Adams Wei Yu

Reverse top-k search using random walk with restart

With the increasing popularity of social networks, large volumes of graph data are becoming available. Large graphs are also derived by structure extraction from relational, text, or scientific data (e.g., relational tuple networks, citation graphs, ontology networks, protein-protein interaction graphs). Node-to-node proximity is the key building block for many graph-based applications that search or analyze the data. Among various proximity measures, random walk with restart (RWR) is widely adopted because of its ability to consider the global structure of the whole network. Although RWR-based similarity search has been well studied before, there is no prior work on reverse top-k proximity search in graphs based on RWR. We discuss the applicability of this query and show that its direct evaluation using existing methods on RWR-based similarity search has very high computational and storage demands. To address this issue, we propose an indexing technique, paired with an on-line reverse top-k search algorithm. Our experiments show that our technique is efficient and has manageable storage requirements even when applied on very large graphs.

Search by mobile image based on visual and spatial consistency

Performance of state-of-the-art image retrieval systems has been improved significantly using bag-of-words approaches. After represented by visual words quantized from local features, images can be indexed and retrieved using scalable textual retrieval approaches. However, there exist at least two issues unsolved, especially for search by mobile images with large variations: (1) the loss of features discriminative power due to quantization; and (2) the underuse of spatial relationships among visual words. To address both issues, considering properties of mobile images, this paper presents a novel method coupling visual and spatial information consistently: to improve discriminative power, features of the query image are first grouped using both matched visual features and their spatial relationships; Then grouped features are softly matched to alleviate quantization loss. Experiments on both UKBench database and a collected database with more than one million images show that the proposed method achieves 10% improvement over the approach with a vocabulary tree and bundled feature method.

Learning to Skim Text

Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models have to read the whole text word by word, making it slow to handle long documents. For example, it is difficult to use a recurrent network to read a book and answer questions about it. In this paper, we present an approach of reading text while skipping irrelevant information if needed. The underlying model is a recurrent network that learns how far to jump after reading a few words of the input text. We employ a standard policy gradient method to train the model to make discrete jumping decisions. In our benchmarks on four different tasks, including number prediction, sentiment analysis, news article classification and automatic Q\&A, our proposed model, a modified LSTM with jumping, is up to 6 times faster than the standard sequential LSTM, while maintaining the same or even better accuracy.

Music identification via vocabulary tree with MFCC peaks

In this paper, a Vocabulary Tree based framework is proposed for music identification whose target is to recognize a fragment from a song database. The key to a high recognition precision within this framework is a novel feature, namely MFCC Peaks, which is a combination of MFCC and Spectral Peaks features. Our approach consists of three stages. We first build the Vocabulary Tree with 2 million MFCC Peaks features extracted from hundreds of music. Then each song in the database is quantified into some words by traveling from root down to a certain leaf. Given a query input, we apply the same quantization procedure to this fragment, score the archive according to the TF-IDF scheme and return the best matches. The experimental results demonstrate that our proposed feature has strong identifying and generalization ability. Other trials show that our approach scales well with the size of database. Further comparison also demonstrates that while our algorithm achieves approximately the same retrieval precision as other state-of-the-art methods, it cost less time and memory.

Probabilistic modeling of scenes using object frames

In this paper, we propose a probabilistic scene model using object frames, each of which is a group of co-occurring objects with fixed spatial relations. In contrast to standard co-occurrence models, which mostly explore the pairwise co-existence of objects, the proposed model captures the spatial relationship among groups of objects. Such information is closely tied to the semantics of the underlying scenes, which allows us to perform object detection and scene recognition in a unified framework. The proposed probabilistic model has two major components. The first models the dependencies between object frames and objects by adopting the Latent Dirichlet Allocation model for text analysis. The second component characterizes the dependencies between object frames and scenes by establishing a mapping between global image features and object frame distributions. Experimental results show that the induced object frames are both semantically meaningful and spatially consistent. In addition, our model significantly improves the performance of object recognition and scene retrieval.