High-quality image inpainting requires filling missing regions in a damaged image with plausible content. Existing works either fill the regions by copying image patches or generating semantically-coherent patches from region context, while neglect the fact that both visual and semantic plausibility are highly-demanded. In this paper, we propose a Pyramid-context ENcoder Network (PEN-Net) for image inpainting by deep generative models. The PEN-Net is built upon a U-Net structure, which can restore an image by encoding contextual semantics from full resolution input, and decoding the learned semantic features back into images. Specifically, we propose a pyramid-context encoder, which progressively learns region affinity by attention from a high-level semantic feature map and transfers the learned attention to the previous low-level feature map. As the missing content can be filled by attention transfer from deep to shallow in a pyramid fashion, both visual and semantic coherence for image inpainting can be ensured. We further propose a multi-scale decoder with deeply-supervised pyramid losses and an adversarial loss. Such a design not only results in fast convergence in training, but more realistic results in testing. Extensive experiments on various datasets show the superior performance of the proposed network
Image captioning has received significant attention with remarkable improvements in recent advances. Nevertheless, images in the wild encapsulate rich knowledge and cannot be sufficiently described with models built on image-caption pairs containing only in-domain objects. In this paper, we propose to address the problem by augmenting standard deep captioning architectures with object learners. Specifically, we present Long Short-Term Memory with Pointing (LSTM-P) --- a new architecture that facilitates vocabulary expansion and produces novel objects via pointing mechanism. Technically, object learners are initially pre-trained on available object recognition data. Pointing in LSTM-P then balances the probability between generating a word through LSTM and copying a word from the recognized objects at each time step in decoder stage. Furthermore, our captioning encourages global coverage of objects in the sentence. Extensive experiments are conducted on both held-out COCO image captioning and ImageNet datasets for describing novel objects, and superior results are reported when comparing to state-of-the-art approaches. More remarkably, we obtain an average of 60.9% in F1 score on held-out COCO~dataset.
Previous works have shown that face recognition with high accuracy 3D data is more reliable and insensitive to pose and light variations. Recently, low-cost and portable 3D acquisition techniques like ToF(Time of Flight) and DoE based structured light enable us to access 3D data easily, e.g. via a mobile phone. However, these devices can only provide sparse(limited speckles in structured light system) and noisy 3D data which can not support face recognition directly. In this paper, we aim at achieving high performance face recognition for devices equipped with such modules which is very meaningful in practice as such devices will be very popular. We propose a framework to perform face recognition by fusing a sequence of low-quality 3D data. As 3D data are sparse and noisy which can not be well handled by conventional methods like the ICP algorithm, we design a PointNet-like Deep Registration Network(DRNet) which works with ordered 3D point coordinates while preserving the ability of mining local structures via convolution. Meanwhile we develop a novel loss function to optimize our DRNet based on the quaternion expression which obviously outperforms other widely used functions. For face recognition, we design a deep convolutional network which takes the fused 3D depth-map as input based on AMSoftmax model. Experiments show that our DRNet can achieve rotation error 0.95 degrees and translation error 0.28mm for registration. The face recognition on fused data also achieves rank-1 accuracy 99.2%, FAR-0.001 97.5% on Bosphorus dataset which is comparable with state-of-the-art high-quality data based recognition performance.
Automatically describing a video with natural language is regarded as a fundamental challenge in computer vision. The problem nevertheless is not trivial especially when a video contains multiple events to be worthy of mention, which often happens in real videos. A valid question is how to temporally localize and then describe events, which is known as "dense video captioning." In this paper, we present a novel framework for dense video captioning that unifies the localization of temporal event proposals and sentence generation of each proposal, by jointly training them in an end-to-end manner. To combine these two worlds, we integrate a new design, namely descriptiveness regression, into a single shot detection structure to infer the descriptive complexity of each detected proposal via sentence generation. This in turn adjusts the temporal locations of each event proposal. Our model differs from existing dense video captioning methods since we propose a joint and global optimization of detection and captioning, and the framework uniquely capitalizes on an attribute-augmented video captioning architecture. Extensive experiments are conducted on ActivityNet Captions dataset and our framework shows clear improvements when compared to the state-of-the-art techniques. More remarkably, we obtain a new record: METEOR of 12.96% on ActivityNet Captions official test set.
We consider the compression artifacts reduction problem, where a compressed image is transformed into an artifact-free image. Recent approaches for this problem typically train a one-to-one mapping using a per-pixel $L_2$ loss between the outputs and the ground-truths. We point out that these approaches used to produce overly smooth results, and PSNR doesn't reflect their real performance. In this paper, we propose a one-to-many network, which measures output quality using a perceptual loss, a naturalness loss, and a JPEG loss. We also avoid grid-like artifacts during deconvolution using a "shift-and-average" strategy. Extensive experimental results demonstrate the dramatic visual improvement of our approach over the state of the arts.
Training data are critical in face recognition systems. However, labeling a large scale face data for a particular domain is very tedious. In this paper, we propose a method to automatically and incrementally construct datasets from massive weakly labeled data of the target domain which are readily available on the Internet under the help of a pretrained face model. More specifically, given a large scale weakly labeled dataset in which each face image is associated with a label, i.e. the name of an identity, we create a graph for each identity with edges linking matched faces verified by the existing model under a tight threshold. Then we use the maximal subgraph as the cleaned data for that identity. With the cleaned dataset, we update the existing face model and use the new model to filter the original dataset to get a larger cleaned dataset. We collect a large weakly labeled dataset containing 530,560 Asian face images of 7,962 identities from the Internet, which will be published for the study of face recognition. By running the filtering process, we obtain a cleaned datasets (99.7+% purity) of size 223,767 (recall 70.9%). On our testing dataset of Asian faces, the model trained by the cleaned dataset achieves recognition rate 93.1%, which obviously outperforms the model trained by the public dataset CASIA whose recognition rate is 85.9%.
Deep models have achieved impressive performance for face hallucination tasks. However, we observe that directly feeding the hallucinated facial images into recog- nition models can even degrade the recognition performance despite the much better visualization quality. In this paper, we address this problem by jointly learning a deep model for two tasks, i.e. face hallucination and recognition. In particular, we design an end-to-end deep convolution network with hallucination sub-network cascaded by recognition sub-network. The recognition sub- network are responsible for producing discriminative feature representations using the hallucinated images as inputs generated by hallucination sub-network. During training, we feed LR facial images into the network and optimize the parameters by minimizing two loss items, i.e. 1) face hallucination loss measured by the pixel wise difference between the ground truth HR images and network-generated images; and 2) verification loss which is measured by the classification error and intra-class distance. We extensively evaluate our method on LFW and YTF datasets. The experimental results show that our method can achieve recognition accuracy 97.95% on 4x down-sampled LFW testing set, outperforming the accuracy 96.35% of conventional face recognition model. And on the more challenging YTF dataset, we achieve recognition accuracy 90.65%, a margin over the recognition accuracy 89.45% obtained by conventional face recognition model on the 4x down-sampled version.
Identifying the same individual across different scenes is an important yet difficult task in intelligent video surveillance. Its main difficulty lies in how to preserve similarity of the same person against large appearance and structure variation while discriminating different individuals. In this paper, we present a scalable distance driven feature learning framework based on the deep neural network for person re-identification, and demonstrate its effectiveness to handle the existing challenges. Specifically, given the training images with the class labels (person IDs), we first produce a large number of triplet units, each of which contains three images, i.e. one person with a matched reference and a mismatched reference. Treating the units as the input, we build the convolutional neural network to generate the layered representations, and follow with the $L2$ distance metric. By means of parameter optimization, our framework tends to maximize the relative distance between the matched pair and the mismatched pair for each triplet unit. Moreover, a nontrivial issue arising with the framework is that the triplet organization cubically enlarges the number of training triplets, as one image can be involved into several triplet units. To overcome this problem, we develop an effective triplet generation scheme and an optimized gradient descent algorithm, making the computational load mainly depends on the number of original images instead of the number of triplets. On several challenging databases, our approach achieves very promising results and outperforms other state-of-the-art approaches.