Jan C. van Gemert

Visual Word Ambiguity

This paper studies automatic image classification by modeling soft assignment in the popular codebook model. The codebook model describes an image as a bag of discrete visual words selected from a vocabulary, where the frequency distributions of visual words in an image allow classification. One inherent component of the codebook model is the assignment of discrete visual words to continuous image features. Despite the clear mismatch of this hard assignment with the nature of continuous features, the approach has been successfully applied for some years. In this paper, we investigate four types of soft assignment of visual words to image features. We demonstrate that explicitly modeling visual word assignment ambiguity improves classification performance compared to the hard assignment of the traditional codebook model. The traditional codebook model is compared against our method for five well-known data sets: 15 natural scenes, Caltech-101, Caltech-256, and Pascal VOC 2007/2008. We demonstrate that large codebook vocabulary sizes completely deteriorate the performance of the traditional model, whereas the proposed model performs consistently. Moreover, we show that our method profits in high-dimensional feature spaces and reaps higher benefits when increasing the number of image categories.

The challenge problem for automated detection of 101 semantic concepts in multimedia

We introduce the challenge problem for generic video indexing to gain insight in intermediate steps that affect performance of multimedia analysis methods, while at the same time fostering repeatability of experiments. To arrive at a challenge problem, we provide a general scheme for the systematic examination of automated concept detection methods, by decomposing the generic video indexing problem into 2 unimodal analysis experiments, 2 multimodal analysis experiments, and 1 combined analysis experiment. For each experiment, we evaluate generic video indexing performance on 85 hours of international broadcast news data, from the TRECVID 2005/2006 benchmark, using a lexicon of 101 semantic concepts. By establishing a minimum performance on each experiment, the challenge problem allows for component-based optimization of the generic indexing issue, while simultaneously offering other researchers a reference for comparison during indexing methodology development. To stimulate further investigations in intermediate analysis steps that inuence video indexing performance, the challenge offers to the research community a manually annotated concept lexicon, pre-computed low-level multimedia features, trained classifier models, and five experiments together with baseline performance, which are all available at http://www.mediamill.nl/challenge/.

Kernel Codebooks for Scene Categorization

This paper introduces a method for scene categorization by modeling ambiguity in the popular codebook approach. The codebook approach describes an image as a bag of discrete visual codewords, where the frequency distributions of these words are used for image categorization. There are two drawbacks to the traditional codebook model: codeword uncertainty and codeword plausibility. Both of these drawbacks stem from the hard assignment of visual features to a single codeword. We show that allowing a degree of ambiguity in assigning codewords improves categorization performance for three state-of-the-art datasets.

What do 15,000 object categories tell us about classifying and localizing actions?

This paper contributes to automatic classification and localization of human actions in video. Whereas motion is the key ingredient in modern approaches, we assess the benefits of having objects in the video representation. Rather than considering a handful of carefully selected and localized objects, we conduct an empirical study on the benefit of encoding 15,000 object categories for action using 6 datasets totaling more than 200 hours of video and covering 180 action classes. Our key contributions are i) the first in-depth study of encoding objects for actions, ii) we show that objects matter for actions, and are often semantically relevant as well. iii) We establish that actions have object preferences. Rather than using all objects, selection is advantageous for action recognition. iv)We reveal that object-action relations are generic, which allows to transferring these relationships from the one domain to the other. And, v) objects, when combined with motion, improve the state-of-the-art for both action classification and localization.

Comparing compact codebooks for visual categorization

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 200h 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.

MediaMill: exploring news video archives based on learned semantics

In this technical demonstration we showcase the MediaMill system. A search engine that facilitates access to news video archives at a semantic level. The core of the system is an unprecedented lexicon of 100 automatically detected semantic concepts. Based on this lexicon we demonstrate how users can obtain highly relevant retrieval results using query-by-concept. In addition, we show how the lexicon of concepts can be exploited for novel applications using advanced semantic visualizations. Several aspects of the MediaMill system are evaluated as part of our TRECVID 2005 efforts.

Evaluation of Color Spatio-Temporal Interest Points for Human Action Recognition

This paper considers the recognition of realistic human actions in videos based on spatio-temporal interest points (STIPs). Existing STIP-based action recognition approaches operate on intensity representations of the image data. Because of this, these approaches are sensitive to disturbing photometric phenomena, such as shadows and highlights. In addition, valuable information is neglected by discarding chromaticity from the photometric representation. These issues are addressed by color STIPs. Color STIPs are multichannel reformulations of STIP detectors and descriptors, for which we consider a number of chromatic and invariant representations derived from the opponent color space. Color STIPs are shown to outperform their intensity-based counterparts on the challenging UCF sports, UCF11 and UCF50 action recognition benchmarks by more than 5% on average, where most of the gain is due to the multichannel descriptors. In addition, the results show that color STIPs are currently the single best low-level feature choice for STIP-based approaches to human action recognition.

The Rijksmuseum Challenge: Museum-Centered Visual Recognition

This paper offers a challenge for visual classification and content-based retrieval of artistic content. The challenge is posed from a museum-centric point of view offering a wide range of object types including paintings, photographs, ceramics, furniture, etc. The freely available dataset consists of 112,039 photographic reproductions of the artworks exhibited in the Rijksmuseum in Amsterdam, the Netherlands. We offer four automatic visual recognition challenges consisting of predicting the artist, type, material and creation year. We include a set of baseline results, and make available state-of-the-art image features encoded with the Fisher vector. Progress on this challenge improves the tools of a museum curator while improving content-based exploration by online visitors of the museum collection.

Bag-of-Fragments: Selecting and Encoding Video Fragments for Event Detection and Recounting

The goal of this paper is event detection and recounting using a representation of concept detector scores. Different from existing work, which encodes videos by averaging concept scores over all frames, we propose to encode videos using fragments that are discriminatively learned per event. Our bag-of-fragments split a video into semantically coherent fragment proposals. From training video proposals we show how to select the most discriminative fragment for an event. An encoding of a video is in turn generated by matching and pooling these discriminative fragments to the fragment proposals of the video. The bag-of-fragments forms an effective encoding for event detection and is able to provide a precise temporally localized event recounting. Furthermore, we show how bag-of-fragments can be extended to deal with irrelevant concepts in the event recounting. Experiments on challenging web videos show that i) our modest number of fragment proposals give a high sub-event recall, ii) bag-of-fragments is complementary to global averaging and provides better event detection, iii) bag-of-fragments with concept filtering yields a desirable event recounting. We conclude that fragments matter for video event detection and recounting.

Object reading: text recognition for object recognition

We propose to use text recognition to aid in visual object class recognition. To this end we first propose a new algorithm for text detection in natural images. The proposed text detection is based on saliency cues and a context fusion step. The algorithm does not need any parameter tuning and can deal with varying imaging conditions. We evaluate three different tasks: 1. Scene text recognition, where we increase the state-of-the-art by 0.17 on the ICDAR 2003 dataset. 2. Saliency based object recognition, where we outperform other state-of-the-art saliency methods for object recognition on the PASCAL VOC 2011 dataset. 3. Object recognition with the aid of recognized text, where we are the first to report multi-modal results on the IMET set. Results show that text helps for object class recognition if the text is not uniquely coupled to individual object instances.