ECCV 2020 论文列表

In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). The task aims at spatio-temporally localizing the given relations in the form of subject-predicate-object in the videos, so as to provide supportive visual facts for other high-level video-language tasks (e.g., video-language grounding and video question answering). The challenges in this task include but not limited to: (1) both the subject and object are required to be spatio-temporally localized to ground a query relation; (2) the temporal dynamic nature of visual relations in videos is difficult to capture; and (3) the grounding should be achieved without any direct supervision in space and time. To ground the relations, we tackle the challenges by collaboratively optimizing two sequences of regions over a constructed hierarchical spatio-temporal region graph through relation attending and reconstruction, in which we further propose a message passing mechanism by spatial attention shifting between visual entities. Experimental results demonstrate that our model can not only outperform baseline approaches significantly, but also produces visually meaningful facts to support visual grounding. (Code is available at https://github.com/doc-doc/vRGV)."

We introduce the task of Image-Set Visual Question Answering (ISVQA), which generalizes the commonly studied single-image VQA problem to multi-image settings. Taking a natural language question and a set of images as input, it aims to answer the question based on the content of the images. The questions can be about objects and relationships in one or more images or about the entire scene depicted by the image set. To enable research in this new topic, we introduce two ISVQA datasets - indoor and outdoor scenes. They simulate the real-world scenarios of indoor image collections and multiple car-mounted cameras, respectively. The indoor-scene dataset contains 91,479 human-annotated questions for 48,138 image sets, and the outdoor-scene dataset has 49,617 questions for 12,746 image sets. We analyze the properties of the two datasets, including question-and-answer distributions, types of questions, biases in dataset, and question-image dependencies. We also build new baseline models to investigate new research challenges in ISVQA."

In this paper, we explore the problem of interesting scene prediction for mobile robots. This area is currently underexplored but is crucial for many practical applications such as autonomous exploration and decision making. Inspired by industrial demands, we first propose a novel translation-invariant visual memory for recalling and identifying interesting scenes, then design a three-stage architecture of long-term, short-term, and online learning. This enables our system to learn human-like experience, environmental knowledge, and online adaption, respectively. Our approach achieves much higher accuracy than the state-of-the-art algorithms on challenging robotic interestingness datasets."

Human-Object interaction (HOI) detection aims to localize and infer relationships between human and objects in an image. It is challenging because an enormous number of possible combinations of objects and verbs types forms a long-tail distribution. We devise a deep Visual Compositional Learning (VCL) framework, which is a simple yet efficient framework to effectively address this problem. VCL first decomposes an HOI representation into object and verb specific features, and then composes new interaction samples in the feature space via stitching the decomposed features. The integration of decomposition and composition enables VCL to share object and verb features among different HOI samples and images, and to generate new interaction samples and new types of HOI, and thus largely alleviates the long-tail distribution problem and benefits low-shot or zero-shot HOI detection. Extensive experiments demonstrate that the proposed VCL can effectively improve the generalization of HOI detection on HICO-DET and V-COCO and outperforms the recent state-of-the-art methods on HICO-DET."

Semantic segmentation of 3D meshes is an important problem for 3D scene understanding. In this paper we revisit the classic multiview representation of 3D meshes and study several techniques that make them effective for 3D semantic segmentation of meshes. Given a 3D mesh reconstructed from RGBD sensors, our method effectively chooses different virtual views of the 3D mesh and renders multiple 2D channels for training an effective 2D semantic segmentation model. Features from multiple per view predictions are finally fused on 3D mesh vertices to predict mesh semantic segmentation labels. Using the large scale indoor 3D semantic segmentation benchmark of ScanNet, we show that our virtual views enables more effective data augmentation not possible with 2D only methods. Overall, our virtual multiview fusion method is able to achieve significantly better 3D semantic segmentation results compared to prior multiview approaches and competitive with state-of-the-art 3D sparse convolution approaches."

Depictions of similar human body configurations can vary with changing viewpoints. Using only 2D information, we would like to enable vision algorithms to recognize similarity in human body poses across multiple views. This ability is useful for analyzing body movements and human behaviors in images and videos. In this paper, we propose an approach for learning a compact view-invariant embedding space from 2D joint keypoints alone, without explicitly predicting 3D poses. Since 2D poses are projected from 3D space, they have an inherent ambiguity, which is difficult to represent through a deterministic mapping. Hence, we use probabilistic embeddings to model this input uncertainty. Experimental results show that our embedding model achieves higher accuracy when retrieving similar poses across different camera views, in comparison with 2D-to-3D pose lifting models. We also demonstrate the effectiveness of applying our embeddings to view-invariant action recognition and video alignment. Our code will be released for research."

Remote physiological measurements, e.g., remote photoplethysmography (rPPG) based heart rate (HR), heart rate variability (HRV) and respiration frequency (RF) measuring, are playing more and more important roles under the application scenarios where contact measurement is inconvenient or impossible. Since the amplitude of the physiological signals is usually very small, they can be easily affected by head movements, lighting conditions, and sensor diversities. To address these challenges, we propose a cross-verified feature disentangling strategy to disentangle the physiological features with non-physiological representations such as head movements and lighting conditions, and then use the distilled physiological features for robust multi-task physiological measurements. We first transform the input face videos into a multi-scale spatial-temporal map (MSTmap), which can suppress the irrelevant background and noise features while retaining most of the temporal characteristics of the periodic physiological signals. Then we take pairwise MSTmaps as inputs to an autoencoder architecture with two encoders (one for physiological signals and the other for non-physiological information) and use a cross-verified scheme to obtain physiological features disentangled with the non-physiological features. The disentangled features are finally used for the joint prediction of multiple physiological signals like average HR values and rPPG signals. Comprehensive experiments on different large-scale public datasets of multiple physiological measurement tasks as well as the cross-database testing demonstrate the robustness of our approach."

Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window. They are less efficient compared to the recurrent-based methods. In this work, we propose a novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame. It divides the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks. In addition, a hidden state adaptation module that allows the current frame to selectively use information from hidden state is introduced to enhance its robustness to appearance change and error accumulation. Extensive ablation study validate the effectiveness of the proposed modules. Experiments on several benchmark datasets demonstrate superior performance of the proposed method compared to state-of-the-art methods on video super-resolution."

How to make a segmentation model efficiently adapt to a specific video as well as online target appearance variations is a fun- damental issue in the field of video object segmentation. In this work, a graph memory network is developed to address the novel idea of “learning to update the segmentation model”. Specifically, we exploit an episodic memory network, organized as a fully connected graph, to store frames as nodes and capture cross-frame correlations by edges. Further, learnable controllers are embedded to ease memory reading and writing, as well as maintain a fixed memory scale. The structured, external memory design enables our model to comprehensively mine and quickly store new knowl- edge, even with limited visual information, and the differentiable memory controllers slowly learn an abstract method for storing useful represen- tations in the memory and how to later use these representations for prediction, via gradient descent. In addition, the proposed graph mem- ory network yields a neat yet principled framework, which can generalize well to both one-shot and zero-shot video object segmentation tasks. Ex- tensive experiments on four challenging benchmark datasets verify that our graph memory network is able to facilitate the adaptation of the segmentation network for case-by-case video object segmentation."

While single-image object detectors can be naively applied to videos in a frame-by-frame fashion, the prediction is often temporally inconsistent. Moreover, the computation can be redundant since neighboring frames are inherently similar to each other. In this work we propose to improve video object detection via temporal aggregation. Specifically, a detection model is applied on sparse keyframes to handle new objects, occlusions, and rapid motions. We then use real-time trackers to exploit temporal cues and track the detected objects in the remaining frames, which enhances efficiency and temporal coherence. Object status at the bounding-box level is propagated across frames and updated by our aggregation modules. For keyframe scheduling, we propose adaptive policies using reinforcement learning and simple heuristics. The proposed framework achieves the state-of-the-art performance on the Imagenet VID 2015 dataset while running real-time on CPU. Extensive experiments are done to show the effectiveness of our training strategies and justify the model designs."

Person search by natural language aims at retrieving a specific person in a large-scale image pool that matches given textual descriptions. While most of the current methods treat the task as a holistic visual and textual feature matching one, we approach it from an attribute-aligning perspective that allows grounding specific attribute phrases to the corresponding visual regions. We achieve success as well as a performance boost by a robust feature learning that the referred identity can be accurately bundled by multiple attribute cues. To be concrete, our Visual-Textual Attribute Alignment model (dubbed as ViTAA) learns to disentangle the feature space of a person into sub-spaces corresponding to attributes using a light auxiliary attribute segmentation layer. It then aligns these visual features with the textual attributes parsed from the sentences via a novel contrastive learning loss. We validate our ViTAA framework through extensive experiments on tasks of person search by natural language and by attribute-phrase queries, on which our system achieves state-of-the-art performances."

This paper tackles a 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image. We provide a new benchmark with ground-truth annotations for 2,001 complex buildings across the cities of Atlanta, Paris, and Las Vegas. We also propose a novel algorithm utilizing 1) convolutional neural networks (CNNs) that detects geometric primitives and infers their relationships and 2) an integer programming (IP) that assembles the information into a 2D planar graph. While being a trivial task for human vision, the inference of a graph structure with an arbitrary topology is still an open problem for computer vision. Qualitative and quantitative evaluations demonstrate that our algorithm makes significant improvements over the current state-of-the-art, towards an intelligent system at the level of human perception. We will share code and data."

Variational autoencoders (VAEs) and generative adversarial networks (GANs) enjoy an intuitive connection to manifold learning: in training the decoder/generator is optimized to approximate a homeomorphism between the data distribution and the sampling space. This is a construction that strives to define the data manifold. A major obstacle to VAEs and GANs, however, is choosing a suitable prior that matches the data topology. Well-known consequences of poorly picked priors are posterior and mode collapse. To our knowledge, no existing method sidesteps this user choice. Conversely, extit{diffusion maps} automatically infer the data topology and enjoy a rigorous connection to manifold learning, but do not scale easily or provide the inverse homeomorphism (i.e. decoder/generator). We propose a method that combines these approaches into a generative model that inherits the asymptotic guarantees of extit{diffusion maps} while preserving the scalability of deep models. We prove approximation theoretic results for the dimension dependence of our proposed method. Finally, we demonstrate the effectiveness of our method with various real and synthetic datasets."

Connectionist Temporal Classification (CTC) is a training criterion designed for sequence labelling problems where the alignment between the inputs and the target labels is unknown. One of the key steps is to add a blank symbol to the target vocabulary. However, CTC tends to output spiky distributions since it prefers to output blank symbol most of the time. These spiky distributions show inferior alignments and the non-blank symbols are not learned sufficiently. To remedy this, we propose variational CTC (Var-CTC) to enhance the learning of non-blank symbols. The proposed Var-CTC converts the output distribution of vanilla CTC with hierarchy distribution. It first learns the approximated posterior distribution of blank to determine whether to output a specific non-blank symbol or not. Then it learns the alignment between non-blank symbols and input sequence. Experiments on scene text recognition and offline handwritten text recognition show Var-CTC achieves better alignments. Besides, with the enhanced learning of non-blank symbols, the confidence scores of model outputs are more discriminative. Compared with the vanilla CTC, the proposed Var-CTC can improve the recall performance by a large margin when the models maintain the same level of precision."

As is well known, single image super-resolution (SR) is an ill-posed problem where multiple high resolution (HR) images can be matched to one low resolution (LR) image due to the difference of their representation capabilities. Such many-to-one nature is particularly magnified when super-resolving with large upscaling factors from very low dimensional domains such as 8$ imes$8 resolution where detailed information of HR is hardly discovered. Most existing methods are optimized for deterministic generation of SR images under pre-defined objectives such as pixel-level reconstruction and thus limited to the one-to-one correspondence between LR and SR images against the nature. In this paper, we propose VarSR, Variational Super Resolution Network, that matches latent distributions of LR and HR images to recover the missing details. Specifically, we draw samples from the learned common latent distribution of LR and HR to generate diverse SR images as the many-to-one relationship. Experimental results validate that our method can produce more accurate and perceptually plausible SR images from very low resolutions compared to the deterministic techniques."

Logical connectives and their implications on the meaning of a natural language sentence are a fundamental aspect of understanding. In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question about an image, are able to answer the logical composition of multiple such questions. When put under this extit{Lens of Logic}, state-of-the-art VQA models have difficulty in correctly answering these logically composed questions. We construct an augmentation of the VQA dataset as a benchmark, with questions containing logical compositions and linguistic transformations (negation, disjunction, conjunction, and antonyms). We propose our {Lens of Logic (LOL)} model which uses question-attention and logic-attention to understand logical connectives in the question, and a novel Fréchet-Compatibility Loss, which ensures that the answers of the component questions and the composed question are consistent with the inferred logical operation. Our model shows substantial improvement in learning logical compositions while retaining performance on VQA. We suggest this work as a move towards robustness by embedding logical connectives in visual understanding."

In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii) similar visual patterns varying with time. Therefore, ADL may look very similar and often necessitate to look at their fine-grained details to distinguish them. Because the recent spatio-temporal 3D ConvNets are too rigid to capture the subtle visual patterns across an action, we propose a novel Video-Pose Network: VPN. The 2 key components of this VPN are a spatial embedding and an attention network. The spatial embedding projects the 3D poses and RGB cues in a common semantic space. This enables the action recognition framework to learn better spatio-temporal features exploiting both modalities. In order to discriminate similar actions, the attention network provides two functionalities - (i) an end-to-end learnable pose backbone exploiting the topology of human body, and (ii) a coupler to provide joint spatio-temporal attention weights across a video. Experiments show that VPN outperforms the state-of-the-art results for action classification on a large scale human activity dataset: NTU-RGB+D 120, its subset NTU-RGB+D 60, a real-world challenging human activity dataset: Toyota Smarthome and a small scale human-object interaction dataset Northwestern UCLA."

Video Moment Retrieval (VMR) is a task to localize the temporal moment in untrimmed video specified by natural language query. For VMR, several methods that require full supervision for training have been proposed. Unfortunately, acquiring a large number of training videos with labeled temporal boundaries for each query is a labor-intensive process. This paper explores a method for performing VMR in a weakly-supervised manner (wVMR): training is performed without temporal moment labels but only with the text query that describes a segment of the video. Existing methods on wVMR generate multi-scale proposals and apply query-guided attention mechanism to highlight the most relevant proposal. To leverage the weak supervision, contrastive learning is used which predicts higher scores for the correct video-query pairs than for the incorrect pairs. It has been observed that a large number of candidate proposals, coarse query representation, and one-way attention mechanism lead to blurry attention map which limits the localization performance. To address this issue, Video-Language Alignment Network (VLANet) is proposed that learns a sharper attention by pruning out spurious candidate proposals and applying a multi-directional attention mechanism with fine-grained query representation. The Surrogate Proposal Selection module selects a proposal based on the proximity to the query in the joint embedding space, and thus substantially reduces candidate proposals which leads to lower computation load and sharper attention. Next, the Cascaded Cross-modal Attention module considers dense feature interactions and multi-directional attention flows to learn the multi-modal alignment. VLANet is trained end-to-end using contrastive loss which enforces semantically similar videos and queries to cluster. The experiments show that the method achieves state-of-the-art performance on Charades-STA and DiDeMo datasets."

Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image. Previous works assume missing region patterns are known, limiting its application scope. In this paper, we relax the assumption by defining a new blind inpainting setting, making training a blind inpainting neural system robust against various unknown missing region patterns. Specifically, we propose a two-stage visual consistency network (VCN), meant to estimate where to fill (via masks) and generate what to fill. In this procedure, the unavoidable potential mask prediction errors lead to severe artifacts in the subsequent repairing. To address it, our VCN predicts semantically inconsistent regions first, making mask prediction more tractable. Then it repairs these estimated missing regions using a new spatial normalization, enabling VCN to be robust to the mask prediction errors. In this way, semantically convincing and visually compelling content is thus generated. Extensive experiments are conducted, showing our method is effective and robust in blind image inpainting. And our VCN allows for a wide spectrum of applications."