Gait recognition aims to identify users by their walking patterns. Compared with appearance-based methods, skeleton-based methods exhibit well robustness to cluttered backgrounds, carried items, and clothing variations. However, skeleton extraction faces the wrong human tracking and keypoints missing problems, especially under multiperson scenarios. To address above issues, this article proposes a novel gait recognition method using deep neural network specifically designed for multiperson scenarios. The method consists of individual gait separate module (IGSM) and fuzzy skeleton completion network (FU-SCN). To achieve effective human tracking, IGSM employs root–skeleton keypoints predictions and object keypoint similarity (OKS)-based skeleton calculation to separate individual gait sets when multiple persons exist. In addition, keypoints missing renders human poses estimation fuzzy. We propose FU-SCN, a deep neuro-fuzzy network, to enhances the interpretability of the fuzzy pose estimation via generating fine-grained gait representation. FU-SCN utilizes fuzzy bottleneck structure to extract features on low-dimension keypoints, and multiscale fusion to extract dissimilar relations of human body during walking on each scale. Extensive experiments are conducted on the CASIA-B dataset and our multigait dataset. The results show that our method is one of the SOTA methods and shows outperformance under complex scenarios. Compared with PTSN, PoseMapGait, JointsGait, GaitGraph2, and CycleGait, our method achieves an average accuracy improvement of 53.77%, 42.07%, 25.3%, 13.47%, and 9.5%, respectively, and it keeps low time cost with average 180 ms using edge devices.

Lossy image compression is a fundamental technology in media transmission and storage. Variable-rate approaches have recently gained much attention to avoid the usage of a set of different models for compressing images at different rates. During the media sharing, multiple re-encodings with different rates would be inevitably executed. However, existing Variational Autoencoder (VAE)-based approaches would be readily corrupted in such circumstances, resulting in the occurrence of strong artifacts and the destruction of image fidelity. Based on the theoretical findings of preserving image fidelity via invertible transformation, we aim to tackle the issue of high-fidelity fine variable-rate image compression and thus propose the Invertible Continuous Codec (I2C). We implement the I2C in a mathematical invertible manner with the core Invertible Activation Transformation (IAT) module. I2C is constructed upon a single-rate Invertible Neural Network (INN) based model and the quality level (QLevel) would be fed into the IAT to generate scaling and bias tensors. Extensive experiments demonstrate that the proposed I2C method outperforms state-of-the-art variable-rate image compression methods by a large margin, especially after multiple continuous re-encodings with different rates, while having the ability to obtain a very fine variable-rate control without any performance compromise.

Collecting labeled data for the task of semantic segmentation is expensive and time-consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural Network (CNN) based semantic segmentation approaches have achieved impressive results by using large amounts of labeled training data, their performance drops significantly as the amount of labeled data decreases. This happens because deep CNNs trained with the de facto cross-entropy loss can easily overfit to small amounts of labeled data. To address this issue, we propose a simple and effective contrastive learning-based training strategy in which we first pretrain the network using a pixel-wise, label-based contrastive loss, and then fine-tune it using the cross-entropy loss. This approach increases intra-class compactness and inter-class separability, thereby resulting in a better pixel classifier. We demonstrate the effectiveness of the proposed training strategy using the Cityscapes and PASCAL VOC 2012 segmentation datasets. Our results show that pretraining with the proposed contrastive loss results in large performance gains (more than 20% absolute improvement in some settings) when the amount of labeled data is limited. In many settings, the proposed contrastive pretraining strategy, which does not use any additional data, is able to match or outperform the widely-used ImageNet pretraining strategy that uses more than a million additional labeled images.

Many emerging applications of intelligent robots need to explore and understand new environments, where it is desirable to detect objects of novel classes on the fly with minimum online efforts. This is an object detection on demand (ODOD) task. It is challenging, because it is impossible to annotate a large number of data on the fly, and the embedded systems are usually unable to perform back-propagation which is essential for training. Most existing few-shot detection methods are confronted here as they need extra training. We propose a novel morphable detector (MD), that simply "morphs" some of its changeable parameters online estimated from the few samples, so as to detect novel classes without any extra training. The MD has two sets of parameters, one for the feature embedding and the other for class representation (called "prototypes"). Each class is associated with a hidden prototype to be learned by integrating the visual and semantic embeddings. The learning of the MD is based on the alternate learning of the feature embedding and the prototypes in an EM-like approach which allows the recovery of an unknown prototype from a few samples of a novel class. Once an MD is learned, it is able to use a few samples of a novel class to directly compute its prototype to fulfill the online morphing process. We have shown the superiority of the MD in Pascal [12], COCO [27] and FSOD [13] datasets.

Recognizing the attributes of objects and their parts is central to many computer vision applications. Although great progress has been made to apply object-level recognition, recognizing the attributes of parts remains less applicable since the training data for part attributes recognition is usually scarce especially for internet-scale applications. Furthermore, most existing part attribute recognition methods rely on the part annotations which are more expensive to obtain. In order to solve the data insufficiency problem and get rid of dependence on the part annotation, we introduce a novel Concept Sharing Network (CSN) for part attribute recognition. A great advantage of CSN is its capability of recognizing the part attribute (a combination of part location and appearance pattern) that has insufficient or zero training data, by learning the part location and appearance pattern respectively from the training data that usually mix them in a single label. Extensive experiments on CUB, Celeb A, and a newly proposed human attribute dataset demonstrate the effectiveness of CSN and its advantages over other methods, especially for the attributes with few training samples. Further experiments show that CSN can also perform zero-shot part attribute recognition.

Heatmap regression-based models have significantly advanced the progress of facial landmark detection. However, the lack of structural constraints always generates inaccurate heatmaps resulting in poor landmark detection performance. While hierarchical structure modeling methods have been proposed to tackle this issue, they all heavily rely on manually designed tree structures. The designed hierarchical structure is likely to be completely corrupted due to the missing or inaccurate prediction of landmarks. To the best of our knowledge, in the context of deep learning, no work before has investigated how to automatically model proper structures for facial landmarks, by discovering their inherent relations. In this paper, we propose a novel Hierarchical Structured Landmark Ensemble (HSLE) model for learning robust facial landmark detection, by using it as the structural constraints. Different from existing approaches of manually designing structures, our proposed HSLE model is constructed automatically via discovering the most robust patterns so HSLE has the ability to robustly depict both local and holistic landmark structures simultaneously. Our proposed HSLE can be readily plugged into any existing facial landmark detection baselines for further performance improvement. Extensive experimental results demonstrate our approach significantly outperforms the baseline by a large margin to achieve a state-of-the-art performance.

In this work, we present a novel and effective framework to facilitate object detection with the instance-level segmentation information that is only supervised by bounding box annotation. Starting from the joint object detection and instance segmentation network, we propose to recursively estimate the pseudo ground-truth object masks from the instance-level object segmentation network training, and then enhance the detection network with top-down segmentation feedbacks. The pseudo ground truth mask and network parameters are optimized alternatively to mutually benefit each other. To obtain the promising pseudo masks in each iteration, we embed a graphical inference that incorporates the low-level image appearance consistency and the bounding box annotations to refine the segmentation masks predicted by the segmentation network. Our approach progressively improves the object detection performance by incorporating the detailed pixel-wise information learned from the weakly-supervised segmentation network. Extensive evaluation on the detection task in PASCAL VOC 2007 and 2012 [12] verifies that the proposed approach is effective.

In this paper, we propose to use image blurriness to estimate the depth map for underwater image enhancement. It is based on the observation that objects farther from the camera are more blurry for underwater images. Adopting image blurriness with the image formation model (IFM), we can estimate the distance between scene points and the camera and thereby recover and enhance underwater images. Experimental results on enhancing such images in different lighting conditions demonstrate the proposed method performs better than other IFM-based enhancement methods.