Exemplar-based models have achieved great success on localizing the parts of semi-rigid objects. However, their efficacy on highly articulated objects such as humans is yet to be explored. Inspired by hierarchical object representation and recent application of Deep Convolutional Neural Networks (DCNNs) on human pose estimation, we propose a novel formulation that incorporates both hierarchical exemplar-based models and DCNNs in the spatial terms. Specifically, we obtain more expressive spatial models by assuming independence between exemplars at different levels in the hierarchy; we also obtain stronger spatial constraints by inferring the spatial relations between parts at the same level. As our method strikes a good balance between expressiveness and strength of spatial models, it is both effective and generalizable, achieving state-of-the-art results on different benchmarks: Leeds Sports Dataset and CUB-200-2011.

We address the problem of large-scale fine-grained visual categorization, describing new methods we have used to produce an online field guide to 500 North American bird species. We focus on the challenges raised when such a system is asked to distinguish between highly similar species of birds. First, we introduce "one-vs-most classifiers." By eliminating highly similar species during training, these classifiers achieve more accurate and intuitive results than common one-vs-all classifiers. Second, we show how to estimate spatio-temporal class priors from observations that are sampled at irregular and biased locations. We show how these priors can be used to significantly improve performance. We then show state-of-the-art recognition performance on a new, large dataset that we make publicly available. These recognition methods are integrated into the online field guide, which is also publicly available.

In this paper, we propose a novel approach for bird part localization, targeting fine-grained categories with wide variations in appearance due to different poses (including aspect and orientation) and subcategories. As it is challenging to represent such variations across a large set of diverse samples with tractable parametric models, we turn to individual exemplars. Specifically, we extend the exemplar-based models in [4] by enforcing pose and subcategory consistency at the parts. During training, we build pose-specific detectors scoring part poses across subcategories, and subcategory-specific detectors scoring part appearance across poses. At the testing stage, likely exemplars are matched to the image, suggesting part locations whose pose and subcategory consistency are well-supported by the image cues. From these hypotheses, part configuration can be predicted with very high accuracy. Experimental results demonstrate significant performance gains from our method on an extensive dataset: CUB-200-2011 [30], for both localization and classification tasks.

We propose the theory of image neighborhood processing which includes algorithm, storage and processing for parallel image data. Its core idea lies in the identity and parallelism of data structures used by software algorithm, memory and processing unit. This theory solves the problem of frame data flow which is the bottleneck of high speed image processing. In this paper, we discuss the storage structure using incomplete rotate matrix and its corresponding processing unit. Based on the theory of image neighborhood processing, we have developed NIPC-3 neighborhood image parallel computer, providing parallel access to very large neighborhood image. The largest size of neighborhood core is 25 × 24 and the peak speed of neighborhood computing reaches 135 billion multiplication-accumulation operations per second. Experimental results show that NIPC-3 enables much faster implementation for low level processing and can be utilized by more complex algorithms.