Visual features are of vital importance for human action understanding in videos. This paper presents a new video representation, called trajectory-pooled deep-convolutional descriptor (TDD), which shares the merits of both hand-crafted features and deep-learned features. Specifically, we utilize deep architectures to learn discriminative convolutional feature maps, and conduct trajectory-constrained pooling to aggregate these convolutional features into effective descriptors. To enhance the robustness of TDDs, we design two normalization methods to transform convolutional feature maps, namely spatiotemporal normalization and channel normalization. The advantages of our features come from (i) TDDs are automatically learned and contain high discriminative capacity compared with those hand-crafted features; (ii) TDDs take account of the intrinsic characteristics of temporal dimension and introduce the strategies of trajectory-constrained sampling and pooling for aggregating deep-learned features. We conduct experiments on two challenging datasets: HMDB51 and UCF101. Experimental results show that TDDs outperform previous hand-crafted features and deep-learned features. Our method also achieves superior performance to the state of the art on these datasets (HMDB51 65.9%, UCF101 91.5%).
Recently Trajectory-pooled Deep-learning Descriptors were shown to achieve state-of-the-art human action recognition results on a number of datasets. This paper improves their performance by applying rank pooling to each trajectory, encoding the temporal evolution of deep learning features computed along the trajectory. This leads to Evolution-Preserving Trajectory (EPT) descriptors, a novel type of video descriptor that significantly outperforms Trajectory-pooled Deep-learning Descriptors. EPT descriptors are defined based on dense trajectories, and they provide complimentary benefits to vide…
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…
Peking University（北京大学）；Beijing Institute of Technology（北京理工大学）
Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential Deep Trajectory Descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDT…
Improved dense trajectories (iDT) have shown great performance in action recognition, and their combination with the two-stream approach has achieved state-of-the-art performance. It is, however, difficult for iDT to completely remove background trajectories from video with camera shaking. Trajectories in less discriminative regions should be given modest weights in order to create more discriminative local descriptors for action recognition. In addition, the two-stream approach, which learns appearance and motion information separately, cannot focus on motion in important regions when extract…
Australian Center for Robotic Vision（澳大利亚机器人视觉中心）；The Australian National University（澳大利亚国立大学）；Data61/CSIRO（Data61/澳大利亚联邦科学与工业研究组织）
Most successful deep learning algorithms for action recognition extend models designed for image-based tasks such as object recognition to video. Such extensions are typically trained for actions on single video frames or very short clips, and then their predictions from sliding-windows over the video sequence are pooled for recognizing the action at the sequence level. Usually this pooling step uses the first-order statistics of frame-level action predictions. In this paper, we explore the advantages of using higher-order correlations; specifically, we introduce Higher-order Kernel (HOK) desc…
Tianjin University（天津大学）；Hefei University of Technology（合肥工业大学）
Deep ConvNets have shown its good performance in image classification tasks. However it still remains as a problem in deep video representation for action recognition. The problem comes from two aspects: on one hand, current video ConvNets are relatively shallow compared with image ConvNets, which limits its capability of capturing the complex video action information; on the other hand, temporal information of videos is not properly utilized to pool and encode the video sequences. Towards these issues, in this paper, we utilize two state-of-the-art ConvNets, i.e., the very deep spatial net (V…
This paper addresses the task of unsupervised learning of representations for action recognition in videos. Previous works proposed to utilize future prediction, or other domain-specific objectives to train a network, but achieved only limited success. In contrast, in the relevant field of image representation learning, simpler, discrimination-based methods have recently bridged the gap to fully-supervised performance. We first propose to adapt two top performing objectives in this class - instance recognition and local aggregation, to the video domain. In particular, the latter approach itera…
University of Adelaide（阿德莱德大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
The introduction of low-cost RGB-D sensors has promoted the research in skeleton-based human action recognition. Devising a representation suitable for characterising actions on the basis of noisy skeleton sequences remains a challenge, however. We here provide two insights into this challenge. First, we show that the discriminative information of a skeleton sequence usually resides in a short temporal interval and we propose a simple-but-effective local descriptor called trajectorylet to capture the static and kinematic information within this interval. Second, we further propose to encode ea…
Data61/CSIRO（Data61/联邦科学与工业研究组织）；Australian National University（澳大利亚国立大学）；University of Western Australia（西澳大学）
In this paper, we revive the use of old-fashioned handcrafted video representations for action recognition and put new life into these techniques via a CNN-based hallucination step. Despite of the use of RGB and optical flow frames, the I3D model (amongst others) thrives on combining its output with the Improved Dense Trajectory (IDT) and extracted with its low-level video descriptors encoded via Bag-of-Words (BoW) and Fisher Vectors (FV). Such a fusion of CNNs and handcrafted representations is time-consuming due to pre-processing, descriptor extraction, encoding and tuning parameters. Thus, …
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…
Infrared human action recognition has many advantages, i.e., it is insensitive to illumination change, appearance variability, and shadows. Existing methods for infrared action recognition are either based on spatial or local temporal information, however, the global temporal information, which can better describe the movements of body parts across the whole video, is not considered. In this letter, we propose a novel global temporal representation named optical-flow stacked difference image (OFSDI) and extract robust and discriminative feature from the infrared action data by considering the …
Motivated by the success of data-driven convolutional neural networks (CNNs) in object recognition on static images, researchers are working hard towards developing CNN equivalents for learning video features. However, learning video features globally has proven to be quite a challenge due to its high dimensionality, the lack of labelled data and the difficulty in processing large-scale video data. Therefore, we propose to leverage effective techniques from both data-driven and data-independent approaches to improve action recognition system. Our contribution is three-fold. First, we propose a…
Amazon Research Seattle（亚马逊西雅图研究院）；INRIA（法国国家信息与自动化研究所）
This paper introduces a state-of-the-art video representation and applies it to efficient action recognition and detection. We first propose to improve the popular dense trajectory features by explicit camera motion estimation. More specifically, we extract feature point matches between frames using SURF descriptors and dense optical flow. The matches are used to estimate a homography with RANSAC. To improve the robustness of homography estimation, a human detector is employed to remove outlier matches from the human body as human motion is not constrained by the camera. Trajectories consisten…
Beihang University（北京航空航天大学）；Polytechnic University of Milan（米兰理工大学）
Motion trajectory recognition is important for characterizing the moving property of an object. The speed and accuracy of trajectory recognition rely on a compact and discriminative feature representation, and the situations of varying rotation, scaling and translation has to be specially considered. In this paper we propose a novel feature extraction method for trajectories. Firstly a trajectory is represented by a proposed point context, which is a rotation-scale-translation (RST) invariant shape descriptor with a flexible tradeoff between computational complexity and discrimination, yet we …
We propose an efficient method to learn deep local descriptors for instance-level recognition. The training only requires examples of positive and negative image pairs and is performed as metric learning of sum-pooled global image descriptors. At inference, the local descriptors are provided by the activations of internal components of the network. We demonstrate why such an approach learns local descriptors that work well for image similarity estimation with classical efficient match kernel methods. The experimental validation studies the trade-off between performance and memory requirements …
Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of computer vision tasks such as image retrieval, fine-grained classification, and visual question answering. In this paper, we address the problem of fine-grained classification and image retrieval by leveraging textual information along with visual cues to comprehend the existing intrinsic relation between the two modalities. The novelty of the proposed model …
Data61/CSIRO（联邦科学与工业研究组织数据61部）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；The Australian National University（澳大利亚国立大学）；MERL（三菱电机研究实验室）
Popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the underlying action---indeed, many are common across multiple actions---pooling schemes that impose equal importance on all frames might be unfavorable. In an attempt to tackle this problem, we propose discriminative pooling, based on the notion that among the deep features generated on all short clips, there is at least one that characterizes the action. To this end, …
Most popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the underlying action---many are common across multiple actions---pooling schemes that impose equal importance on all frames might be unfavorable. In an attempt to tackle this problem, we propose discriminative pooling, based on the notion that among the deep features generated on all short clips, there is at least one that characterizes the action. To identify thes…
We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained deep networks as a black box to produce features, our method leverages a deep architecture trained for the specific task of image retrieval. Our contribution is twofold: (i) we leverage a ranking framework to learn convolution and projection weights that are used to build the region features; and (ii) we employ a region proposal network to learn which regions s…
Identifying human actions in complex scenes is widely considered as a challenging research problem due to the unpredictable behaviors and variation of appearances and postures. For extracting variations in motion and postures, trajectories provide meaningful way. However, simple trajectories are normally represented by vector of spatial coordinates. In order to identify human actions, we must exploit structural relationship between different trajectories. In this paper, we propose a method that divides the video into N number of segments and then for each segment we extract trajectories. We th…
State Key Lab of CAD&CG, Zhejiang University（浙江大学计算机辅助设计与图形学国家重点实验室）；Zhejiang Lab（之江实验室）
Few-shot learning (FSL) aims to classify images under low-data regimes, where the conventional pooled global feature is likely to lose useful local characteristics. Recent work has achieved promising performances by using deep descriptors. They generally take all deep descriptors from neural networks into consideration while ignoring that some of them are useless in classification due to their limited receptive field, e.g., task-irrelevant descriptors could be misleading and multiple aggregative descriptors from background clutter could even overwhelm the object's presence. In this paper, we a…
University of Edinburgh（爱丁堡大学）；Google Research（谷歌研究院）
We propose an unsupervised approach for discovering characteristic motion patterns in videos of highly articulated objects performing natural, unscripted behaviors, such as tigers in the wild. We discover consistent patterns in a bottom-up manner by analyzing the relative displacements of large numbers of ordered trajectory pairs through time, such that each trajectory is attached to a different moving part on the object. The pairs of trajectories descriptor relies entirely on motion and is more discriminative than state-of-the-art features that employ single trajectories. Our method generates…
National University of Singapore（新加坡国立大学）；NICTA；University of Queensland（昆士兰大学）；Queensland University of Technology（昆士兰科技大学）
In the field of face recognition, Sparse Representation (SR) has received considerable attention during the past few years. Most of the relevant literature focuses on holistic descriptors in closed-set identification applications. The underlying assumption in SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such assumption is easily violated in the more challenging face verification scenario, where an algorithm is required to determine if two faces (where one or both have not be…
This paper addresses the problem of very large-scale image retrieval, focusing on improving its accuracy and robustness. We target enhanced robustness of search to factors such as variations in illumination, object appearance and scale, partial occlusions, and cluttered backgrounds - particularly important when search is performed across very large datasets with significant variability. We propose a novel CNN-based global descriptor, called REMAP, which learns and aggregates a hierarchy of deep features from multiple CNN layers, and is trained end-to-end with a triplet loss. REMAP explicitly l…
City University of Hong Kong（香港城市大学）；Zhejiang University of Technology（浙江工业大学）
Motion behaviors of a rigid body can be characterized by a 6-dimensional motion trajectory, which contains position vectors of a reference point on the rigid body and rotations of this rigid body over time. This paper devises a Rotation and Relative Velocity (RRV) descriptor by exploring the local translational and rotational invariants of motion trajectories of rigid bodies, which is insensitive to noise, invariant to rigid transformation and scaling. A flexible metric is also introduced to measure the distance between two RRV descriptors. The RRV descriptor is then applied to characterize mo…
The process of automatic generation of a road map from GPS trajectories, called map inference, remains a challenging task to perform on a geospatial data from a variety of domains as the majority of existing studies focus on road maps in cities. Inherently, existing algorithms are not guaranteed to work on unusual geospatial sites, such as an airport tarmac, pedestrianized paths and shortcuts, or animal migration routes, etc. Moreover, deep learning has not been explored well enough for such tasks. This paper introduces COLTRANE, ConvolutiOnaL TRAjectory NEtwork, a novel deep map inference fra…
Convolutional Neural Network (CNN) features have been successfully employed in recent works as an image descriptor for various vision tasks. But the inability of the deep CNN features to exhibit invariance to geometric transformations and object compositions poses a great challenge for image search. In this work, we demonstrate the effectiveness of the objectness prior over the deep CNN features of image regions for obtaining an invariant image representation. The proposed approach represents the image as a vector of pooled CNN features describing the underlying objects. This representation pr…
University of Florence（佛罗伦萨大学）；IMT Lille Douai（里尔杜埃高等矿业电信学院）；Univ. Lille（里尔大学）；CNRS（法国国家科学研究中心）
In this paper, a model is presented to extract statistical summaries to characterize the repetition of a cyclic body action, for instance a gym exercise, for the purpose of checking the compliance of the observed action to a template one and highlighting the parts of the action that are not correctly executed (if any). The proposed system relies on a Riemannian metric to compute the distance between two poses in such a way that the geometry of the manifold where the pose descriptors lie is preserved; a model to detect the begin and end of each cycle; a model to temporally align the poses of di…
Facebook AI Research（Facebook AI研究院）；Carnegie Mellon University（卡内基梅隆大学）；University of São Paulo（圣保罗大学）
Aerial vehicles are revolutionizing the way film-makers can capture shots of actors by composing novel aerial and dynamic viewpoints. However, despite great advancements in autonomous flight technology, generating expressive camera behaviors is still a challenge and requires non-technical users to edit a large number of unintuitive control parameters. In this work, we develop a data-driven framework that enables editing of these complex camera positioning parameters in a semantic space (e.g. calm, enjoyable, establishing). First, we generate a database of video clips with a diverse range of sh…
One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descriptor should encode semantic, spatial and low level information. Even though off-the-shelf pre-trained neural networks can already produce good representations in combination with aggregation methods, appropriate fine tuning for the task of image retrieval has shown to significantly boost retrieval performance. In this paper, we present a simple yet effective supervised aggregation method built on top of existing reg…
A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential for robot autonomy. For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically designed in most cases, and can be vulnerable in complex environments. This paper shows that feature extraction with deep convolutional neural networks (CNNs) can be seamlessly incorporated into a modern SLAM framework. The proposed SLAM system utilizes a state-of-the-art CNN to detect keypoints in each image frame, and to give n…
International Institute of Information Technology, Hyderabad (IIIT-H)（海得拉巴国际信息技术学院（IIIT-H））
3D Human Motion Indexing and Retrieval is an interesting problem due to the rise of several data-driven applications aimed at analyzing and/or re-utilizing 3D human skeletal data, such as data-driven animation, analysis of sports bio-mechanics, human surveillance etc. Spatio-temporal articulations of humans, noisy/missing data, different speeds of the same motion etc. make it challenging and several of the existing state of the art methods use hand-craft features along with optimization based or histogram based comparison in order to perform retrieval. Further, they demonstrate it only for ver…
