Video re-localization is an important enabling technology with many applications, such as fast seeking in videos, video copy detection, as well as video surveillance. Meanwhile, it is also a challenging research task because the visual appearance of a semantic concept in videos can have large variations. The first hurdle to clear for the video re-localization task is the lack of existing datasets. It is labor expensive to collect pairs of videos with semantic coherence or correspondence, and label the corresponding segments. We first exploit and reorganize the videos in ActivityNet to form a new dataset for video re-localization research, which consists of about 10,000 videos of diverse visual appearances associated with the localized boundary information. Subsequently, we propose an innovative cross gated bilinear matching model such that every time-step in the reference video is matched against the attentively weighted query video. Consequently, the prediction of the starting and ending time is formulated as a classification problem based on the matching results. Extensive experimental results show that the proposed method outperforms the baseline methods.

The problem of video object segmentation can become extremely challenging when multiple instances co-exist. While each instance may exhibit large scale and pose variations, the problem is compounded when instances occlude each other causing failures in tracking. In this study, we formulate a deep recurrent network that is capable of segmenting and tracking objects in video simultaneously by their temporal continuity, yet able to re-identify them when they re-appear after a prolonged occlusion. We combine both temporal propagation and re-identification functionalities into a single framework that can be trained end-to-end. In particular, we present a re-identification module with template expansion to retrieve missing objects despite their large appearance changes. In addition, we contribute a new attention-based recurrent mask propagation approach that is robust to distractors not belonging to the target segment. Our approach achieves a new state-of-the-art global mean (Region Jaccard and Boundary F measure) of 68.2 on the challenging DAVIS 2017 benchmark (test-dev set), outperforming the winning solution which achieves a global mean of 66.1 on the same partition.

We address the problem of video object segmentation which outputs the masks of a target object throughout a video given only a bounding box in the first frame. There are two main challenges for this task. First, the background may contain similar objects as the target. Second, the appearance of the target object may change drastically over time. To tackle these challenges, we propose an end-to-end training network which accomplishes foreground predictions by leveraging the location-sensitive embeddings which are capable to distinguish the pixels of similar objects. To deal with appearance changes, for a test video, we propose a robust model adaptation method which pre-scans the whole video, generates pseudo foreground/background labels and retrains the model based on the labels. Our method outperforms the state-of-the-art methods on the DAVIS and the SegTrack V2 datasets.

We introduce Spatial-Temporal Memory Networks for video object detection. At its core, a novel Spatial-Temporal Memory module (STMM) serves as the recurrent computation unit to model long-term temporal appearance and motion dynamics. The STMM's design enables full integration of pretrained backbone CNN weights, which we find to be critical for accurate detection. Furthermore, in order to tackle object motion in videos, we propose a novel MatchTrans module to align the spatial-temporal memory from frame to frame. Our method produces state-of-the-art results on the benchmark ImageNet VID dataset, and our ablative studies clearly demonstrate the contribution of our different design choices. We release our code and models at http://fanyix.cs.ucdavis.edu/project/stmn/project.html.

An ever increasing amount of our digital communication, media consumption, and content creation revolves around videos. We share, watch, and archive many aspects of our lives through them, all of which are powered by strong video compression. Traditional video compression is laboriously hand designed and hand optimized. This paper presents an alternative in an end-to-end deep learning codec. Our codec builds one simple idea: Video compression is repeated image interpolation. It thus benefits from recent advances in deep image interpolation and generation. Our deep video codec outperforms today's prevailing codecs, such as H.261, MPEG4 Part 2, and performs on par with H.264.