14 December 2020 in IEEE Transactions on Image Processing
The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters hence unsuitable for mobile devices, while other small memory footprint models follow the spirit of classification network and ignore the inherent characteristic of semantic segmentation. To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation. We first propose the Context Guided (CG) block, which learns the joint feature of both local feature and surrounding context effectively and efficiently, and further improves the joint feature with the global context. Based on the CG block, we develop CGNet which captures contextual information in all stages of the network. CGNet is specially tailored to exploit the inherent property of semantic segmentation and increase the segmentation accuracy. Moreover, CGNet is elaborately designed to reduce the number of parameters and save memory footprint. Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing light-weight segmentation networks. Extensive experiments on Cityscapes and CamVid datasets verify the effectiveness of the proposed approach. Specifically, without any post-processing and multi-scale testing, the proposed CGNet achieves 64.8% mean IoU on Cityscapes with less than 0.5 M parameters.
10 January 2019 in IEEE Transactions on Image Processing
Learning discriminative representations for unseen person images is critical for person re-identification (ReID). Most of the current approaches learn deep representations in classification tasks, which essentially minimize the empirical classification risk on the training set. As shown in our experiments, such representations easily get over-fitted on a discriminative human body part on the training set. To gain the discriminative power on unseen person images, we propose a deep representation learning procedure named part loss network, to minimize both the empirical classification risk on training person images and the representation learning risk on unseen person images. The representation learning risk is evaluated by the proposed part loss, which automatically detects human body parts and computes the person classification loss on each part separately. Compared with traditional global classification loss, simultaneously considering part loss enforces the deep network to learn representations for different body parts and gain the discriminative power on unseen persons. Experimental results on three person ReID datasets, i.e., Market1501, CUHK03 and VIPeR, show that our representation outperforms existing deep representations.
24 June 2019 in IEEE Transactions on Multimedia
Video captioning refers to automatic generate natural language sentences which summarize the video contents. Inspired by the visual attention mechanism of human beings, temporal attention mechanism has been widely used in video description to selectively focus on important frames. However, most existing methods based on temporal attention mechanism suffer from the problems of recognition error and detail missing, because temporal attention mechanism cannot further catch significant regions in frames. In order to address above problems, we propose the use of a novel spatial-temporal attention mechanism (STAT) within an encoder-decoder neural network for video captioning. The proposed STAT successfully takes into account both the spatial and temporal structures in a video, so it makes the decoder to automatically select the significant regions in the most relevant temporal segments for word prediction. We evaluate our STAT on two well-known benchmarks: MSVD and MSR-VTT-10K. Experimental results show that our proposed STAT achieves the state-of-the-art performance with several popular evaluation metrics: BLEU-4, METEOR and CIDEr.
4 October 2017 in IEEE Transactions on Intelligent Transportation Systems
Image content analysis is an important surround perception modality of intelligent vehicles. In order to efficiently recognize the on-road environment based on image content analysis from the large-scale scene database, relevant images retrieval becomes one of the fundamental problems. To improve the efficiency of calculating similarities between images, hashing techniques have received increasing attentions. For most existing hash methods, the suboptimal binary codes are generated, as the hand-crafted feature representation is not optimally compatible with the binary codes. In this paper, a one-stage supervised deep hashing framework (SDHP) is proposed to learn high-quality binary codes. A deep convolutional neural network is implemented, and we enforce the learned codes to meet the following criterions: 1) similar images should be encoded into similar binary codes, and vice versa; 2) the quantization loss from Euclidean space to Hamming space should be minimized; and 3) the learned codes should be evenly distributed. The method is further extended into SDHP+ to improve the discriminative power of binary codes. Extensive experimental comparisons with state-of-the-art hashing algorithms are conducted on CIFAR-10 and NUS-WIDE, the MAP of SDHP reaches to 87.67% and 77.48% with 48 b, respectively, and the MAP of SDHP+ reaches to 91.16%, 81.08% with 12 b, 48 b on CIFAR-10 and NUS-WIDE, respectively. It illustrates that the proposed method can obviously improve the search accuracy.
17 January 2020 in IEEE Transactions on Multimedia
3D layout is crucial for scene understanding and reconstruction, and very useful in applications like real estate and furniture design. In this paper, we propose a fully automatic solution to estimate 3D layout of an indoor scene from a single 2D image. Our technique contains two key components. Firstly, we train a neural network that directly estimates room structure lines from the input image Secondly, we propose a novel technique to automatically identify the layout topology of an input image, followed by a nonlinear optimization with equality constraints to estimate the final 3D layout of a scene. Based on our knowledge, this is the first fully automatic technique to achieve single image-based 3D layout estimation of an indoor scene. We evaluate our method on the public datasets LSUN, Hedau and 3DGP and the results show that the proposed method achieves accurate 3D layout reconstruction on various images with different layout topologies.
18 May 2018 in IEEE Transactions on Multimedia
Uyghur text localization in complex background images is a challenging task and has broad application prospects on many areas. Generally, Uyghur characters in images consist of strokes which have uniform features and are different from background in several aspects, such as color, intensity and texture. Based on this fact, we propose a FASTroke keypoint extractor which is fast and stroke-specific. Compared with the commonly used MSER detector, FASTroke produces two times less components and at lest 10% more characters. Moreover, the characters in a line also have uniform features, for example size, color and stroke width. Consequently, a component similarity based clustering is presented, which does not include componentlevel classification. It brings two benefits, no extra error is imported by component-level classifier and the computation is drastically reduced. The experiments confirm that our method has achieved the best performance on UICBI-500 benchmark dataset.