Multimedia Event Detection Research Articles

Video2vec Embeddings Recognize Events When Examples Are Scarce.

This paper aims for event recognition when video examples are scarce or even completely absent. The key in such a challenging setting is a semantic video representation. Rather than building the representation from individual attribute detectors and their annotations, we propose to learn the entire representation from freely available web videos and their descriptions using an embedding between video features and term vectors. In our proposed embedding, which we call Video2vec, the correlations between the words are utilized to learn a more effective representation by optimizing a joint objective balancing descriptiveness and predictability. We show how learning the Video2vec embedding using a multimodal predictability loss, including appearance, motion and audio features, results in a better predictable representation. We also propose an event specific variant of Video2vec to learn a more accurate representation for the words, which are indicative of the event, by introducing a term sensitive descriptiveness loss. Our experiments on three challenging collections of web videos from the NIST TRECVID Multimedia Event Detection and Columbia Consumer Videos datasets demonstrate: i) the advantages of Video2vec over representations using attributes or alternative embeddings, ii) the benefit of fusing video modalities by an embedding over common strategies, iii) the complementarity of term sensitive descriptiveness and multimodal predictability for event recognition. By its ability to improve predictability of present day audio-visual video features, while at the same time maximizing their semantic descriptiveness, Video2vec leads to state-of-the-art accuracy for both few- and zero-example recognition of events in video.

TagBook: A Semantic Video Representation Without Supervision for Event Detection

We consider the problem of event detection in video for scenarios where only a few, or even zero, examples are available for training. For this challenging setting, the prevailing solutions in the literature rely on a semantic video representation obtained from thousands of pretrained concept detectors. Different from existing work, we propose a new semantic video representation that is based on freely available social tagged videos only, without the need for training any intermediate concept detectors. We introduce a simple algorithm that propagates tags from a video's nearest neighbors, similar in spirit to the ones used for image retrieval, but redesign it for video event detection by including video source set refinement and varying the video tag assignment. We call our approach TagBook and study its construction, descriptiveness, and detection performance on the TRECVID 2013 and 2014 multimedia event detection datasets and the Columbia Consumer Video dataset. Despite its simple nature, the proposed TagBook video representation is remarkably effective for few-example and zero-example event detection, even outperforming very recent state-of-the-art alternatives building on supervised representations.

Robust spatial-temporal deep model for multimedia event detection

The task of multimedia event detection (MED) aims at training a set of models that can automatically detect the most event-relevant videos from large datasets. In this paper, we attempt to build a robust spatial-temporal deep neural network for large-scale video event detection. In our setting, each video follows a multiple instance assumption, where its visual segments contain both spatial and temporal properties of events. Regarding these properties, we try to implement the MED system by a two-step training phase: unsupervised recurrent video reconstruction and supervised fine-tuning. We conduct extensive experiments on the challenging TRECVID MED14 dataset, which indicate that with the consideration of both spatial and temporal information, the detection performance can be further boosted compared with the state-of-the-art MED models.

Combining multi-representation for multimedia event detection using co-training

In recent years, multimedia event detection has been attracting extensive research attention because of the exponential increase in volume of web video data. Traditional approaches usually utilize single visual representation, which may suffer from the problem of insufficient descriptive power. How to jointly employ multiple types of visual representation to facilitate multimedia event detection (MED) in videos remains an open problem. In this work, we propose a novel system for event detection based on combination of multi-view representations and co-training algorithm. Specifically, given several types of low-level visual features (i.e., Convolutional Neural Networks (CNNs) and Fisher vector), we first train an initial classifier for each type of visual feature. Then, we use these classifiers to separately predict labels of unlabeled videos, and those with consistent prediction are merged into the training set. We alternatively repeat the processes of training the classifiers and enlarging the training set until convergence. To investigate the relationship among different types of visual features, the prediction scores of the two classifiers are fused by a linear weighted fusion method. We evaluate our MED system on the TRECVID MED11 data set, and the experimental results have demonstrated the outstanding performance of the proposed approach as compared to several other state-of-the-art algorithms.

Bi-Level Semantic Representation Analysis for Multimedia Event Detection.

Multimedia event detection has been one of the major endeavors in video event analysis. A variety of approaches have been proposed recently to tackle this problem. Among others, using semantic representation has been accredited for its promising performance and desirable ability for human-understandable reasoning. To generate semantic representation, we usually utilize several external image/video archives and apply the concept detectors trained on them to the event videos. Due to the intrinsic difference of these archives, the resulted representation is presumable to have different predicting capabilities for a certain event. Notwithstanding, not much work is available for assessing the efficacy of semantic representation from the source-level. On the other hand, it is plausible to perceive that some concepts are noisy for detecting a specific event. Motivated by these two shortcomings, we propose a bi-level semantic representation analyzing method. Regarding source-level, our method learns weights of semantic representation attained from different multimedia archives. Meanwhile, it restrains the negative influence of noisy or irrelevant concepts in the overall concept-level. In addition, we particularly focus on efficient multimedia event detection with few positive examples, which is highly appreciated in the real-world scenario. We perform extensive experiments on the challenging TRECVID MED 2013 and 2014 datasets with encouraging results that validate the efficacy of our proposed approach.

Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos

We propose a new zero-shot Event-Detection method by Multi-modal Distributional Semantic embedding of videos. Our model embeds object and action concepts as well as other available modalities from videos into a distributional semantic space. To our knowledge, this is the first Zero-Shot event detection model that is built on top of distributional semantics and extends it in the following directions: (a) semantic embedding of multimodal information in videos (with focus on the visual modalities), (b) semantic embedding of concepts definitions, and (c) retrieve videos by free text event query (e.g., "changing a vehicle tire") based on their content. We first embed the video into the multi-modal semantic space and then measure the similarity between videos with the event query in free text form. We validated our method on the large TRECVID MED (Multimedia Event Detection) challenge. Using only the event title as a query, our method outperformed the state-the-art that uses big descriptions from 12.6\% to 13.5\% with MAP metric and from 0.73 to 0.83 with ROC-AUC metric. It is also an order of magnitude faster.

Concepts Not Alone: Exploring Pairwise Relationships for Zero-Shot Video Activity Recognition

Vast quantities of videos are now being captured at astonishing rates, but the majority of these are not labelled. To cope with such data, we consider the task of content-based activity recognition in videos without any manually labelled examples, also known as zero-shot video recognition. To achieve this, videos are represented in terms of detected visual concepts, which are then scored as relevant or irrelevant according to their similarity with a given textual query. In this paper, we propose a more robust approach for scoring concepts in order to alleviate many of the brittleness and low precision problems of previous work. Not only do we jointly consider semantic relatedness, visual reliability, and discriminative power. To handle noise and non-linearities in the ranking scores of the selected concepts, we propose a novel pairwise order matrix approach for score aggregation. Extensive experiments on the large-scale TRECVID Multimedia Event Detection data show the superiority of our approach.

Invited Paper] Strategies for Searching Video Content with Text Queries or Video Examples

The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these videos are unsearchable by current search engines. Therefore, content-based video retrieval (CBVR) tackles this metadata-scarcity problem by directly analyzing the visual and audio streams of each video. CBVR encompasses multiple research topics, including low-level feature design, feature fusion, semantic detector training and video search/reranking. We present novel strategies in these topics to enhance CBVR in both accuracy and speed under different query inputs, including pure textual queries and query by video examples. Our proposed strategies have been incorporated into our submission for the TRECVID 2014 Multimedia Event Detection evaluation, where our system outperformed other submissions in both text queries and video example queries, thus demonstrating the effectiveness of our proposed approaches.

Static Shot based Keyframe Extraction for Multimedia Event Detection

Nowadays, processing of Multimedia information leads to high computational cost due its larger size especially for video processing. In order to reduce the size of the video and to save the user's time in spending their attention on whole video, video summarization is adopted. However, it can be performed using keyframe extraction from the video. To perform this task, a new simple keyframe extraction method is proposed using divide and conquer strategy in which, Scale Invariant Feature Transform (SIFT) based feature representation vector is extracted and the whole video is categorized into static and dynamic shots. The dynamic shot is further processed till it becomes static. A representative frame is extracted from every static shot and the redundant keyframes are removed using keyframe similarity matching measure. Experimental evaluation is carried out and the proposed work is compared with related existing work. The authors' method outperforms existing methods in terms of Precision (P), Recall (R), F-Score (F). Also, Fidelity measure is computed for proposed work which gives better result.

Invited Paper] Object Pooling for Multimedia Event Detection and Evidence Localization

Invited Paper] Object Pooling for Multimedia Event Detection and Evidence Localization

Event Bank based multimedia representation via latent group logistic regression minimization

In order to perform multimedia event detection (MED) tasks in uncontrolled videos, a very large number of labeled videos are required for training the event classifier, which would become quite challenging especially when there are lots of events. Because an event involves usually several spatial temporal objects, one intuitive solution is to model those objects from a large number of labeled images which can be obtained very easily from standard image datasets, such as the ImageNet challenge dataset, and to model their spatial temporal relationships from a relatively small number of labeled videos which can be also obtained very easily from standard video datasets, such as the TRECVID MED 2012 dataset. In this paper, we propose accordingly a latent group logistic regression (latent GLR) mixture model for those objects and an event bank descriptor for their spatial temporal relationships. Furthermore, we develop an efficient iterative training algorithm to learn model parameters of the individual latent GLR mixture model, which combines the coordinate descent approach and the gradient descent approach to minimize the l2,1-norm or group regularized logistic loss function. We also conduct extensive experiments to evaluate the object detection performance by using the latent GLR mixture model on the ImageNet challenge dataset and the event detection performance by using the event bank descriptor on the TRECVID MED 2012 dataset. The results demonstrate the effectiveness of both proposed approaches.

Knowledge based query expansion in complex multimedia event detection

A common approach in content based video information retrieval is to perform automatic shot annotation with semantic labels using pre-trained classifiers. The visual vocabulary of state-of-the-art automatic annotation systems is limited to a few thousand concepts, which creates a semantic gap between the semantic labels and the natural language query. One of the methods to bridge this semantic gap is to expand the original user query using knowledge bases. Both common knowledge bases such as Wikipedia and expert knowledge bases such as a manually created ontology can be used to bridge the semantic gap. Expert knowledge bases have highest performance, but are only available in closed domains. Only in closed domains all necessary information, including structure and disambiguation, can be made available in a knowledge base. Common knowledge bases are often used in open domain, because it covers a lot of general information. In this research, query expansion using common knowledge bases ConceptNet and Wikipedia is compared to an expert description of the topic applied to content-based information retrieval of complex events. We run experiments on the Test Set of TRECVID MED 2014. Results show that 1) Query Expansion can improve performance compared to using no query expansion in the case that the main noun of the query could not be matched to a concept detector; 2) Query expansion using expert knowledge is not necessarily better than query expansion using common knowledge; 3) ConceptNet performs slightly better than Wikipedia; 4) Late fusion can slightly improve performance. To conclude, query expansion has potential in complex event detection.

Complex event recognition using constrained low-rank representation

Complex event recognition is the problem of recognizing events in long and unconstrained videos. In this extremely challenging task, concepts have recently shown a promising direction where core low-level events (referred to as concepts) are annotated and modeled using a portion of the training data, then each complex event is described using concept scores, which are features representing the occurrence confidence for the concepts in the event. However, because of the complex nature of the videos, both the concept models and the corresponding concept scores are significantly noisy. In order to address this problem, we propose a novel low-rank formulation, which combines the precisely annotated videos used to train the concepts, with the rich concept scores. Our approach finds a new representation for each event, which is not only low-rank, but also constrained to adhere to the concept annotation, thus suppressing the noise, and maintaining a consistent occurrence of the concepts in each event. Extensive experiments on large scale real world dataset TRECVID Multimedia Event Detection 2011 and 2012 demonstrate that our approach consistently improves the discriminativity of the concept scores by a significant margin.

Event oriented dictionary learning for complex event detection.

Complex event detection is a retrieval task with the goal of finding videos of a particular event in a large-scale unconstrained Internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for the complex event detection task. However, how to effectively select the high-level semantic meaningful concepts from a large pool to assist complex event detection is rarely studied in the literature. In this paper, we propose a novel strategy to automatically select semantic meaningful concepts for the event detection task based on both the events-kit text descriptions and the concepts high-level feature descriptions. Moreover, we introduce a novel event oriented dictionary representation based on the selected semantic concepts. Toward this goal, we leverage training images (frames) of selected concepts from the semantic indexing dataset with a pool of 346 concepts, into a novel supervised multitask lp -norm dictionary learning framework. Extensive experimental results on TRECVID multimedia event detection dataset demonstrate the efficacy of our proposed method.

Complex Event Detection via Event Oriented Dictionary Learning

Complex event detection is a retrieval task with the goal of finding videos of a particular event in a large-scale unconstrained internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for the complex event detection task. However, how to effectively select the high-level semantic meaningful concepts from a large pool to assist complex event detection is rarely studied in the literature. In this paper, we propose two novel strategies to automatically select semantic meaningful concepts for the event detection task based on both the events-kit text descriptions and the concepts high-level feature descriptions. Moreover, we introduce a novel event oriented dictionary representation based on the selected semantic concepts. Towards this goal, we leverage training samples of selected concepts from the Semantic Indexing (SIN) dataset with a pool of 346 concepts, into a novel supervised multi-task dictionary learning framework. Extensive experimental results on TRECVID Multimedia Event Detection (MED) dataset demonstrate the efficacy of our proposed method.

Multimedia event detection with ℓ2-regularized logistic Gaussian mixture regression

Multimedia event detection (MED) is one of the most important branches of multimedia content analysis. Current research work on MED focuses mainly on detecting specific events, such as sport events...

Conceptlets: Selective Semantics for Classifying Video Events

An emerging trend in video event classification is to learn an event from a bank of concept detector scores. Different from existing work, which simply relies on a bank containing all available detectors, we propose in this paper an algorithm that learns from examples what concepts in a bank are most informative per event, which we call the conceptlet. We model finding the conceptlet out of a large set of concept detectors as an importance sampling problem. Our proposed approximate algorithm finds the optimal conceptlet using a cross-entropy optimization. We study the behavior of video event classification based on conceptlets by performing four experiments on challenging internet video from the 2010 and 2012 TRECVID multimedia event detection tasks and Columbia's consumer video dataset. Starting from a concept bank of more than thousand precomputed detectors, our experiments establish there are (sets of) individual concept detectors that are more discriminative and appear to be more descriptive for a particular event than others, event classification using an automatically obtained conceptlet is more robust than using all available concepts, and conceptlets obtained with our cross-entropy algorithm are better than conceptlets from state-of-the-art feature selection algorithms. What is more, the conceptlets make sense for the events of interest, without being programmed to do so.

Weakly supervised detection of video events using hidden conditional random fields

Multimedia Event Detection (MED) is the task to identify videos in which a certain event occurs. This paper addresses two problems in MED: weakly supervised setting and unclear event structure. The first indicates that since associations of shots with the event are laborious and incur annotator’s subjectivity, training videos are loosely annotated as to whether the event is contained or not. It is unknown which shots are relevant or irrelevant to the event. The second problem is the difficulty of assuming the event structure in advance, due to arbitrary camera and editing techniques. To tackle these problems, we propose a method using a Hidden Conditional Random Field (HCRF) which is a probabilistic discriminative classifier with a set of hidden states. We consider that the weakly supervised setting can be handled using hidden states as the intermediate layer to discriminate between relevant and irrelevant shots to the event. In addition, an unclear structure of the event can be exposed by features of each hidden state and its relation to the other states. Based on the above idea, we optimise hidden states and their relation so as to distinguish training videos containing the event from the others. Also, to exploit the full potential of HCRFs, we establish approaches for training video preparation, parameter initialisation and fusion of multiple HCRFs. Experimental results on TRECVID video data validate the effectiveness of our method.

Knowledge Adaptation with Partially Shared Features for Event Detection Using Few Exemplars.

Multimedia event detection (MED) is an emerging area of research. Previous work mainly focuses on simple event detection in sports and news videos, or abnormality detection in surveillance videos. In contrast, we focus on detecting more complicated and generic events that gain more users' interest, and we explore an effective solution for MED. Moreover, our solution only uses few positive examples since precisely labeled multimedia content is scarce in the real world. As the information from these few positive examples is limited, we propose using knowledge adaptation to facilitate event detection. Different from the state of the art, our algorithm is able to adapt knowledge from another source for MED even if the features of the source and the target are partially different, but overlapping. Avoiding the requirement that the two domains are consistent in feature types is desirable as data collection platforms change or augment their capabilities and we should be able to respond to this with little or no effort. We perform extensive experiments on real-world multimedia archives consisting of several challenging events. The results show that our approach outperforms several other state-of-the-art detection algorithms.

Video Event Detection Using Motion Relativity and Feature Selection

Event detection plays an essential role in video con- tent analysis. In this paper, we present our approach based on motion relativity and feature selection for video event detection. First, we propose a new motion feature, namely Expanded Rela- tive Motion Histogram of Bag-of-Visual-Words (ERMH-BoW) to employ motion relativity for event detection. In ERMH-BoW, by representing what aspect of an event with Bag-of-Visual-Words (BoW), we construct relative motion histograms between different visual words to depict the objects' activities or how aspect of the event. ERMH-BoW thus integrates both what and how as- pects for a complete event description. Meanwhile, we show that by employing motion relativity, ERMH-BoW is invariant to the varying camera movement and able to honestly describe the object activities in an event. Furthermore, compared with other motion features, ERMH-BoW encodes not only the motion of objects, but also the interactions between different objects/scenes. Second, to address the high-dimensionality problem of the ERMH-BoW feature, we further propose an approach based on information gain and informativeness weighting to select a cleaner and more discriminative set of features. Our experiments carried out on several challenging datasets provided by TRECVID for the MED (Multimedia Event Detection) task demonstrate that our proposed approach outperforms the state-of-the-art approaches for video event detection.