Learning video concept detectors from social media sources, such as Flickr images and YouTube videos, has the potential to address a wide variety of concept queries for video search. While the potential has been recognized by many, and progress on the topic has been impressive, we argue that key questions crucial to know how to learn effective video concept detectors from social media examples? remain open. As an initial attempt to answer these questions, we conduct an experimental study using a video search engine which is capable of learning concept detectors from social media examples, be it socially tagged videos or socially tagged images. Within the video search engine we investigate three strategies for positive example selection, three negative example selection strategies and three learning strategies. The performance is evaluated on the challenging TRECVID 2012 benchmark consisting of 600 h of Internet video. From the experiments we derive four best practices: (1) tagged images are a better source for learning video concepts than tagged videos, (2) selecting tag relevant positive training examples is always beneficial, (3) selecting relevant negative examples is advantageous and should be treated differently for video and image sources, and (4) learning concept detectors with selected relevant training data before learning is better then incorporating the relevance during the learning process. The best practices within our video search engine lead to state-of-the-art performance in the TRECVID 2013 benchmark for concept detection without manually provided annotations.

Multimedia event detection (MED)is a challenging problem because of the heterogeneous content and variable quality found in large collections of Internet videos. To study the value of multimedia features and fusion for representing and learning events from a set of example video clips, we created SESAME, a system for video SEarch with Speed and Accuracy for Multimedia Events. SESAME includes multiple bag-of-words event classifiers based on single data types: low-level visual, motion, and audio features; high-level semantic visual concepts; and automatic speech recognition. Event detection performance was evaluated for each event classifier. The performance of low-level visual and motion features was improved by the use of difference coding. The accuracy of the visual concepts was nearly as strong as that of the low-level visual features. Experiments with a number of fusion methods for combining the event detection scores from these classifiers revealed that simple fusion methods, such as arithmetic mean, perform as well as or better than other, more complex fusion methods. SESAME's performance in the 2012 TRECVID MED evaluation was one of the best reported.

Learning classifiers for many visual concepts are important for image categorization and retrieval. As a classifier tends to misclassify negative examples which are visually similar to positive ones, inclusion of such misclassified and thus relevant negatives should be stressed during learning. User-tagged images are abundant online, but which images are the relevant negatives remains unclear. Sampling negatives at random is the de facto standard in the literature. In this paper, we go beyond random sampling by proposing Negative Bootstrap. Given a visual concept and a few positive examples, the new algorithm iteratively finds relevant negatives. Per iteration, we learn from a small proportion of many user-tagged images, yielding an ensemble of meta classifiers. For efficient classification, we introduce Model Compression such that the classification time is independent of the ensemble size. Compared with the state of the art, we obtain relative gains of 14% and 18% on two present-day benchmarks in terms of mean average precision. For concept search in one million images, model compression reduces the search time from over 20 h to approximately 6 min. The effectiveness and efficiency, without the need of manually labeling any negatives, make negative bootstrap appealing for learning better visual concept classifiers.

Content-based video retrieval is maturing to the point where it can be used in real-world retrieval practices. One such practice is the audiovisual archive, whose users increasingly require fine-grained access to broadcast television content. In this paper, we take into account the information needs and retrieval data already present in the audiovisual archive, and demonstrate that retrieval performance can be significantly improved when content-based methods are applied to search. To the best of our knowledge, this is the first time that the practice of an audiovisual archive has been taken into account for quantitative retrieval evaluation. To arrive at our main result, we propose an evaluation methodology tailored to the specific needs and circumstances of the audiovisual archive, which are typically missed by existing evaluation initiatives. We utilize logged searches, content purchases, session information, and simulators to create realistic query sets and relevance judgments. To reflect the retrieval practice of both the archive and the video retrieval community as closely as possible, our experiments with three video search engines incorporate archive-created catalog entries as well as state-of-the-art multimedia content analysis results. A detailed query-level analysis indicates that individual content-based retrieval methods such as transcript-based retrieval and concept-based retrieval yield approximately equal performance gains. When combined, we find that content-based video retrieval incorporated into the archive’s practice results in significant performance increases for shot retrieval and for retrieving entire television programs. The time has come for audiovisual archives to start accommodating content-based video retrieval methods into their daily practice.

Searching for the co-occurrence of two visual concepts in unlabeled images is an important step towards answering complex user queries. Traditional visual search methods use combinations of the confidence scores of individual concept detectors to tackle such queries. In this paper we introduce the notion of bi-concepts, a new concept-based retrieval method that is directly learned from social-tagged images. As the number of potential bi-concepts is gigantic, manually collecting training examples is infeasible. Instead, we propose a multimedia framework to collect de-noised positive as well as informative negative training examples from the social web, to learn bi-concept detectors from these examples, and to apply them in a search engine for retrieving bi-concepts in unlabeled images. We study the behavior of our bi-concept search engine using 1.2M social-tagged images as a data source. Our experiments indicate that harvesting examples for bi-concepts differs from traditional single-concept methods, yet the examples can be collected with high accuracy using a multi-modal approach. We find that directly learning bi-concepts is better than oracle linear fusion of single-concept detectors, with a relative improvement of 100%. This study reveals the potential of learning high-order semantics from social images, for free, suggesting promising new lines of research.

In this paper, we address the incoherence problem of the visual words in bag-of-words vocabularies. Different from existing work, which assigns words based on closeness in descriptor space, we focus on identifying pairs of independent, distant words - the visual synonyms - that are likely to host image patches of similar visual reality. We focus on landmark images, where the image geometry guides the detection of synonym pairs. Image geometry is used to find those image features that lie in the nearly identical physical location, yet are assigned to different words of the visual vocabulary. Defined in this way, we evaluate the validity of visual synonyms. We also examine the closeness of synonyms in the L2-normalized feature space. We show that visual synonyms may successfully be used for vocabulary reduction. Furthermore, we show that combining the reduced visual vocabularies with synonym augmentation, we perform on par with the state-of-the-art bag-of-words approach, while having a 98% smaller vocabulary.

In this paper we present the Name-It-Game, an interactive multimedia game fostering the swift creation of a large data set of region-based image annotations. Compared to existing annotation games, we consider an added semantic structure, by means of the WordNet ontology, the main innovation of the Name-It-Game. Using an ontology-powered game, instead of the more traditional annotation tools, potentially makes region-based image labeling more fun and accessible for every type of user. However, the current games often present the players with hard-to-guess objects. To prevent this from happening in the Name-It-Game, we successfully identify WordNet categories which filter out hard-to-guess objects. To verify the speed of the annotation process, we compare the online Name-It-Game with a desktop tool with similar features. Results show that the Name-It-Game outperforms this tool for semantic region-based image labeling. Lastly, we measure the accuracy of the produced segmentations and compare them with carefully created LabelMe segmentations. Judging from the quantitative and qualitative results, we believe the segmentations are competitive to those of LabelMe, especially when averaged over multiple games. By adding semantics to region-based image annotations, using the Name-It-Game, we have opened up an efficient means to provide precious labels in a playful manner.

Visual categorization is important to manage large collections of digital images and video, where textual meta-data is often incomplete or simply unavailable. The bag-of-words model has become the most powerful method for visual categorization of images and video. Despite its high accuracy, a severe drawback of this model is its high computational cost. As the trend to increase computational power in newer CPU and GPU architectures is to increase their level of parallelism, exploiting this parallelism becomes an important direction to handle the computational cost of the bag-of-words approach. When optimizing a system based on the bag-of-words approach, the goal is to minimize the time it takes to process batches of images. Additionally, we also consider power usage as an evaluation metric. In this paper, we analyze the bag-of-words model for visual categorization in terms of computational cost and identify two major bottlenecks: the quantization step and the classification step. We address these two bottlenecks by proposing two efficient algorithms for quantization and classification by exploiting the GPU hardware and the CUDA parallel programming model. The algorithms are designed to (1) keep categorization accuracy intact, (2) decompose the problem and (3) give the same numerical results. In the experiments on large scale datasets it is shown that, by using a parallel implementation on the Geforce GTX260 GPU, classifying unseen images is 4.8 times faster than a quad-core CPU version on the Core i7 920, while giving the exact same numerical results. In addition, we show how the algorithms can be generalized to other applications, such as text retrieval and video retrieval. Moreover, when the obtained speedup is used to process extra video frames in a video retrieval benchmark, the accuracy of visual categorization is improved by 29%.

Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been proposed. Because many different descriptors exist, a structured overview is required of color invariant descriptors in the context of image category recognition. Therefore, this paper studies the invariance properties and the distinctiveness of color descriptors in a structured way. The analytical invariance properties of color descriptors are explored, using a taxonomy based on invariance properties with respect to photometric transformations, and tested experimentally using a dataset with known illumination conditions. In addition, the distinctiveness of color descriptors is assessed experimentally using two benchmarks, one from the image domain and one from the video domain. From the theoretical and experimental results, it can be derived that invariance to light intensity changes and light color changes affects category recognition. The results reveal further that, for light intensity changes, the usefulness of invariance is category-specific. Overall, when choosing a single descriptor and no prior knowledge about the dataset and object and scene categories is available, the OpponentSIFT is recommended. Furthermore, a combined set of color descriptors outperforms intensity-based SIFT and improves category recognition by 8% on the PASCAL VOC 2007 and by 7% on the MediaMill Challenge.

The Microsoft SenseCam is a small lightweight wearable camera used to passively capture photos and other sensor readings from a user’s day-to-day activities. It captures on average 3,000 images in a typical day, equating to almost 1 million images per year. It can be used to aid memory by creating a personal multimedia lifelog, or visual recording of the wearer’s life. However the sheer volume of image data captured within a visual lifelog creates a number of challenges, particularly for locating relevant content. Within this work, we explore the applicability of semantic concept detection, a method often used within video retrieval, on the domain of visual lifelogs. Our concept detector models the correspondence between low-level visual features and high-level semantic concepts (such as indoors, outdoors, people, buildings, etc.) using supervised machine learning. By doing so it determines the probability of a concept’s presence. We apply detection of 27 everyday semantic concepts on a lifelog collection composed of 257,518 SenseCam images from 5 users. The results were evaluated on a subset of 95,907 images, to determine the accuracy for detection of each semantic concept. We conducted further analysis on the temporal consistency, co-occurance and relationships within the detected concepts to more extensively investigate the robustness of the detectors within this domain.

Progress in visual-concept search suggests that machine understanding of images is within reach.

In the face of current large-scale video libraries, the practical applicability of content-based indexing algorithms is constrained by their efficiency. This paper strives for efficient large-scale video indexing by comparing various visual-based concept categorization techniques. In visual categorization, the popular codebook model has shown excellent categorization performance. The codebook model represents continuous visual features by discrete prototypes predefined in a vocabulary. The vocabulary size has a major impact on categorization efficiency, where a more compact vocabulary is more efficient. However, smaller vocabularies typically score lower on classification performance than larger vocabularies. This paper compares four approaches to achieve a compact codebook vocabulary while retaining categorization performance. For these four methods, we investigate the trade-off between codebook compactness and categorization performance. We evaluate the methods on more than 200 h of challenging video data with as many as 101 semantic concepts. The results allow us to create a taxonomy of the four methods based on their efficiency and categorization performance.

Social image analysis and retrieval is important for helping people organize and access the increasing amount of user-tagged multimedia. Since user tagging is known to be uncontrolled, ambiguous, and overly personalized, a fundamental problem is how to interpret the relevance of a user-contributed tag with respect to the visual content the tag is describing. Intuitively, if different persons label visually similar images using the same tags, these tags are likely to reflect objective aspects of the visual content. Starting from this intuition, we propose in this paper a neighbor voting algorithm which accurately and efficiently learns tag relevance by accumulating votes from visual neighbors. Under a set of well defined and realistic assumptions, we prove that our algorithm is a good tag relevance measurement for both image ranking and tag ranking. Three experiments on 3.5 million Flickr photos demonstrate the general applicability of our algorithm in both social image retrieval and image tag suggestion. Our tag relevance learning algorithm substantially improves upon baselines for all the experiments. The results suggest that the proposed algorithm is promising for real-world applications.

In this paper, we review 300 references on video retrieval, indicating when text-only solutions are unsatisfactory and showing the promising alternatives which are in majority concept-based. Therefore, central to our discussion is the notion of a semantic concept: an objective linguistic description of an observable entity. Specifically, we present our view on how its automated detection, selection under uncertainty, and interactive usage might solve the major scientific problem for video retrieval: the semantic gap. To bridge the gap, we lay down the anatomy of a concept-based video search engine. We present a component-wise decomposition of such an interdisciplinary multimedia system, covering influences from information retrieval, computer vision, machine learning, and human-computer interaction. For each of the components we review state-of-the-art solutions in the literature, each having different characteristics and merits. Because of these differences, we cannot understand the progress in video retrieval without serious evaluation efforts such as carried out in the NIST TRECVID benchmark. We discuss its data, tasks, results, and the many derived community initiatives in creating annotations and baselines for repeatable experiments. We conclude with our perspective on future challenges and opportunities.

Image collections are getting larger and larger. To access those collections, systems for managing, searching, and browsing are necessary. Visualization plays an essential role in such systems. Existing visualization systems do not analyze all the problems occurring when dealing with large visual collections. In this paper, we make these problems explicit. From there, we establish three general requirements: overview, visibility, and structure preservation. Solutions for each requirement are proposed, as well as functions balancing the different requirements. We present an optimal visualization scheme, supporting users in interacting with large image collections. Experimental results with a collection of 10,000 Corel images, using simulated user actions, show that the proposed scheme significantly improves performance for a given task compared to the 2D grid-based visualizations commonly used in content-based image retrieval.

Video search is an experience for the senses. As a result, traditional information retrieval metrics can't fully measure the quality of a video search system. To provide a more interactive assessment of today's video search engines, the authors have organized the VideOlympics as a real-time evaluation showcase where systems compete to answer specific video searches in front of a live audience. At VideOlympics, seeing and hearing is believing.

At one end of the spectrum, research in interactive content-based retrieval concentrates on machine learning methods for effective use of relevance feedback. On the other end, the information visualization community focuses on effective methods for conveying information to the user. What is lacking is research considering the information visualization and interactive retrieval as truly integrated parts of one content-based search system. In such an integrated system, there are many degrees of freedom like the similarity function, the number of images to display, the image size, different visualization modes, and possible feedback modes. To base the optimal values for all of those on user studies is unfeasible. We therefore develop search scenarios in which tasks and user actions are simulated. From there, the proposed scheme is optimized based on objective constraints and evaluation criteria. In such a manner, the degrees of freedom are reduced and the remaining degrees can be evaluated in user studies. In this article, we present a system that integrates advanced similarity based visualization with active learning. We have performed extensive experimentation on interactive category search with different image collections. The results using the proposed simulation scheme show that indeed the use of advanced visualization and active learning pays off in all of these datasets.

In this paper, we argue to learn dissimilarity for interactive search in content based image retrieval. In literature, dissimilarity is often learned via the feature space by feature selection, feature weighting or by adjusting the parameters of a function of the features. Other than existing techniques, we use feedback to adjust the dissimilarity space independent of feature space. This has the great advantage that it manipulates dissimilarity directly. To create a dissimilarity space, we use the method proposed by Pekalska and Duin, selecting a set of images called prototypes and computing distances to those prototypes for all images in the collection. After the user gives feedback, we apply active learning with a one-class support vector machine to decide the movement of images such that relevant images stay close together while irrelevant ones are pushed away (the work of Guo ). The dissimilarity space is then adjusted accordingly. Results on a Corel dataset of 10000 images and a TrecVid collection of 43907 keyframes show that our proposed approach is not only intuitive, it also significantly improves the retrieval performance.

As the world uses more digital video that requires greater storage space, Grid computing is becoming indispensable for urgent problems in multimedia content analysis. Parallel-Horus, a support tool for applications in multimedia Grid computing, lets users implement multimedia applications as sequential programs for efficient execution on clusters and Grids, based on wide-area multimedia services.

In this paper, we propose an automatic video retrieval method based on high-level concept detectors. Research in video analysis has reached the point where over 100 concept detectors can be learned in a generic fashion, albeit with mixed performance. Such a set of detectors is very small still compared to ontologies aiming to capture the full vocabulary a user has. We aim to throw a bridge between the two fields by building a multimedia thesaurus, i.e., a set of machine learned concept detectors that is enriched with semantic descriptions and semantic structure obtained from WordNet. Given a multimodal user query, we identify three strategies to select a relevant detector from this thesaurus, namely: text matching, ontology querying, and semantic visual querying. We evaluate the methods against the automatic search task of the TRECVID 2005 video retrieval benchmark, using a news video archive of 85 h in combination with a thesaurus of 363 machine learned concept detectors. We assess the influence of thesaurus size on video search performance, evaluate and compare the multimodal selection strategies for concept detectors, and finally discuss their combined potential using oracle fusion. The set of queries in the TRECVID 2005 corpus is too small for us to be definite in our conclusions, but the results suggest promising new lines of research.

The six papers in this special section focus on semantic image and video indexing in broad domains. To bring semantics to the user in broad domains both the indexing and retrieval step have to be considered. The papers here address both steps and the relation to ontologies.

Effective video retrieval is the result of an interplay between interactive query selection, advanced visualization of results, and a goal-oriented human user. Traditional interactive video retrieval approaches emphasize paradigms, such as query-by-keyword and query-by-example, to aid the user in the search for relevant footage. However, recent results in automatic indexing indicate that query-by-concept is becoming a viable resource for interactive retrieval also. We propose in this paper a new video retrieval paradigm. The core of the paradigm is formed by first detecting a large lexicon of semantic concepts. From there, we combine query-by-concept, query-by-example, query-by-keyword, and user interaction into the MediaMill semantic video search engine. To measure the impact of increasing lexicon size on interactive video retrieval performance, we performed two experiments against the 2004 and 2005 NIST TRECVID benchmarks, using lexicons containing 32 and 101 concepts respectively. The results suggest that from all factors that play a role in interactive retrieval, a large lexicon of semantic concepts matters most. Indeed, by exploiting large lexicons, many video search questions are solvable without using query-by-keyword and query-by-example. What is more, we show that the lexicon-driven search engine outperforms all state-of-the-art video retrieval systems in both TRECVID 2004 and 2005.

This paper presents the semantic pathfinder architecture for generic indexing of multimedia archives. The semantic pathfinder extracts semantic concepts from video by exploring different paths through three consecutive analysis steps, which we derive from the observation that produced video is the result of an authoring-driven process. We exploit this authoring metaphor for machine-driven understanding. The pathfinder starts with the content analysis step. In this analysis step, we follow a data-driven approach of indexing semantics. The style analysis step is the second analysis step. Here we tackle the indexing problem by viewing a video from the perspective of production. Finally, in the context analysis step, we view semantics in context. The virtue of the semantic pathfinder is its ability to learn the best path of analysis steps on a per-concept basis. To show the generality of this novel indexing approach we develop detectors for a lexicon of 32 concepts and we evaluate the semantic pathfinder against the 2004 NIST TRECVID video retrieval benchmark, using a news archive of 64 hours. Top ranking performance in the semantic concept detection task indicates the merit of the semantic pathfinder for generic indexing of multimedia archives.

We propose a generic and robust framework for news video indexing, which we found on a broadcast news production model. We identify within this model four production phases, each providing useful metadata for annotation. In contrast to semi-automatic indexing approaches, which exploit this information at production time, we adhere to an automatic data-driven approach. To that end, we analyze a digital news video using a separate set of multimodal detectors for each production phase. By combining the resulting production-derived features into a statistical classifier ensemble, the framework facilitates robust classification of several rich semantic concepts in news video; rich meaning that concepts share many similarities in their production process. Experiments on an archive of 120 hours of news video, from the 2003 TRECVID benchmark, show that a combined analysis of production phases yields the best results. In addition, we demonstrate that the accuracy of the proposed style analysis framework for classification of several rich semantic concepts is state-of-the-art.

The results of a study are presented, in which people queried a news archive using an interactive video retrieval system. 242 search sessions by 39 participants on 24 topics were assessed. Before, during and after the study, participants filled in questionnaires about their expectations of a search. The questionnaire data, logged user actions on the system, queries formulated by users, and a quality measure of each search were studied. The results of the study show that topics concerning 'specific' people or objects were better retrieved than topics concerning 'general' objects and scenes. Users were able to estimate the overall quality of a search but did not know when the optimal result was reached within the search process. Analysis of the results at various stages in the retrieval process suggests that retrieval based on transcriptions of the speech in video data adds more to the average precision of the result than content-based image retrieval based on low-level visual features. The latter is particularly useful in providing the user with an overview of the dataset and thus an indication of the success of a search. Based on the results, implications for the design of user interfaces of video retrieval systems are discussed.

Content-based image retrieval (CBIR) has been under investigation for a long time with many systems built to meet different application demands. However, in all systems, there is still a gap between the user's expectation and the system's retrieval capabilities. Therefore, user interaction is an essential component of any CBIR system. Interaction up to now has mostly focused on changing global image features or similarities between images. We consider the interaction with salient details in the image i.e. points, lines, and regions. Interactive salient detail definition goes further than summarizing the image into a set of salient details. We aim to dynamically update the user- and context-dependent definition of saliency based on relevance feedback. To that end, we propose an interaction framework for salient details from the perspective of the user. A number of instantiations of the framework are presented. Finally, we apply our approach for query refinement in detail based image retrieval system with salient points and regions. Experimental results prove the effectiveness of adapting the saliency from user feedback in the retrieval process.

We propose the Time Interval Multimedia Event (TIME) framework as a robust approach for classification of semantic events in multimodal video documents. The representation used in TIME extends the Allen time relations and allows for proper inclusion of context and synchronization of the heterogeneous information sources involved in multimodal video analysis. To demonstrate the viability of our approach, it was evaluated on the domains of soccer and news broadcasts. For automatic classification of semantic events, we compare three different machine learning techniques, i.c. C4.5 decision tree, Maximum Entropy, and Support Vector Machine. The results show that semantic video indexing results significantly benefit from using the TIME framework.

Efficient and effective handling of video documents depends on the availability of indexes. Manual indexing is unfeasible for large video collections. In this paper we survey several methods aiming at automating this time and resource consuming process. Good reviews on single modality based video indexing have appeared in literature. Effective indexing, however, requires a multimodal approach in which either the most appropriate modality is selected or the different modalities are used in collaborative fashion. Therefore, instead of separately treating the different information sources involved, and their specific algorithms, we focus on the similarities and differences between the modalities. To that end we put forward a unifying and multimodal framework, which views a video document from the perspective of its author. This framework forms the guiding principle for identifying index types, for which automatic methods are found in literature. It furthermore forms the basis for categorizing these different methods.