•As far as we know, we are the first to propose a general framework to incorporate the quantization-based methods into the conventional similarity-preserving hashing, in order to improve the ...effectiveness of hashing methods. In theory, any quantization method can be adopted to reduce the quantization error of any similarity-preserving hashing methods to improve their performance.•This framework can be applied to both unsupervised and supervised hashing. We experimentally obtained the best performance compared to state-ofthe-art supervised and unsupervised hashing methods on six popular datasets.•We successfully show it to work on a huge dataset SIFT1B (1 billion data points) by utilizing the graph approximation and out-of-sample extension.
Nowadays, due to the exponential growth of user generated images and videos, there is an increasing interest in learning-based hashing methods. In computer vision, the hash functions are learned in such a way that the hash codes can preserve essential properties of the original space (or label information). Then the Hamming distance of the hash codes can approximate the data similarity. On the other hand, vector quantization methods quantize the data into different clusters based on the criteria of minimal quantization error, and then perform the search using look-up tables. While hashing methods using Hamming distance can achieve faster search speed, their accuracy is often outperformed by quantization methods with the same code length, due to the low quantization error and more flexible distance lookups. To improve the effectiveness of the hashing methods, in this work, we propose Quantization-based Hashing (QBH), a general framework which incorporates the advantages of quantization error reduction methods into conventional property preserving hashing methods. The learned hash codes simultaneously preserve the properties in the original space and reduce the quantization error, and thus can achieve better performance. Furthermore, the hash functions and a quantizer can be jointly learned and iteratively updated in a unified framework, which can be readily used to generate hash codes or quantize new data points. Importantly, QBH is a generic framework that can be integrated to different property preserving hashing methods and quantization strategies, and we apply QBH to both unsupervised and supervised hashing models as showcases in this paper. Experimental results on three large-scale unlabeled datasets (i.e., SIFT1M, GIST1M, and SIFT1B), three labeled datastes (i.e., ESPGAME, IAPRTC and MIRFLICKR) and one video dataset (UQ_VIDEO) demonstrate the superior performance of our QBH over existing unsupervised and supervised hashing methods.
Recognizing human activities from videos is a fundamental research problem in computer vision. Recently, there has been a growing interest in analyzing human behavior from data collected with ...wearable cameras. First-person cameras continuously record several hours of their wearers' life. To cope with this vast amount of unlabeled and heterogeneous data, novel algorithmic solutions are required. In this paper, we propose a multitask clustering framework for activity of daily living analysis from visual data gathered from wearable cameras. Our intuition is that, even if the data are not annotated, it is possible to exploit the fact that the tasks of recognizing everyday activities of multiple individuals are related, since typically people perform the same actions in similar environments, e.g., people working in an office often read and write documents). In our framework, rather than clustering data from different users separately, we propose to look for clustering partitions which are coherent among related tasks. In particular, two novel multitask clustering algorithms, derived from a common optimization problem, are introduced. Our experimental evaluation, conducted both on synthetic data and on publicly available first-person vision data sets, shows that the proposed approach outperforms several single-task and multitask learning methods.
With the increasing popularity of Unmanned Aerial Vehicles (UAVs) in computer vision-related applications, intelligent UAV video analysis has recently attracted the attention of an increasing number ...of researchers. To facilitate research in the UAV field, this paper presents a UAV dataset with 100 videos featuring approximately 2700 vehicles recorded under unconstrained conditions and 840k manually annotated bounding boxes. These UAV videos were recorded in complex real-world scenarios and pose significant new challenges, such as complex scenes, high density, small objects, and large camera motion, to the existing object detection and tracking methods. These challenges have encouraged us to define a benchmark for three fundamental computer vision tasks, namely, object detection, single object tracking (SOT) and multiple object tracking (MOT), on our UAV dataset. Specifically, our UAV benchmark facilitates evaluation and detailed analysis of state-of-the-art detection and tracking methods on the proposed UAV dataset. Furthermore, we propose a novel approach based on the so-called Context-aware Multi-task Siamese Network (CMSN) model that explores new cues in UAV videos by judging the consistency degree between objects and contexts and that can be used for SOT and MOT. The experimental results demonstrate that our model could make tracking results more robust in both SOT and MOT, showing that the current tracking and detection methods have limitations in dealing with the proposed UAV benchmark and that further research is indeed needed.
We present AMIGOS- A dataset for Multimodal research of affect, personality traits and mood on Individuals and GrOupS. Different to other databases, we elicited affect using both short and long ...videos in two social contexts, one with individual viewers and one with groups of viewers. The database allows the multimodal study of the affective responses, by means of neuro-physiological signals of individuals in relation to their personality and mood, and with respect to the social context and videos' duration. The data is collected in two experimental settings. In the first one, 40 participants watched 16 short emotional videos. In the second one, the participants watched 4 long videos, some of them alone and the rest in groups. The participants' signals, namely, Electroencephalogram (EEG), Electrocardiogram (ECG) and Galvanic Skin Response (GSR), were recorded using wearable sensors. Participants' frontal HD video and both RGB and depth full body videos were also recorded. Participants emotions have been annotated with both self-assessment of affective levels (valence, arousal, control, familiarity, liking and basic emotions) felt during the videos as well as external-assessment of levels of valence and arousal. We present a detailed correlation analysis of the different dimensions as well as baseline methods and results for single-trial classification of valence and arousal, personality traits, mood and social context. The database is made publicly available.
Gesture recognition is a hot topic in computer vision and pattern recognition, which plays a vitally important role in natural human-computer interface. Although great progress has been made ...recently, fast and robust hand gesture recognition remains an open problem, since the existing methods have not well balanced the performance and the efficiency simultaneously. To bridge it, this work combines image entropy and density clustering to exploit the key frames from hand gesture video for further feature extraction, which can improve the efficiency of recognition. Moreover, a feature fusion strategy is also proposed to further improve feature representation, which elevates the performance of recognition. To validate our approach in a “wild” environment, we also introduce two new datasets called HandGesture and Action3D datasets. Experiments consistently demonstrate that our strategy achieves competitive results on Northwestern University, Cambridge, HandGesture and Action3D hand gesture datasets. Our code and datasets will release at https://github.com/Ha0Tang/HandGestureRecognition.
This paper studies vehicle ReID in aerial videos taken by Unmanned Aerial Vehicles (UAVs). Compared with existing vehicle ReID tasks performed with fixed surveillance cameras, UAV vehicle ReID is ...still under-explored and could be more challenging, e.g., aerial videos have dynamic and complex backgrounds, different vehicles show similar appearance, and the same vehicle commonly show distinct viewpoints and scales. To facilitate the research on UAV vehicle ReID, this paper contributes a novel dataset called UAV-VeID. UAV-VeID contains 41,917 images of 4601 vehicles captured by UAVs, where each vehicle has multiple images taken from different viewpoints. UAV-VeID also includes a large-scale distractor set to encourage the research on efficient ReID schemes. Compared with existing vehicle ReID datasets, UAV-VeID exhibits substantial variances in viewpoints and scales of vehicles, thus requires more robust features. To alleviate the negative effects of those variances, this paper also proposes a viewpoint adversarial training strategy and a multi-scale consensus loss to promote the robustness and discriminative power of learned deep features. Extensive experiments on UAV-VeID show our approach outperforms recent vehicle ReID algorithms. Moreover, our method also achieves competitive performance compared with recent works on existing vehicle ReID datasets including VehicleID, VeRi-776 and VERI-Wild.
Anomaly detection is of great significance for intelligent surveillance videos. Current works typically struggle with object detection and localization problems due to crowded and complex scenes. ...Hence, we propose a Deep Spatiotemporal Translation Network (DSTN), novel unsupervised anomaly detection and localization method based on Generative Adversarial Network (GAN) and Edge Wrapping (EW). In training, we use only the frames of normal events in order to generate their corresponding dense optical flow as temporal features. During testing, since all the video sequences are input into the system, unknown events are considered as anomalous events due to the fact that the model knows only the normal patterns. To benefit from the information provided by both appearance and motion features, we introduce (i) a novel fusion of background removal and real optical flow frames with (ii) a concatenation of the original and background removal frames. We improve the performance of anomaly localization in the pixel-level evaluation by proposing (iii) the Edge Wrapping to reduce the noise and suppress non-related edges of abnormal objects. Our DSTN has been tested on publicly available anomaly datasets, including UCSD pedestrian, UMN, and CUHK Avenue. The results show that it outperforms other state-of-the-art algorithms with respect to the frame-level evaluation, the pixel-level evaluation, and the time complexity for abnormal object detection and localization tasks.