“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

Hand gesture serves as a crucial role during the expression of sign language. Current deep learning based methods for sign language understanding (SLU) are prone to over-fitting due to insufficient sign data resource and suffer limited interpretability. In this paper, we propose the first self-supervised pre-trainable SignBERT+ framework with model-aware hand prior incorporated. In our framework, the hand pose is regarded as a visual token, which is derived from an off-the-shelf detector. Each visual token is embedded with gesture state and spatial-temporal position encoding. To take full advantage of current sign data resource, we first perform self-supervised learning to model its statistics. To this end, we design multi-level masked modeling strategies (joint, frame and clip) to mimic common failure detection cases. Jointly with these masked modeling strategies, we incorporate model-aware hand prior to better capture hierarchical context over the sequence. After the pre-training, we carefully design simple yet effective prediction heads for downstream tasks. To validate the effectiveness of our framework, we perform extensive experiments on three main SLU tasks, involving isolated and continuous sign language recognition (SLR), and sign language translation (SLT). Experimental results demonstrate the effectiveness of our method, achieving new state-of-the-art performance with a notable gain.

SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding

A new video frame interpolation technique is proposed in this paper.We first use the classical motion compensation interpolation (MCI), but only for motion vectors (MVs) marked as reliable in our classification procedure. To fill in the regions where no such MV is available, we proposed a novel 3-D total variation regularized completion model, which exploits both temporal and spatial smoothness among video frames. Experiments demonstrate its superior performance compared to several classical methods, both in visual quality and PSNR values, while the typical artifacts are significantly reduced.

Video frame interpolation using 3-D total variation regularized completion

In recent years, tremendous efforts have been made on document image rectification, but existing advanced algorithms are limited to processing restricted document images, i.e., the input images must incorporate a complete document. Once the captured image merely involves a local text region, its rectification quality is degraded and unsatisfactory. Our previously proposed DocTr, a transformer-assisted network for document image rectification, also suffers from this limitation. In this work, we present DocTr++, a novel unified framework for document image rectification, without any restrictions on the input distorted images. Our major technical improvements can be concluded in three aspects. Firstly, we upgrade the original architecture by adopting a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing. Secondly, we reformulate the pixel-wise mapping relationship between the unrestricted distorted document images and the distortion-free counterparts. The obtained data is used to train our DocTr++ for unrestricted document image rectification. Thirdly, we contribute a real-world test set and metrics applicable for evaluating the rectification quality. To our best knowledge, this is the first learning-based method for the rectification of unrestricted document images. Extensive experiments are conducted, and the results demonstrate the effectiveness and superiority of our method. We hope our DocTr++ will serve as a strong baseline for generic document image rectification, prompting the further advancement and application of learning-based algorithms. The source code and the proposed dataset are publicly available at https://github.com/fh2019ustc/DocTr-Plus.

Deep Unrestricted Document Image Rectification

Recent years have witnessed the popularity of Convolutional Neural Networks (CNN) in a variety of computer vision tasks, including video object tracking. Existing object tracking methods with CNN employ either a scalar score or a confidence map as CNN’s output, which suffer the infeasibility of estimating the object’s accurate scale and rotation angle. Specifically, as with other traditional methods, they assume the targets’ scale aspect ratio and rotation angle are fixed. To address the limitation, we propose to take a binary mask as the output of CNN for tracking. To this end, we adapt a semantic segmentation model by online fine-tuning with augmented samples in the initial frame to uncover the target in the following frames. During the generation of training samples, we employ a Crop and Paste method to better utilize context information, add a random value to lightness component to mimic the illumination change, and take a Gaussian filtering approach to mimic the blur. During the tracking, due to the limitation of CNN’s receptive field size and spatial resolution, the network may fail to identify the target if the estimated bounding box is considerably incorrect. Therefore we propose a bounding box approximation method by considering temporal consistency. Excluding the initial training cost, our tracker runs at 41 FPS on a single GeForce 1080Ti GPU. Evaluated on benchmarks including OTB-2015, VOT-2016 and TempleColor, it achieves comparable results with non real-time top trackers and state-of-the-art performance among those real-time ones.

Exploiting weak mask representation with convolutional neural networks for accurate object tracking

Conventionally, the reference image for image quality assessment (IQA) is completely available (full-reference IQA) or unavailable (no-reference IQA). Even for reduced-reference IQA, the features that are used to predict image quality are still extracted from the pristine reference image. However, the pristine reference image is always unavailable in many real scenarios. In contrast, it is convenient to obtain a number of similar reference images via retrieval from the Internet. These similar reference images may share similar contents and scenes with the image to be assessed. In this paper, we attempt to discuss the image quality assessment problem from the view of similar images, i.e. similar reference IQA. Although the similar reference images share similar contents with the degraded image, the difference between them still cannot be ignored. Therefore, we propose an IQA framework based on local feature matching, which can help to identify the similar regions and structures. Then the IQA features are computed only from these similar regions to predict the final image quality score. Besides, since there is no IQA databases for the similar reference IQA problem, we establish a novel IQA database that consists of 272 images from four scenes. The experiments demonstrate that the performance of our scheme goes beyond state-of-the-art no-reference IQA methods and some full-reference IQA algorithms.

Houqiang Li

Papers

SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding

Video frame interpolation using 3-D total variation regularized completion

Deep Unrestricted Document Image Rectification

Exploiting weak mask representation with convolutional neural networks for accurate object tracking

Similar Reference Image Quality Assessment: A New Database and A Trial with Local Feature Matching