Spatiotemporal action localization requires the incorporation of two sources of information into the designed architecture: (1) temporal information from the previous frames and (2) spatial information from the key frame. Current state-of-the-art approaches usually extract these information with separate networks and use an extra mechanism for fusion to get detections. In this work, we present YOWO, a unified CNN architecture for real-time spatiotemporal action localization in video streams. YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation. Since the whole architecture is unified, it can be optimized end-to-end. The YOWO architecture is fast providing 34 frames-per-second on 16-frames input clips and 62 frames-per-second on 8-frames input clips, which is currently the fastest state-of-the-art architecture on spatiotemporal action localization task. Remarkably, YOWO outperforms the previous state-of-the art results on J-HMDB-21 and UCF101-24 with an impressive improvement of ~3% and ~12%, respectively. We make our code and pretrained models publicly available.

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

Convolutional neural networks (CNNs) have been applied for hyperspectral image classification recently. Among this class of deep models, 3-D CNN has been shown to be more effective by learning discriminative features from abundant spectral signatures and spatial contexts in hyperspectral imagery (HSI). However, by simply imposing 3-D CNN to HSI, a large amount of initial information might be lost in this CNN pipeline. The proposed attention-aware pseudo-3-D (AP3D) convolutional network for HSI classification is motivated by two observations. First, each dimension of the 3-D HSI is not equally important, different attention should be paid to different dimensions of the initial HSI image, especially in the first convolution operation. Second, intermediate representations of the 3-D input image at different stages in the 3-D CNN pipeline represent different levels of features and should not be neglected and abandoned. Instead, a 2-D matrix of scores for each feature map should be fed to the final softmax layer. Quantitative and qualitative results demonstrate that the proposed AP3D model outperforms the state-of-the-art HSI classification methods in agricultural and rural/urban data sets: Indian Pines, Pavia University, and Salinas Scene.

Attention-Aware Pseudo-3-D Convolutional Neural Network for Hyperspectral Image Classification

With the development of video and image processing technology, the field of video tampering forensics is facing enormous challenges. Specifically, as the fundamental basis of judicial forensics, passive forensics for object removal video forgery is particularly essential. To extract tampering traces in video more sufficiently, the author proposed a spatiotemporal trident network based on the spatial rich model (SRM) and 3D convolution (C3D), which provides three branches and can theoretically improve the detection and localization accuracy of tampered regions. Based on the spatiotemporal trident network, a temporal detector and a spatial locator were designed to detect and locate the tampered regions in the temporal and spatial domains of videos. For the temporal detector, 3D CNNs were employed in three branches as the encoders and a bidirectional long short-term memory (BiLSTM) as the decoder. For the spatial locator, a backbone network named C3D-ResNet12 was designed as the encoder of the three branches, and the region proposal networks (RPNs) were employed as the decoders in three branches. In addition, we optimized the loss functions of the above two algorithms based on focal loss and GIoU loss. The experimental results revealed the effectiveness of spatiotemporal detection and localization algorithms: for temporal forgery detection, the accuracy of the frame classification increased to 99+%; for spatial forgery localization, the successful localization rate of the tampered regions in forged frames reached 96+%, and the mean intersection over union of the located tampered regions and the real tampered regions reached 62+%.

Spatiotemporal Trident Networks: Detection and Localization of Object Removal Tampering in Video Passive Forensics

ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation

Most state-of-the-art spatio-temporal (S-T) action localization methods explicitly use optical flow as auxiliary motion information. Although the combination of optical flow and RGB significantly improves the performance, optical flow estimation brings a large amount of computational cost and the whole network is not end-to-end trainable. These shortcomings hinder the interactive fusion between motion information and RGB information, and greatly limit its real-world applications. In this paper, we exploit better ways to use motion information in a unified end-to-end trainable network architecture. First, we use knowledge distillation to enable the 3D-Convolutional branch to learn motion information from RGB inputs. Second, we propose a novel motion cue called short-range-motion (SRM) module to enhance the 2D-Convolutional branch to learn RGB information and dynamic motion information. In this strategy, flow computation at test time is avoided. Finally, we apply our methods to learn powerful RGB-motion representations for action classification and localization. Experimental results show that our method significantly outperforms the state-of-the-arts on dataset benchmarks J-HMDB-21 and UCF101-24 with an impressive improvement of \(\sim \)8% and \(\sim \)3%.

/pdf/real-time-spatio-temporal-action-localization-via-learning-3e797yktit.pdf

Real-Time Spatio-Temporal Action Localization via Learning Motion Representation.

The spatial independence and temporal continuity of video data as a whole are not fully investigated for video action detection. To tackle this issue, a deep network architecture is proposed, named Pseudo-3D Convolutional Tube Network (P3D-CTN). In particular, the proposed P3D-CTN integrates the frame-based two-dimensional convolutional module with the P3D convolutional module to balance the spatial and temporal information, and generates deeper features about human actions. Evaluations on two benchmark datasets (i.e., UCF-Sports and J-HMDB) demonstrate that the proposed P3D-CTN has superior performances in the task of action label prediction and yields state-of-the-art results for spatio-temporal action detection.

P3D-CTN: Pseudo-3D Convolutional Tube Network for Spatio-Temporal Action Detection in Videos

Traffic flow prediction is the upstream problem of path planning, intelligent transportation system, and other tasks. Many studies have been carried out on the traffic flow prediction of the spatio-temporal network, but the effects of spatio-temporal flexibility (historical data of the same type of time intervals in the same location will change flexibly) and spatio-temporal correlation (different road conditions have different effects at different times) have not been considered at the same time. We propose the Deep Spatio-temporal Adaptive 3D Convolution Neural Network (ST-A3DNet), which is a new scheme to solve both spatio-temporal correlation and flexibility, and consider spatio-temporal complexity (complex external factors, such as weather and holidays). Different from other traffic forecasting models, ST-A3DNet captures the spatio-temporal relationship at the same time through the Adaptive 3D convolution module, assigns different weights flexibly according to the influence of historical data, and obtains the impact of external factors on the flow through the ex-mask module. Considering the holidays and weather conditions, we train our model for experiments in Xi’an and Chengdu. We evaluate the ST-A3DNet and the results show that we have better results than the other 11 baselines.

Deep Spatio-temporal Adaptive 3D Convolutional Neural Networks for Traffic Flow Prediction

Deep Convolutional Neural Network has shown significant improvements in many fields of computer vision, and a series of researches are proposed to explore advanced model structures to attenuate the problem of over-fitting. In this paper, two data driven techniques are designed including SwitchNode and SwitchConnect, which employ the sparsity of deterministic data to regularize convolutional neural network models. Specifically, the proposed SwitchNode method switches from the redundant nodes which have similar activations and spatial information to new initialization nodes, while the SwitchConnect method retrains replaceable convolutional kernels. The effectiveness of the proposed data driven regularization methods has been verified by the performance gain experimented on several benchmark image classification datasets.

Deshuang Huang

Papers

P3D-CTN: Pseudo-3D Convolutional Tube Network for Spatio-Temporal Action Detection in Videos

Deep Spatio-temporal Adaptive 3D Convolutional Neural Networks for Traffic Flow Prediction

Data Driven Regularization for Convolutional Neural Networks on Image Classification