Typical methods for supervised sequence modeling are built upon the recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model explicitly information interactions between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since one-order interactions cannot be maintained for a long term due to information dilution and gradient vanishing. To tackle this limitation, we propose the Non-local Recurrent Neural Memory (NRNM) for supervised sequence modeling, which performs non-local operations to learn full-order interactions within a sliding temporal block and models global interactions between blocks in a gated recurrent manner. Consequently, our model is able to capture the long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We demonstrate the merits of our NRNM on two different tasks: action recognition and sentiment analysis.
University of Missouri（密苏里大学）；TCL Research America（TCL美国研究院）
In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking. Our recurrent convolutional network exploits the history of locations as well as the distinctive visual features learned by the deep neural networks. Inspired by recent bounding box regression methods for object detection, we study the regression capability of Long Short-Term Memory (LSTM) in the temporal domain, and propose to concatenate high-level visual features produced by convolutional networks with region information. In contrast to existing deep learning …
Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers
Massachusetts Institute of Technology, Cambridge, MA, USA（麻省理工学院）；IBM Research, Cambridge, MA, USA（IBM研究院）；University of Toronto, Toronto, Canada（多伦多大学）
Stanford University（斯坦福大学）；University of Washington（华盛顿大学）
The main challenge of online multi-object tracking is to reliably associate object trajectories with detections in each video frame based on their tracking history. In this work, we propose the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework to characterize the appearance and motion dynamics of multiple objects over time. The RAN couples an external memory and an internal memory. The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detect…
Hikvision Research Institute（海康威视研究院）；Shanghai Jiaotong University（上海交通大学）；Zhejiang University（浙江大学）
This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only supervision of video-level labels and makes prediction of intervals of multiple actions. Specifically, we first assemble video clips according to class labels by an attention mechanism that learns class-variable attention weights and thus helps the noise relieving from background or other actions. Secondly, we build temporal relationship between actions by feeding the assembled features into an enhanced recurrent neural ne…
This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global, and contextual information of salient objects is important to obtain a high quality salient map. To achieve this goal, the DSRCNN is designed based on VGGNet-16. Firstly, the recurrent connections are incorporated into each convolutional layer, which can make the model more powerful for learning the contextual information. Secondly, side-output layers are adde…
Unsupervised image captioning with no annotations is an emerging challenge in computer vision, where the existing arts usually adopt GAN (Generative Adversarial Networks) models. In this paper, we propose a novel memory-based network rather than GAN, named Recurrent Relational Memory Network ($R^2M$). Unlike complicated and sensitive adversarial learning that non-ideally performs for long sentence generation, $R^2M$ implements a concepts-to-sentence memory translator through two-stage memory mechanisms: fusion and recurrent memories, correlating the relational reasoning between common visual c…
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Deep learning-based, single-view depth estimation methods have recently shown highly promising results. However, such methods ignore one of the most important features for determining depth in the human vision system, which is motion. We propose a learning-based, multi-view dense depth map and odometry estimation method that uses Recurrent Neural Networks (RNN) and trains utilizing multi-view image reprojection and forward-backward flow-consistency losses. Our model can be trained in a supervised or even unsupervised mode. It is designed for depth and visual odometry estimation from video wher…
Successful Human-Robot collaboration requires a predictive model of human behavior. The robot needs to be able to recognize current goals and actions and to predict future activities in a given context. However, the spatio-temporal sequence of human actions is difficult to model since latent factors such as intention, task, knowledge, intuition and preference determine the action choices of each individual. In this work we introduce semi-supervised variational recurrent neural networks which are able to a) model temporal distributions over latent factors and the observable feature space, b) in…
We propose a novel recurrent network-based HDR deghosting method for fusing arbitrary length dynamic sequences. The proposed method uses convolutional and recurrent architectures to generate visually pleasing, ghosting-free HDR images. We introduce a new recurrent cell architecture, namely Self-Gated Memory (SGM) cell, that outperforms the standard LSTM cell while containing fewer parameters and having faster running times. In the SGM cell, the information flow through a gate is controlled by multiplying the gate's output by a function of itself. Additionally, we use two SGM cells in a bidirec…
Text recognition in natural scene is a challenging problem due to the many factors affecting text appearance. In this paper, we presents a method that directly transcribes scene text images to text without needing of sophisticated character segmentation. We leverage recent advances of deep neural networks to model the appearance of scene text images with temporal dynamics. Specifically, we integrates convolutional neural network (CNN) and recurrent neural network (RNN) which is motivated by observing the complementary modeling capabilities of the two models. The main contribution of this work …
Tencent（腾讯）；Southern University of Science and Technology（南方科技大学）
Typical techniques for video captioning follow the encoder-decoder framework, which can only focus on one source video being processed. A potential disadvantage of such design is that it cannot capture the multiple visual context information of a word appearing in more than one relevant videos in training data. To tackle this limitation, we propose the Memory-Attended Recurrent Network (MARN) for video captioning, in which a memory structure is designed to explore the full-spectrum correspondence between a word and its various similar visual contexts across videos in training data. Thus, our m…
Alibaba DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；University of Science and Technology of China（中国科学技术大学）
Space-time memory (STM) based video object segmentation (VOS) networks usually keep increasing memory bank every several frames, which shows excellent performance. However, 1) the hardware cannot withstand the ever-increasing memory requirements as the video length increases. 2) Storing lots of information inevitably introduces lots of noise, which is not conducive to reading the most important information from the memory bank. In this paper, we propose a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size. Specifically, we explicitly generate and update RDE by the propos…
Polytechnique Montréal（蒙特利尔高等理工学院）；The Montreal Institute for Learning Algorithms（蒙特利尔学习算法研究所）
We explore recurrent encoder multi-decoder neural network architectures for semi-supervised sequence classification and reconstruction. We find that the use of multiple reconstruction modules helps models generalize in a classification task when only a small amount of labeled data is available, which is often the case in practice. Such models provide useful high-level representations of motions allowing clustering, searching and faster labeling of new sequences. We also propose a new, realistic partitioning of a well-known, high quality motion-capture dataset for better evaluations. We further…
We propose the Recurrent Soft Attention Model, which integrates the visual attention from the original image to a LSTM memory cell through a down-sample network. The model recurrently transmits visual attention to the memory cells for glimpse mask generation, which is a more natural way for attention integration and exploitation in general object detection and recognition problem. We test our model under the metric of the top-1 accuracy on the CIFAR-10 dataset. The experiment shows that our down-sample network and feedback mechanism plays an effective role among the whole network structure.
Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）；AUDI AG（奥迪股份公司）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Fraunhofer IOSB（弗劳恩霍夫光学、系统技术与图像利用研究所）
Understanding and interpreting a 3d environment is a key challenge for autonomous vehicles. Semantic segmentation of 3d point clouds combines 3d information with semantics and thereby provides a valuable contribution to this task. In many real-world applications, point clouds are generated by lidar sensors in a consecutive fashion. Working with a time series instead of single and independent frames enables the exploitation of temporal information. We therefore propose a recurrent segmentation architecture (RNN), which takes a single range image frame as input and exploits recursively aggregate…
Indian Institute of Technology Kharagpur（印度理工学院卡哈拉格普尔分校）
In this paper, we introduce Key-Value Memory Networks to a multimodal setting and a novel key-addressing mechanism to deal with sequence-to-sequence models. The proposed model naturally decomposes the problem of video captioning into vision and language segments, dealing with them as key-value pairs. More specifically, we learn a semantic embedding (v) corresponding to each frame (k) in the video, thereby creating (k, v) memory slots. We propose to find the next step attention weights conditioned on the previous attention distributions for the key-value memory slots in the memory addressing sc…
Learning scene flow from a monocular camera still remains a challenging task due to its ill-posedness as well as lack of annotated data. Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their accuracy lags behind (semi-)supervised methods. In this paper, we introduce a self-supervised monocular scene flow method that substantially improves the accuracy over the previous approaches. Based on RAFT, a state-of-the-art optical flow model, we design a new decoder to iteratively update 3D motion fields and disparity maps simultaneously. Furthermore, we prop…
IRSTEA（法国国家环境与农业科技研究院）；UMR TETIS（TETIS联合研究单位）；LIRMM（蒙彼利埃计算机科学与机器人实验室）；Univ. of Montpellier（蒙彼利埃大学）；CIRAD（法国国际农业发展研究中心）
Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN based classification, we propose a new supervised layer-wise pretraining strategy to initialize network parameters. The proposed approach leverages a data-aware strategy that sets up a taxonomy of classification problems automatically derived by the model behavior. To the best of our knowledge, despite the great interest in RNN-based classification, this is…
Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the feature tensor of each frame in video. Hence, their space and time complexity increase linearly as the length of video grows, which could be very costly for long videos. We propose a novel visual memory network architecture for the learning and inference problem in the spatial-temporal domain. We maintain a fixed set of memory slots in our memory network and propose an algorithm based on Gumbel-Softmax to learn an adaptive…
UNC Chapel Hill（北卡罗来纳大学教堂山分校）；Tencent AI Lab（腾讯人工智能实验室）；Microsoft Dynamics 365 AI（微软Dynamics 365人工智能部门）
Generating multi-sentence descriptions for videos is one of the most challenging captioning tasks due to its high requirements for not only visual relevance but also discourse-based coherence across the sentences in the paragraph. Towards this goal, we propose a new approach called Memory-Augmented Recurrent Transformer (MART), which uses a memory module to augment the transformer architecture. The memory module generates a highly summarized memory state from the video segments and the sentence history so as to help better prediction of the next sentence (w.r.t. coreference and repetition aspe…
The significant computational costs of deploying neural networks in large-scale or resource constrained environments, such as data centers and mobile devices, has spurred interest in model compression, which can achieve a reduction in both arithmetic operations and storage memory. Several techniques have been proposed for reducing or compressing the parameters for feed-forward and convolutional neural networks, but less is understood about the effect of parameter compression on recurrent neural networks (RNN). In particular, the extent to which the recurrent parameters can be compressed and th…
Institute for Informatics, LMU Munich（慕尼黑大学信息学研究所）
Common to all different kinds of recurrent neural networks (RNNs) is the intention to model relations between data points through time. When there is no immediate relationship between subsequent data points (like when the data points are generated at random, e.g.), we show that RNNs are still able to remember a few data points back into the sequence by memorizing them by heart using standard backpropagation. However, we also show that for classical RNNs, LSTM and GRU networks the distance of data points between recurrent calls that can be reproduced this way is highly limited (compared to even…
Autonomous cars need continuously updated depth information. Thus far, depth is mostly estimated independently for a single frame at a time, even if the method starts from video input. Our method produces a time series of depth maps, which makes it an ideal candidate for online learning approaches. In particular, we put three different types of depth estimation (supervised depth prediction, self-supervised depth prediction, and self-supervised depth completion) into a common framework. We integrate the corresponding networks with a ConvLSTM such that the spatiotemporal structures of depth acro…
University of California, Merced（加州大学默塞德分校）；Adobe Research（奥多比研究院）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
An important problem for both graphics and vision is to synthesize novel views of a 3D object from a single image. This is particularly challenging due to the partial observability inherent in projecting a 3D object onto the image space, and the ill-posedness of inferring object shape and pose. However, we can train a neural network to address the problem if we restrict our attention to specific object categories (in our case faces and chairs) for which we can gather ample training data. In this paper, we propose a novel recurrent convolutional encoder-decoder network that is trained end-to-en…
In this paper, we investigate the effectiveness of deep learning techniques for lung nodule classification in computed tomography scans. Using less than 10,000 training examples, our deep networks perform two times better than a standard radiology software. Visualization of the networks' neurons reveals semantically meaningful features that are consistent with the clinical knowledge and radiologists' perception. Our paper also proposes a novel framework for rapidly adapting deep networks to the radiologists' feedback, or change in the data due to the shift in sensor's resolution or patient pop…
Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳））；Tecent（腾讯）；JD Explore Academy（京东探索研究院）；Kuaishou Technology（快手科技）
The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model one-order information interactions explicitly between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since the temporal features …
