“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

This paper contributes a new high quality dataset for person re-identification, named "Market-1501". Generally, current datasets: 1) are limited in scale, 2) consist of hand-drawn bboxes, which are unavailable under realistic settings, 3) have only one ground truth and one query image for each identity (close environment). To tackle these problems, the proposed Market-1501 dataset is featured in three aspects. First, it contains over 32,000 annotated bboxes, plus a distractor set of over 500K images, making it the largest person re-id dataset to date. Second, images in Market-1501 dataset are produced using the Deformable Part Model (DPM) as pedestrian detector. Third, our dataset is collected in an open system, where each identity has multiple images under each camera. As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor. We view person re-identification as a special task of image search. In experiment, we show that the proposed descriptor yields competitive accuracy on VIPeR, CUHK03, and Market-1501 datasets, and is scalable on the large-scale 500k dataset.

/pdf/scalable-person-re-identification-a-benchmark-iiee63lja2.pdf

Scalable Person Re-identification: A Benchmark

The author's preface gives an outline: "This book is about weakconvergence methods in metric spaces, with applications sufficient to show their power and utility. The Introduction motivates the definitions and indicates how the theory will yield solutions to problems arising outside it. Chapter 1 sets out the basic general theorems, which are then specialized in Chapter 2 to the space C[0, l ] of continuous functions on the unit interval and in Chapter 3 to the space D [0, 1 ] of functions with discontinuities of the first kind. The results of the first three chapters are used in Chapter 4 to derive a variety of limit theorems for dependent sequences of random variables. " The book develops and expands on Donsker's 1951 and 1952 papers on the invariance principle and empirical distributions. The basic random variables remain real-valued although, of course, measures on C[0, l ] and D[0, l ] are vitally used. Within this framework, there are various possibilities for a different and apparently better treatment of the material. More of the general theory of weak convergence of probabilities on separable metric spaces would be useful. Metrizability of the convergence is not brought up until late in the Appendix. The close relation of the Prokhorov metric and a metric for convergence in probability is (hence) not mentioned (see V. Strassen, Ann. Math. Statist. 36 (1965), 423-439; the reviewer, ibid. 39 (1968), 1563-1572). This relation would illuminate and organize such results as Theorems 4.1, 4.2 and 4.4 which give isolated, ad hoc connections between weak convergence of measures and nearness in probability. In the middle of p. 16, it should be noted that C*(S) consists of signed measures which need only be finitely additive if 5 is not compact. On p. 239, where the author twice speaks of separable subsets having nonmeasurable cardinal, he means "discrete" rather than "separable." Theorem 1.4 is Ulam's theorem that a Borel probability on a complete separable metric space is tight. Theorem 1 of Appendix 3 weakens completeness to topological completeness. After mentioning that probabilities on the rationals are tight, the author says it is an

Convergence of probability measures

Recent advances in convolutional neural networks

The PASCAL Visual Object Classes Challenge

This paper investigates the joint source-channel coding problem of sending a memoryless source over a memoryless degraded broadcast channel. An inner bound and an outer bound on the achievable distortion region are derived, which respectively generalize and unify several existing bounds. Moreover, when specialized to Gaussian source broadcast or binary source broadcast, the inner bound and outer bound could recover the best known inner bound and outer bound in the literature. Besides, the inner bound and outer bound are also extended to Wyner-Ziv source broadcast problem, i.e., source broadcast with degraded side information available at decoders. Some new bounds are obtained when specialized to Wyner-Ziv Gaussian case and Wyner-Ziv binary case.

Distortion bounds for source broadcast over degraded channel

Currently Web image search is mostly implemented as text retrieval based on the textual information extracted from the Web page associated with the image. Since the text in the Web page may not match with the image content, image search re-ranking is preferable to refine the text-based search results. In this paper, we propose a novel scheme of latent visual context analysis (LVCA) for image re-ranking. The latent visual context is explored in both latent semantic context and visual link graphs. We argue that the image significance is determined by its contained visual word context, which is analyzed through Latent Semantic Analysis (LSA) and visual word link graph. With the visual word context information, the image context is explored by analysis of image link graph and the significance value for each image can be inferred by VisualRank. In both visual word link graph and image link graph, latent-layer will be incorporated to effectively discover the visual context. We validate our approach on text-query based search results returned by Google Image. Experimental results show improvement of both accuracy and efficiency of our method over the state-of-the-art VisualRank algorithm.

/pdf/latent-visual-context-analysis-for-image-re-ranking-cmsvi1v4et.pdf

Latent visual context analysis for image re-ranking

The emerging MVC+D standard specifies the coding of Multiview Video plus Depth (MVD) data for enabling advanced 3D video applications. MVC+D specifications define the coding of all views of MVD at equal spatial resolution and apply a conventional MVC technique for coding the multiview texture and the depth independently. This paper presents a modified MVC+D coding scheme, where only the base view is coded at the original resolution whereas dependent views are coded at reduced resolution. To enable inter-view prediction, the base view is downsampled within the MVC coding loop to provide a relevant reference for dependent views. At the decoder side, the proposed scheme consists of a post-processing scheme which upsamples of the decoded views to their original resolution. The proposed scheme is compared against the original MVC+D scheme and an average of 4% delta bitrate reduction (dBR) in the coded views and 14.5% of dBR in the synthesized views are reported.

Coding of mixed-resolution multiview video in 3D video application

In this paper, we propose a low complexity lossless compression scheme for multispectral images based on distributed coding. Data decorrelation operations are moved to decoder on the ground in order to design a lightweight yet very efficient encoder suitable for onboard applications. The decoder with abundant resources will perform spectral-spatial adaptive fuzzy prediction to generate high quality side information for distributed coding by capturing the spatially varying spectral correlation. The LDPC decoding is integrated with Markov random field (MRF) modeling aiming at joint exploitation of spectral correlation and spatial correlation. Simulations have been carried out to demonstrate that the proposed scheme is able to provide competitive performance with respect to the state-of-the-art 3D DPCM technique but with significantly lower encoding complexity.

Distributed coding techniques for onboard lossless compression of multispectral images

The support for region of interest (ROI) browsing, which allows dropping background part of video bitstreams, is a desirable feature for video applications. With the help of the slice group technique provided by H.264/SVC, rectangular ROI areas can be encoded into separate ROI slices. Additionally, by imposing certain constraints on motion estimation, ROI part of the bitstream can be decoded without background slices of the same layer. However, due to the additional spatial and temporal constraints applied to the encoder, overall coding efficiency would be significantly decreased. In this paper, a rate-distortion optimized (RDO) encoding scheme is proposed to improve the coding efficiency of ROI slices. When background slices are discarded, the proposed method uses base layer information to generate the prediction signal of the enhancement layer. Thus, the temporal constraints can be loosened during the encoding process. To do it in this way, the possible mismatch between generated reference frames and original ones is also considered during rate-distortion optimization so that a reasonable trade-off between coding efficiency and decoding drift can be made. Besides, a new Lagrange multiplier derivation method is developed for further coding performance improvement. Experimental results demonstrate that the proposed method achieves significant bitrate saving compared to existing methods.

/pdf/a-rate-distortion-optimized-coding-method-for-region-of-4lv9p18lyx.pdf

Houqiang Li

Papers

Distortion bounds for source broadcast over degraded channel

Latent visual context analysis for image re-ranking

Coding of mixed-resolution multiview video in 3D video application

Distributed coding techniques for onboard lossless compression of multispectral images

A rate-distortion optimized coding method for region of interest in scalable video coding