In this paper, we propose a new video representation learning method, named Temporal Squeeze (TS) pooling, which can extract the essential movement information from a long sequence of video frames and map it into a set of few images, named Squeezed Images. By embedding the Temporal Squeeze pooling as a layer into off-the-shelf Convolution Neural Networks (CNN), we design a new video classification model, named Temporal Squeeze Network (TeSNet). The resulting Squeezed Images contain the essential movement information from the video frames, corresponding to the optimization of the video classification task. We evaluate our architecture on two video classification benchmarks, and the results achieved are compared to the state-of-the-art.
DSXFormer: Dual-Pooling Spectral Squeeze-Expansion and Dynamic Context Attention Transformer for Hyperspectral Image Classification
School of Computing, Gachon University（加荣大学计算机学院）；School of Computer Science, Chengdu University of Technology（成都理工大学计算机学院）；Department of Information Technology, College of Computer, Qassim University（卡西姆大学计算机学院信息科技系）；Kore University of Enna（恩纳大学）
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；University of Mannheim（曼海姆大学）
We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene. Particularly in indoor videos such as captured by robotic platforms or handheld and bodyworn RGBD cameras, nearby video frames provide diverse viewpoints and additional context of objects and scenes. To leverage such information, we first compute region correspondences by optical flow and image boundary-based superpixels. Given these region corre…
Nanjing University of Science and Technology（南京理工大学）
Contrastive learning has been successfully leveraged to learn action representations for addressing the problem of semi-supervised skeleton-based action recognition. However, most contrastive learning-based methods only contrast global features mixing spatiotemporal information, which confuses the spatial- and temporal-specific information reflecting different semantic at the frame level and joint level. Thus, we propose a novel Spatiotemporal Decouple-and-Squeeze Contrastive Learning (SDS-CL) framework to comprehensively learn more abundant representations of skeleton-based actions by jointly…
Action Unit (AU) detection plays an important role for facial expression recognition. To the best of our knowledge, there is little research about AU analysis for micro-expressions. In this paper, we focus on AU detection in micro-expressions. Microexpression AU detection is challenging due to the small quantity of micro-expression databases, low intensity, short duration of facial muscle change, and class imbalance. In order to alleviate the problems, we propose a novel Spatio-Temporal Adaptive Pooling (STAP) network for AU detection in micro-expressions. Firstly, STAP is aggregated by a seri…
Rongcheng College, Harbin University of Science and Technology（哈尔滨理工大学荣成学院）；Harbin University of Science and Technology（哈尔滨理工大学）；Hunan University of Technology and Business（湖南工商大学）
Background and objective: In this paper, a modified U-Net based framework is presented, which leverages techniques from Squeeze-and-Excitation (SE) block, Atrous Spatial Pyramid Pooling (ASPP) and residual learning for accurate and robust liver CT segmentation, and the effectiveness of the proposed method was tested on two public datasets LiTS17 and SLiver07. Methods: A new network architecture called SAR-U-Net was designed. Firstly, the SE block is introduced to adaptively extract image features after each convolution in the U-Net encoder, while suppressing irrelevant regions, and highlightin…
Dalian University of Technology（大连理工大学）；Tianjin University（天津大学）
For video recognition task, a global representation summarizing the whole contents of the video snippets plays an important role for the final performance. However, existing video architectures usually generate it by using a simple, global average pooling (GAP) method, which has limited ability to capture complex dynamics of videos. For image recognition task, there exist evidences showing that covariance pooling has stronger representation ability than GAP. Unfortunately, such plain covariance pooling used in image recognition is an orderless representative, which cannot model spatio-temporal…
In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion …
The key of Human-Object Interaction(HOI) recognition is to infer the relationship between human and objects. Recently, the image's Human-Object Interaction(HOI) detection has made significant progress. However, there is still room for improvement in video HOI detection performance. Existing one-stage methods use well-designed end-to-end networks to detect a video segment and directly predict an interaction. It makes the model learning and further optimization of the network more complex. This paper introduces the Spatial Parsing and Dynamic Temporal Pooling (SPDTP) network, which takes the ent…
Automatic pain intensity assessment has a high value in disease diagnosis applications. Inspired by the fact that many diseases and brain disorders can interrupt normal facial expression formation, we aim to develop a computational model for automatic pain intensity assessment from spontaneous and micro facial variations. For this purpose, we propose a 3D deep architecture for dynamic facial video representation. The proposed model is built by stacking several convolutional modules where each module encompasses a 3D convolution kernel with a fixed temporal depth, several parallel 3D convolutio…
We propose an effective two-stage approach to tackle the problem of language-based Human-centric Spatio-Temporal Video Grounding (HC-STVG) task. In the first stage, we propose an Augmented 2D Temporal Adjacent Network (Augmented 2D-TAN) to temporally ground the target moment corresponding to the given description. Primarily, we improve the original 2D-TAN from two aspects: First, a temporal context-aware Bi-LSTM Aggregation Module is developed to aggregate clip-level representations, replacing the original max-pooling. Second, we propose to employ Random Concatenation Augmentation (RCA) mechan…
We address the problem of generating video features for action recognition. The spatial pyramid and its variants have been very popular feature models due to their success in balancing spatial location encoding and spatial invariance. Although it seems straightforward to extend spatial pyramid to the temporal domain (spatio-temporal pyramid), the large spatio-temporal diversity of unconstrained videos and the resulting significantly higher dimensional representations make it less appealing. This paper introduces the space-time extended descriptor, a simple but efficient alternative way to incl…
MS-SSE-Net: A Multi-Scale Spatial Squeeze-and-Excitation Network for Structural Damage Detection in Civil and Geotechnical Engineering
German Research Center for Artificial Intelligence（德国人工智能研究中心）；Intelligentx GmbH；BiogentX；Department of Core Informatics, Graduate School of Informatics ,Osaka Metropolitan University（信息学系，大阪 metropolitan 大学）
Ulm University（乌尔姆大学）；Otto von Guericke University Magdeburg（马格德堡奥托·冯·格里克大学）
Gesture recognition is essential for the interaction of autonomous vehicles with humans. While the current approaches focus on combining several modalities like image features, keypoints and bone vectors, we present neural network architecture that delivers state-of-the-art results only with body skeleton input data. We propose the spatio-temporal multilayer perceptron for gesture recognition in the context of autonomous vehicles. Given 3D body poses over time, we define temporal and spatial mixing operations to extract features in both domains. Additionally, the importance of each time step i…
In this paper, we propose an alternating directional 3D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge -- structural spatio-spectral correlation and global correlation along spectrum. Specifically, 3D convolution is utilized to extract structural spatio-spectral correlation in an HSI, while a quasi-recurrent pooling function is employed to capture the global correlation along spectrum. Moreover, alternating directional structure is introduced to eliminate the causal dependency with no additional computation cost. The pro…
Hunan University（湖南大学）；Fudan University（复旦大学）；Bytedance AI Lab（字节跳动人工智能实验室）
The task of text-video retrieval aims to understand the correspondence between language and vision, has gained increasing attention in recent years. Previous studies either adopt off-the-shelf 2D/3D-CNN and then use average/max pooling to directly capture spatial features with aggregated temporal information as global video embeddings, or introduce graph-based models and expert knowledge to learn local spatial-temporal relations. However, the existing methods have two limitations: 1) The global video representations learn video temporal information in a simple average/max pooling manner and do…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；Computer Vision Center（计算机视觉中心）；University of Barcelona（巴塞罗那大学）
Most action recognition methods base on a) a late aggregation of frame level CNN features using average pooling, max pooling, or RNN, among others, or b) spatio-temporal aggregation via 3D convolutions. The first assume independence among frame features up to a certain level of abstraction and then perform higher-level aggregation, while the second extracts spatio-temporal features from grouped frames as early fusion. In this paper we explore the space in between these two, by letting adjacent feature branches interact as they develop into the higher level representation. The interaction happe…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Three dimensional convolutional neural networks (3D CNNs) have been established as a powerful tool to simultaneously learn features from both spatial and temporal dimensions, which is suitable to be applied to video-based action recognition. In this work, we propose not to directly use the activations of fully-connected layers of a 3D CNN as the video feature, but to use selective convolutional layer activations to form a discriminative descriptor for video. It pools the feature on the convolutional layers under the guidance of body joint positions. Two schemes of mapping body joints into conv…
Centro Singular de Investigación en Tecnoloxías Intelixentes (CiTIUS)（智能技术单一研究中心（CiTIUS））；Universidade de Santiago de Compostela（圣地亚哥-德孔波斯特拉大学）
This paper addresses the problem of how to exploit spatio-temporal information available in videos to improve the object detection precision. We propose a two stage object detector called FANet based on short-term spatio-temporal feature aggregation to give a first detection set, and long-term object linking to refine these detections. Firstly, we generate a set of short tubelet proposals containing the object in $N$ consecutive frames. Then, we aggregate RoI pooled deep features through the tubelet using a temporal pooling operator that summarizes the information with a fixed size output inde…
Current methods for spatiotemporal action tube detection often extend a bounding box proposal at a given keyframe into a 3D temporal cuboid and pool features from nearby frames. However, such pooling fails to accumulate meaningful spatiotemporal features if the position or shape of the actor shows large 2D motion and variability through the frames, due to large camera motion, large actor shape deformation, fast actor action and so on. In this work, we aim to study the performance of cuboid-aware feature aggregation in action detection under large action. Further, we propose to enhance actor fe…
Shanghai Jiao Tong University（上海交通大学）；McMaster University（麦克马斯特大学）；Michigan State University（密歇根州立大学）
To defend against manipulation of image content, such as splicing, copy-move, and removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to detect and localize image manipulations. PSCC-Net processes the image in a two-path procedure: a top-down path that extracts local and global features and a bottom-up path that detects whether the input image is manipulated, and estimates its manipulation masks at multiple scales, where each mask is conditioned on the previous one. Different from the conventional encoder-decoder and no-pooling structures, PSCC-Net leverages feature…
Self-supervised skeleton-based action recognition with contrastive learning has attracted much attention. Recent literature shows that data augmentation and large sets of contrastive pairs are crucial in learning such representations. In this paper, we found that directly extending contrastive pairs based on normal augmentations brings limited returns in terms of performance, because the contribution of contrastive pairs from the normal data augmentation to the loss get smaller as training progresses. Therefore, we delve into hard contrastive pairs for contrastive learning. Motivated by the su…
LMU München（慕尼黑大学）；Technische Universität München（慕尼黑工业大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Fully Convolutional Neural Networks (F-CNNs) achieve state-of-the-art performance for image segmentation in medical imaging. Recently, squeeze and excitation (SE) modules and variations thereof have been introduced to recalibrate feature maps channel- and spatial-wise, which can boost performance while only minimally increasing model complexity. So far, the development of SE has focused on 2D images. In this paper, we propose `Project & Excite' (PE) modules that base upon the ideas of SE and extend them to operating on 3D volumetric images. `Project & Excite' does not perform global average po…
Group Activity Recognition (GAR) aims to detect the activity performed by multiple actors in a scene. Prior works model the spatio-temporal features based on the RGB, optical flow or keypoint data types. However, using both the temporality and these data types altogether increase the computational complexity significantly. Our hypothesis is that by only using the RGB data without temporality, the performance can be maintained with a negligible loss in accuracy. To that end, we propose a novel GAR technique for volleyball videos, DECOMPL, which consists of two complementary branches. In the vis…
Amazon Web Service（亚马逊网络服务）；Rutgers University（罗格斯大学）
We introduce Video Transformer (VidTr) with separable-attention for video classification. Comparing with commonly used 3D networks, VidTr is able to aggregate spatio-temporal information via stacked attentions and provide better performance with higher efficiency. We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage. We then present VidTr which reduces the memory cost by 3.3$\times$ while keeping the same performance. To further optimize the model, we propose the standard devia…
In this paper, we present an end-to-end approach to simultaneously learn spatio-temporal features and corresponding similarity metric for video-based person re-identification. Given the video sequence of a person, features from each frame that are extracted from all levels of a deep convolutional network can preserve a higher spatial resolution from which we can model finer motion patterns. These low-level visual percepts are leveraged into a variant of recurrent model to characterize the temporal variation between time-steps. Features from all time-steps are then summarized using temporal poo…
Australian National University（澳大利亚国立大学）；University of Oxford（牛津大学）；Data61/CSIRO（Data61/联邦科学与工业研究组织）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；The University of Hong Kong（香港大学）
Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to capture short-range action patterns. Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class. Subsequently, the pooled representations are combined into simple relation descriptors which encode so-called query and suppor…
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Tencent（腾讯）；Peng Cheng Laboratory（鹏城实验室）
Traditional video quality assessment (VQA) methods evaluate localized picture quality and video score is predicted by temporally aggregating frame scores. However, video quality exhibits different characteristics from static image quality due to the existence of temporal masking effects. In this paper, we present a novel architecture, namely C3DVQA, that uses Convolutional Neural Network with 3D kernels (C3D) for full-reference VQA task. C3DVQA combines feature learning and score pooling into one spatiotemporal feature learning process. We use 2D convolutional layers to extract spatial feature…
Estimating the travel time for a given path is a fundamental problem in many urban transportation systems. However, prior works fail to well capture moving behaviors embedded in paths and thus do not estimate the travel time accurately. To fill in this gap, in this work, we propose a novel neural network framework, namely {\em Deep Image-based Spatio-Temporal network (DeepIST)}, for travel time estimation of a given path. The novelty of DeepIST lies in the following aspects: 1) we propose to plot a path as a sequence of "generalized images" which include sub-paths along with additional informa…
The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal features from video frames and then feeding them into a temporal classifier that captures high-level temporal patterns. We introduce a new class of temporal models, which we call Temporal Convolutional Networks (TCNs), that use a hierarchy of temporal convolutions to perform fine-grained action segmentation or detection. Our Encoder-Decoder TCN uses pooling and…
NUS Graduate School for Integrative Sciences and Engineering (NGS), National University of Singapore（新加坡国立大学综合科学与工程研究生院）；Dept. of Biomedical Engineering, National University of Singapore（新加坡国立大学生物医学工程系）；Dept. of Instrumentation and Control Engineering, NIT Trichy（印度国立理工学院蒂鲁奇拉帕利分校仪器与控制工程系）；Dept. of Otolaryngology, Singapore General Hospital（新加坡中央医院耳鼻喉科）
Representation learning of the task-oriented attention while tracking instrument holds vast potential in image-guided robotic surgery. Incorporating cognitive ability to automate the camera control enables the surgeon to concentrate more on dealing with surgical instruments. The objective is to reduce the operation time and facilitate the surgery for both surgeons and patients. We propose an end-to-end trainable Spatio-Temporal Multi-Task Learning (ST-MTL) model with a shared encoder and spatio-temporal decoders for the real-time surgical instrument segmentation and task-oriented saliency dete…
Spatial and temporal relationships, both short-range and long-range, between objects in videos, are key cues for recognizing actions. It is a challenging problem to model them jointly. In this paper, we first present a new variant of Long Short-Term Memory, namely Relational LSTM, to address the challenge of relation reasoning across space and time between objects. In our Relational LSTM module, we utilize a non-local operation similar in spirit to the recently proposed non-local network to substitute the fully connected operation in the vanilla LSTM. By doing this, our Relational LSTM is capa…
Weakly supervised video object localization (WSVOL) allows locating object in videos using only global video tags such as object class. State-of-art methods rely on multiple independent stages, where initial spatio-temporal proposals are generated using visual and motion cues, then prominent objects are identified and refined. Localization is done by solving an optimization problem over one or more videos, and video tags are typically used for video clustering. This requires a model per-video or per-class making for costly inference. Moreover, localized regions are not necessary discriminant b…
Social-IWSTCNN: A Social Interaction-Weighted Spatio-Temporal Convolutional Neural Network for Pedestrian Trajectory Prediction in Urban Traffic Scenarios
University of Gothenburg（哥德堡大学）；Chalmers University of Technology（查尔姆斯理工大学）
Technical University Munich（慕尼黑工业大学）；Austrian Institute of Technology（奥地利技术研究所）；University of Technology Vienna（维也纳技术大学）
This work presents a deep learning approach for vehicle detection in satellite video. Vehicle detection is perhaps impossible in single EO satellite images due to the tininess of vehicles (4-10 pixel) and their similarity to the background. Instead, we consider satellite video which overcomes the lack of spatial information by temporal consistency of vehicle movement. A new spatiotemporal model of a compact $3 \times 3$ convolutional, neural network is proposed which neglects pooling layers and uses leaky ReLUs. Then we use a reformulation of the output heatmap including Non-Maximum-Suppressio…
Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
In this paper, we present a new feature representation for first-person videos. In first-person video understanding (e.g., activity recognition), it is very important to capture both entire scene dynamics (i.e., egomotion) and salient local motion observed in videos. We describe a representation framework based on time series pooling, which is designed to abstract short-term/long-term changes in feature descriptor elements. The idea is to keep track of how descriptor values are changing over time and summarize them to represent motion in the activity video. The framework is general, handling a…
National University of Singapore（新加坡国立大学）；Facebook Research（脸书研究院）；Qihoo 360 AI Institute（奇虎360人工智能研究院）
Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention block", a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access features from the entire space efficiently. The component is designed with a double attention mechanism in two steps, where the first step gathers features from the …
École de technologie supérieure（高等技术学院）；Concordia University（康考迪亚大学）
Training deep learning models for accurate spatiotemporal recognition of facial expressions in videos requires significant computational resources. For practical reasons, 3D Convolutional Neural Networks (3D CNNs) are usually trained with relatively short clips randomly extracted from videos. However, such uniform sampling is generally sub-optimal because equal importance is assigned to each temporal clip. In this paper, we present a strategy for efficient video-based training of 3D CNNs. It relies on softmax temporal pooling and a weighted sampling mechanism to select the most relevant traini…
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；University of Electronic Science and Technology of China（电子科技大学）；Singapore Management University（新加坡管理大学）；Sichuan University（四川大学）
The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the simple shortcut connection mechanism limits the ability of re-exploring new potentially complementary features due to the additive function. To address this issue, in this paper, we propose to introduce a regulator module as a memory mechanism to extract complementary features, which are further fed to the ResNet. In particular, the regulator module is composed of convolutional RNNs (e.g., Convolutional LSTMs or Convolutional …
