In recent years, anomaly events detection in crowd scenes attracts many researchers' attention, because of its importance to public safety. Existing methods usually exploit visual information to analyze whether any abnormal events have occurred due to only visual sensors are generally equipped in public places. However, when an abnormal event in crowds occurs, sound information may be discriminative to assist the crowd analysis system to determine whether there is an abnormality. Compare with vision information that is easily occluded, audio signals have a certain degree of penetration. Thus, this paper attempt to exploit multi-modal learning for modeling the audio and visual signals simultaneously. To be specific, we design a two-branch network to model different types of information. The first is a typical 3D CNN model to extract temporal appearance features from video clips. The second is an audio CNN for encoding Log Mel-Spectrogram of audio signals. Finally, by fusing the above features, a more accurate prediction will be produced. We conduct the experiments on SHADE dataset, a synthetic audio-visual dataset in surveillance scenes, and find introducing audio signals effectively improves the performance of anomaly events detection and outperforms other state-of-the-art methods. Furthermore, we will release the code and the pre-trained models as soon as possible.
The rapid development in visual crowd analysis shows a trend to count people by positioning or even detecting, rather than simply summing a density map. It also enlightens us back to the essence of the field, detection to count, which can give more abundant crowd information and has more practical applications. However, some recent work on crowd localization and detection has two limitations: 1) The typical detection methods can not handle the dense crowds and a large variation in scale; 2) The density map heuristic methods suffer from performance deficiency in position and box prediction, especially in high density or large-size crowds. In this paper, we devise a tailored baseline for dense crowds location, detection, and counting from a new perspective, named as LDC-Net for convenience, which has the following features: 1) A strong but minimalist paradigm to detect objects by only predicting a location map and a size map, which endows an ability to detect in a scene with any capacity ($0 \sim 10,000+$ persons); 2) Excellent cross-scale ability in facing a large variation, such as the head ranging in $0 \sim 100,000+$ pixels; 3) Achieve superior performance in location and box prediction tasks, as well as a competitive counting performance compared with the density-based methods. Finally, the source code and pre-trained models will be released.
Although video summarization has achieved tremendous success benefiting from Recurrent Neural Networks (RNN), RNN-based methods neglect the global dependencies and multi-hop relationships among video frames, which limits the performance. Transformer is an effective model to deal with this problem, and surpasses RNN-based methods in several sequence modeling tasks, such as machine translation, video captioning, \emph{etc}. Motivated by the great success of transformer and the natural structure of video (frame-shot-video), a hierarchical transformer is developed for video summarization, which can capture the dependencies among frame and shots, and summarize the video by exploiting the scene information formed by shots. Furthermore, we argue that both the audio and visual information are essential for the video summarization task. To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer. In this paper, the proposed method is denoted as Hierarchical Multimodal Transformer (HMT). Practically, extensive experiments show that HMT surpasses most of the traditional, RNN-based and attention-based video summarization methods.
Person re-identification (re-ID) has gained more and more attention due to its widespread applications in intelligent video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models, and annotating data is an expensive work in real-world scenarios. In addition, due to domain gaps between different datasets, the performance is dramatically decreased when re-ID models pre-trained on label-rich datasets (source domain) are directly applied to other unlabeled datasets (target domain). In this paper, we attempt to remedy these problems from two aspects, namely data and methodology. Firstly, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them, which free humans from heavy data collections and annotations. Based on them, we build two synthetic person re-ID datasets with different scales, "GSPR" and "mini-GSPR" datasets. Secondly, we propose a synthesis-based multi-domain collaborative refinement (SMCR) network, which contains a synthetic pretraining module and two collaborative-refinement modules to implement sufficient learning for the valuable knowledge from multiple domains. Extensive experiments show that our proposed framework obtains significant performance improvements over the state-of-the-art methods on multiple unsupervised domain adaptation tasks of person re-ID.
Crowd localization is a new computer vision task, evolved from crowd counting. Different from the latter, it provides more precise location information for each instance, not just counting numbers for the whole crowd scene, which brings greater challenges, especially in extremely congested crowd scenes. In this paper, we focus on how to achieve precise instance localization in high-density crowd scenes, and to alleviate the problem that the feature extraction ability of the traditional model is reduced due to the target occlusion, the image blur, etc. To this end, we propose a Dilated Convolutional Swin Transformer (DCST) for congested crowd scenes. Specifically, a window-based vision transformer is introduced into the crowd localization task, which effectively improves the capacity of representation learning. Then, the well-designed dilated convolutional module is inserted into some different stages of the transformer to enhance the large-range contextual information. Extensive experiments evidence the effectiveness of the proposed methods and achieve state-of-the-art performance on five popular datasets. Especially, the proposed model achieves F1-measure of 77.5\% and MAE of 84.2 in terms of localization and counting performance, respectively.
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.
Homotopy model is an excellent tool exploited by diverse research works in the field of machine learning. However, its flexibility is limited due to lack of adaptiveness, i.e., manual fixing or tuning the appropriate homotopy coefficients. To address the problem above, we propose a novel adaptive homotopy framework (AH) in which the Maclaurin duality is employed, such that the homotopy parameters can be adaptively obtained. Accordingly, the proposed AH can be widely utilized to enhance the homotopy-based algorithm. In particular, in this paper, we apply AH to contrastive learning (AHCL) such that it can be effectively transferred from weak-supervised learning (given label priori) to unsupervised learning, where soft labels of contrastive learning are directly and adaptively learned. Accordingly, AHCL has the adaptive ability to extract deep features without any sort of prior information. Consequently, the affinity matrix formulated by the related adaptive labels can be constructed as the deep Laplacian graph that incorporates the topology of deep representations for the inputs. Eventually, extensive experiments on benchmark datasets validate the superiority of our method.
Deep neural network (DNN) generally takes thousands of iterations to optimize via gradient descent and thus has a slow convergence. In addition, softmax, as a decision layer, may ignore the distribution information of the data during classification. Aiming to tackle the referred problems, we propose a novel manifold neural network based on non-gradient optimization, i.e., the closed-form solutions. Considering that the activation function is generally invertible, we reconstruct the network via forward ridge regression and low rank backward approximation, which achieve the rapid convergence. Moreover, by unifying the flexible Stiefel manifold and adaptive support vector machine, we devise the novel decision layer which efficiently fits the manifold structure of the data and label information. Consequently, a jointly non-gradient optimization method is designed to generate the network with closed-form results. Eventually, extensive experiments validate the superior performance of the model.
Video frame interpolation can up-convert the frame rate and enhance the video quality. In recent years, although the interpolation performance has achieved great success, image blur usually occurs at the object boundaries owing to the large motion. It has been a long-standing problem, and has not been addressed yet. In this paper, we propose to reduce the image blur and get the clear shape of objects by preserving the edges in the interpolated frames. To this end, the proposed Edge-Aware Network (EA-Net) integrates the edge information into the frame interpolation task. It follows an end-to-end architecture and can be separated into two stages, \emph{i.e.}, edge-guided flow estimation and edge-protected frame synthesis. Specifically, in the flow estimation stage, three edge-aware mechanisms are developed to emphasize the frame edges in estimating flow maps, so that the edge-maps are taken as the auxiliary information to provide more guidance to boost the flow accuracy. In the frame synthesis stage, the flow refinement module is designed to refine the flow map, and the attention module is carried out to adaptively focus on the bidirectional flow maps when synthesizing the intermediate frames. Furthermore, the frame and edge discriminators are adopted to conduct the adversarial training strategy, so as to enhance the reality and clarity of synthesized frames. Experiments on three benchmarks, including Vimeo90k, UCF101 for single-frame interpolation and Adobe240-fps for multi-frame interpolation, have demonstrated the superiority of the proposed EA-Net for the video frame interpolation task.
Audio and vision are two main modalities in video data. Multimodal learning, especially for audiovisual learning, has drawn considerable attention recently, which can boost the performance of various computer vision tasks. However, in video summarization, existing approaches just exploit the visual information while neglect the audio information. In this paper, we argue that the audio modality can assist vision modality to better understand the video content and structure, and further benefit the summarization process. Motivated by this, we propose to jointly exploit the audio and visual information for the video summarization task, and develop an AudioVisual Recurrent Network (AVRN) to achieve this. Specifically, the proposed AVRN can be separated into three parts: 1) the two-stream LSTM is utilized to encode the audio and visual feature sequentially by capturing their temporal dependency. 2) the audiovisual fusion LSTM is employed to fuse the two modalities by exploring the latent consistency between them. 3) the self-attention video encoder is adopted to capture the global dependency in the video. Finally, the fused audiovisual information, and the integrated temporal and global dependencies are jointly used to predict the video summary. Practically, the experimental results on the two benchmarks, \emph{i.e.,} SumMe and TVsum, have demonstrated the effectiveness of each part, and the superiority of AVRN compared to those approaches just exploiting visual information for video summarization.