We address temporal action localization in untrimmed long videos. This is important because videos in real applications are usually unconstrained and contain multiple action instances plus video content of background scenes or other activities. To address this challenging issue, we exploit the effectiveness of deep networks in temporal action localization via three segment-based 3D ConvNets: (1) a proposal network identifies candidate segments in a long video that may contain actions, (2) a classification network learns one-vs-all action classification model to serve as initialization for the localization network, and (3) a localization network fine-tunes the learned classification network to localize each action instance. We propose a novel loss function for the localization network to explicitly consider temporal overlap and achieve high temporal localization accuracy. In the end, only the proposal network and the localization network are used during prediction. On two largescale benchmarks, our approach achieves significantly superior performances compared with other state-of-the-art systems: mAP increases from 1.7% to 7.4% on MEXaction2 and increases from 15.0% to 19.0% on THUMOS 2014.

/pdf/temporal-action-localization-in-untrimmed-videos-via-multi-1ny61x4c3w.pdf

Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs

Multiple instance learning: A survey of problem characteristics and applications

Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos. Specifically, the spatial and the short-term motion features are extracted separately by two Convolutional Neural Networks (CNN). These two types of CNN-based features are then combined in a regularized feature fusion network for classification, which is able to learn and utilize feature relationships for improved performance. In addition, Long Short Term Memory (LSTM) networks are applied on top of the two features to further model longer-term temporal clues. The main contribution of this work is the hybrid learning framework that can model several important aspects of the video data. We also show that (1) combining the spatial and the short-term motion features in the regularized fusion network is better than direct classification and fusion using the CNN with a softmax layer, and (2) the sequence-based LSTM is highly complementary to the traditional classification strategy without considering the temporal frame orders. Extensive experiments are conducted on two popular and challenging benchmarks, the UCF-101 Human Actions and the Columbia Consumer Videos (CCV). On both benchmarks, our framework achieves very competitive performance: 91.3% on the UCF-101 and 83.5% on the CCV.

Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification

In this paper, we study the challenging problem of categorizing videos according to high-level semantics such as the existence of a particular human action or a complex event. Although extensive efforts have been devoted in recent years, most existing works combined multiple video features using simple fusion strategies and neglected the utilization of inter-class semantic relationships. This paper proposes a novel unified framework that jointly exploits the feature relationships and the class relationships for improved categorization performance. Specifically, these two types of relationships are estimated and utilized by imposing regularizations in the learning process of a deep neural network (DNN). Through arming the DNN with better capability of harnessing both the feature and the class relationships, the proposed regularized DNN (rDNN) is more suitable for modeling video semantics. We show that rDNN produces better performance over several state-of-the-art approaches. Competitive results are reported on the well-known Hollywood2 and Columbia Consumer Video benchmarks. In addition, to stimulate future research on large scale video categorization, we collect and release a new benchmark dataset, called FCVID, which contains 91,223 Internet videos and 239 manually annotated categories.

Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks

In this paper, we focus on complex event detection in internet videos while also providing the key evidences of the detection results. Convolutional Neural Networks (CNNs) have achieved promising performance in image classification and action recognition tasks. However, it remains an open problem how to use CNNs for video event detection and recounting, mainly due to the complexity and diversity of video events. In this work, we propose a flexible deep CNN infrastructure, namely Deep Event Network (DevNet), that simultaneously detects pre-defined events and provides key spatial-temporal evidences. Taking key frames of videos as input, we first detect the event of interest at the video level by aggregating the CNN features of the key frames. The pieces of evidences which recount the detection results, are also automatically localized, both temporally and spatially. The challenge is that we only have video level labels, while the key evidences usually take place at the frame levels. Based on the intrinsic property of CNNs, we first generate a spatial-temporal saliency map by back passing through DevNet, which then can be used to find the key frames which are most indicative to the event, as well as to localize the specific spatial position, usually an object, in the frame of the highly indicative area. Experiments on the large scale TRECVID 2014 MEDTest dataset demonstrate the promising performance of our method, both for event detection and evidence recounting.

/pdf/devnet-a-deep-event-network-for-multimedia-event-detection-f9mky17exa.pdf

DevNet: A Deep Event Network for multimedia event detection and evidence recounting

Video event detection allows intelligent indexing of video content based on events. Traditional approaches extract features from video frames or shots, then quantize and pool the features to form a single vector representation for the entire video. Though simple and efficient, the final pooling step may lead to loss of temporally local information, which is important in indicating which part in a long video signifies presence of the event. In this work, we propose a novel instance-based video event detection approach. We represent each video as multiple 'instances', defined as video segments of different temporal intervals. The objective is to learn an instance-level event detection model based on only video-level labels. To solve this problem, we propose a large-margin formulation which treats the instance labels as hidden latent variables, and simultaneously infers the instance labels as well as the instance-level classification model. Our framework infers optimal solutions that assume positive videos have a large number of positive instances while negative videos have the fewest ones. Extensive experiments on large-scale video event datasets demonstrate significant performance gains. The proposed method is also useful in explaining the detection results by localizing the temporal segments in a video which is responsible for the positive detection.

/pdf/video-event-detection-by-inferring-temporal-instance-labels-3as3ewjwfx.pdf

Video Event Detection by Inferring Temporal Instance Labels

Late fusion addresses the problem of combining the prediction scores of multiple classifiers, in which each score is predicted by a classifier trained with a specific feature. However, the existing methods generally use a fixed fusion weight for all the scores of a classifier, and thus fail to optimally determine the fusion weight for the individual samples. In this paper, we propose a sample-specific late fusion method to address this issue. Specifically, we cast the problem into an information propagation process which propagates the fusion weights learned on the labeled samples to individual unlabeled samples, while enforcing that positive samples have higher fusion scores than negative samples. In this process, we identify the optimal fusion weights for each sample and push positive samples to top positions in the fusion score rank list. We formulate our problem as a L∞ norm constrained optimization problem and apply the Alternating Direction Method of Multipliers for the optimization. Extensive experiment results on various visual categorization tasks show that the proposed method consistently and significantly beats the state-of-the-art late fusion methods. To the best knowledge, this is the first method supporting sample-specific fusion weight learning.

/pdf/sample-specific-late-fusion-for-visual-category-recognition-5d84ryu4a5.pdf

Sample-Specific Late Fusion for Visual Category Recognition

This paper presents a human action recognition method using histogram of oriented gradient (HOG) of motion history image (MHI). First, the proposed method generates MHI with differential images which are obtained by frame difference of successive frames of a video. The histogram of oriented gradient (HOG) of the MHI is then computed. Finally, support vector machine (SVM) is applied to train an action classifier using the HOG features. We discovered that the new method improves recognition rate significantly. Moreover, our algorithm does not require the generation process of human silhouette, and therefore the performance is also increased. Experimental results are provided to show the promising performance of the proposed method.

Human Action Recognition Using Histogram of Oriented Gradient of Motion History Image

Complex events consist of various human interactions with different objects in diverse environments. The evidences needed to recognize events may occur in short time periods with variable lengths and can happen anywhere in a video. This fact prevents conventional machine learning algorithms from effectively recognizing the events. In this paper, we propose a novel method that can automatically identify the key evidences in videos for detecting complex events. Both static instances (objects) and dynamic instances (actions) are considered by sampling frames and temporal segments respectively. To compare the characteristic power of heterogeneous instances, we embed static and dynamic instances into a multiple instance learning framework via instance similarity measures, and cast the problem as an Evidence Selective Ranking (ESR) process. We impose l1 norm to select key evidences while using the Infinite Push Loss Function to enforce positive videos to have higher detection scores than negative videos. The Alternating Direction Method of Multipliers (ADMM) algorithm is used to solve the optimization problem. Experiments on large-scale video datasets show that our method can improve the detection accuracy while providing the unique capability in discovering key evidences of each complex event.

/pdf/recognizing-complex-events-in-videos-by-learning-key-static-1tujwytfnx.pdf

Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences

Late fusion is one of the most effective approaches to enhance recognition accuracy through combining prediction scores of multiple classifiers, each of which is trained by a specific feature or model. The existing methods generally use a fixed fusion weight for one classifier over all samples, and ignore the fact that each classifier may perform better or worse for different subsets of samples. In order to address this issue, we propose a novel sample specific late fusion (SSLF) method. Specifically, we cast late fusion into an information propagation process that diffuses the fusion weights of labeled samples to the individual unlabeled samples, and enforce positive samples to have higher fusion scores than negative samples. Upon this process, the optimal fusion weight for each sample is identified, while positive samples are pushed toward the top at the fusion score rank list to achieve better accuracy. In this paper, two SSLF methods are presented. The first method is ranking SSLF (R-SSLF), which is based on graph Laplacian with RankSVM style constraints. We formulate and solve the problem with a fast gradient projection algorithm; the second method is infinite push SSLF (I-SSLF), which combines graph Laplacian with infinite push constraints. I-SSLF is a $l_{\infty }$ norm constrained optimization problem and can be solved by an efficient alternating direction method of multipliers method. Extensive experiments on both large-scale image and video data sets demonstrate the effectiveness of our methods. In addition, in order to make our method scalable to support large data sets, the AnchorGraph model is employed to propagate information on a subset of samples (anchor points) and then reconstruct the entire graph to get the weights of all samples. To the best of our knowledge, this is the first method that supports learning of sample specific fusion weights for late fusion.

Kuan-Ting Lai

Papers

Video Event Detection by Inferring Temporal Instance Labels

Sample-Specific Late Fusion for Visual Category Recognition

Human Action Recognition Using Histogram of Oriented Gradient of Motion History Image

Recognizing Complex Events in Videos by Learning Key Static-Dynamic Evidences

Learning Sample Specific Weights for Late Fusion