Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors fulfil real time processing, while their accuracies are often criticized. In this paper, we explore an alternative to build a fast and accurate detector by strengthening lightweight features using a hand-crafted mechanism. Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, which takes the relationship between the size and eccentricity of RFs into account, to enhance the feature discriminability and robustness. We further assemble RFB to the top of SSD, constructing the RFB Net detector. To evaluate its effectiveness, experiments are conducted on two major benchmarks and the results show that RFB Net is able to reach the performance of advanced very deep detectors while keeping the real-time speed. Code is available at https://github.com/ruinmessi/RFBNet.

International audienceLocal Binary Patterns (LBP) is a non-parametric descriptor whose aim is to efficiently summarize the local structures of images. In recent years, it has aroused increasing interest in many areas of image processing and computer vision, and has shown its effectiveness in a number of applications, in particular for facial image analysis, including tasks as diverse as face detection, face recognition, facial expression analysis, demographic classification, etc. This paper presents a comprehensive survey of LBP metho-dology including several more recent variations. As a typical ap-plication of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions in dealing with various tasks of facial image analysis are also highlighted

The two underlying requirements of face age progression, i.e. aging accuracy and identity permanence, are not well studied in the literature. In this paper, we present a novel generative adversarial network based approach. It separately models the constraints for the intrinsic subjectspecific characteristics and the age-specific facial changes with respect to the elapsed time, ensuring that the generated faces present desired aging effects while simultaneously keeping personalized properties stable. Further, to generate more lifelike facial details, high-level age-specific features conveyed by the synthesized face are estimated by a pyramidal adversarial discriminator at multiple scales, which simulates the aging effects in a finer manner. The proposed method is applicable to diverse face samples in the presence of variations in pose, expression, makeup, etc., and remarkably vivid aging effects are achieved. Both visual fidelity and quantitative evaluations show that the approach advances the state-of-the-art.

No abstract

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density; (2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors; and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection. However, the inconsistency across different feature scales is a primary limitation for the single-shot detectors based on feature pyramid. In this work, we propose a novel and data driven strategy for pyramidal feature fusion, referred to as adaptively spatial feature fusion (ASFF). It learns the way to spatially filter conflictive information to suppress the inconsistency, thus improving the scale-invariance of features, and introduces nearly free inference overhead. With the ASFF strategy and a solid baseline of YOLOv3, we achieve the best speed-accuracy trade-off on the MS COCO dataset, reporting 38.1% AP at 60 FPS, 42.4% AP at 45 FPS and 43.9% AP at 29 FPS. The code is available at https://github.com/ruinmessi/ASFF.

Compared to enhancers, silencers are notably difficult to identify and validate experimentally. In search for human silencers, we utilized H3K27me3-DNase I hypersensitive site (DHS) peaks with tissue specificity negatively correlated with the expression of nearby genes across 25 diverse cell lines. These regions are predicted to be silencers since they are physically linked, using Hi-C loops, or associated, using expression quantitative trait loci (eQTL) results, with a decrease in gene expression much more frequently than general H3K27me3-DHSs. Also, these regions are enriched for the binding sites of transcriptional repressors (such as CTCF, MECOM, SMAD4, and SNAI3) and depleted of the binding sites of transcriptional activators. Using sequence signatures of these regions, we constructed a computational model and predicted approximately 10,000 additional silencers per cell line and demonstrated that the majority of genes linked to these silencers are expressed at a decreased level. Furthermore, single nucleotide polymorphisms (SNPs) in predicted silencers are significantly associated with disease phenotypes. Finally, our results show that silencers commonly interact with enhancers to affect the transcriptional dynamics of tissue-specific genes and to facilitate fine-tuning of transcription in the human genome.

No abstract