Showing papers by "Jimei Yang published in 2014"

Salient Color Names for Person Re-identification

Abstract: Color naming, which relates colors with color names, can help people with a semantic analysis of images in many computer vision applications. In this paper, we propose a novel salient color names based color descriptor (SCNCD) to describe colors. SCNCD utilizes salient color names to guarantee that a higher probability will be assigned to the color name which is nearer to the color. Based on SCNCD, color distributions over color names in different color spaces are then obtained and fused to generate a feature representation. Moreover, the effect of background information is employed and analyzed for person re-identification. With a simple metric learning method, the proposed approach outperforms the state-of-the-art performance (without user’s feedback optimization) on two challenging datasets (VIPeR and PRID 450S). More importantly, the proposed feature can be obtained very fast if we compute SCNCD of each color in advance.

Context Driven Scene Parsing with Attention to Rare Classes

Abstract: This paper presents a scalable scene parsing algorithm based on image retrieval and superpixel matching. We focus on rare object classes, which play an important role in achieving richer semantic understanding of visual scenes, compared to common background classes. Towards this end, we make two novel contributions: rare class expansion and semantic context description. First, considering the long-tailed nature of the label distribution, we expand the retrieval set by rare class exemplars and thus achieve more balanced superpixel classification results. Second, we incorporate both global and local semantic context information through a feedback based mechanism to refine image retrieval and superpixel matching. Results on the SIFTflow and LMSun datasets show the superior performance of our algorithm, especially on the rare classes, without sacrificing overall labeling accuracy.

Max-Margin Boltzmann Machines for Object Segmentation

Abstract: We present Max-Margin Boltzmann Machines (MMBMs) for object segmentation. MMBMs are essentially a class of Conditional Boltzmann Machines that model the joint distribution of hidden variables and output labels conditioned on input observations. In addition to image-to-label connections, we build direct image-to-hidden connections to facilitate global shape prediction, and thus derive a simple Iterated Conditional Modes algorithm for efficient maximum a posteriori inference. We formulate a max-margin objective function for discriminative training, and analyze the effects of different margin functions on learning. We evaluate MMBMs using three datasets against state-of-the-art methods to demonstrate the strength of the proposed algorithms.

Labeling objects in image scenes

Abstract: Disclosed are various embodiments labeling objects using multi-scale partitioning, rare class expansion, and/or spatial context techniques. An input image may be partitioned using different scale values to produce a different set of superpixels for each of the different scale values. Potential object labels for superpixels in each different set of superpixels of the input image may be assessed by comparing descriptors of the superpixels in each different set of superpixels of the input image with descriptors of reference superpixels in labeled reference images. An object label may then be assigned for a pixel of the input image based at least in part on the assessing of the potential object labels.