Predictive learning ideally builds the world model of physical processes in one or more given environments. Typical setups assume that we can collect data from all environments at all times. In practice, however, different prediction tasks may arrive sequentially so that the environments may change persistently throughout the training procedure. Can we develop predictive learning algorithms that can deal with more realistic, non-stationary physical environments? In this paper, we study a new continual learning problem in the context of video prediction, and observe that most existing methods suffer from severe catastrophic forgetting in this setup. To tackle this problem, we propose the continual predictive learning (CPL) approach, which learns a mixture world model via predictive experience replay and performs test-time adaptation with non-parametric task inference. We construct two new benchmarks based on RoboNet and KTH, in which different tasks correspond to different physical robotic environments or human actions. Our approach is shown to effectively mitigate forgetting and remarkably outperform the naíve combinations of previous art in video prediction and continual learning.

Recent advances in image inpainting have shown impressive results for generating plausible visual details on rather simple backgrounds. However, for complex scenes, it is still challenging to restore reasonable contents as the contextual information within the missing regions tends to be ambiguous. To tackle this problem, we introduce pretext tasks that are semantically meaningful to estimating the missing contents. In particular, we perform knowledge distillation on pretext models and adapt the features to image inpainting. The learned semantic priors ought to be partially invariant between the high-level pretext task and low-level image inpainting, which not only help to understand the global context but also provide structural guidance for the restoration of local textures. Based on the semantic priors, we further propose a context-aware image inpainting model, which adaptively integrates global semantics and local features in a unified image generator. The semantic learner and the image generator are trained in an end-to-end manner. We name the model SPL to highlight its ability to learn and leverage semantic priors. It achieves the state of the art on Places2, CelebA, and Paris StreetView datasets

We present a practical and effective method for human action transfer. Given a sequence of source action and limited target information, we aim to transfer motion from source to target. Although recent works based on GAN or VAE achieved impressive results for action transfer in 2D, there still exists a lot of problems which cannot be avoided, such as distorted and discontinuous human body shape, blurry cloth texture and so on. In this paper, we try to solve these problems in a novel 3D viewpoint. On the one hand, we design a skeleton-to-3D-mesh generator to generate the 3D model, which achieves huge improvement on appearance reconstruction. Furthermore, we add a temporal connection to improve the smoothness of the model. On the other hand, instead of directly utilizing the image in RGB space, we transform the target appearance information into UV space for further pose transformation. Specially, unlike conventional graphics render method directly projects visible pixels to UV space, our transformation is according to pixel’s semantic information. We perform experiments on Human3.6M and HumanEva-I to evaluate the performance of pose generator. Both qualitative and quantitative results show that our method outperforms methods based on generation method in 2D. Additionally, we compare our render method with graphic methods on Human3.6M and People-snapshot. The comparison results show that our render method is more robust and effective.

Person re-identification has achieved great progress with deep convolutional neural networks. However, most previous methods focus on learning individual appearance feature embedding, and it is hard for the models to handle difficult situations with different illumination, large pose variance and occlusion. In this work, we take a step further and consider employing context information for person search. For a probe-gallery pair, we first propose a contextual instance expansion module, which employs a relative attention module to search and filter useful context information in the scene. We also build a graph learning framework to effectively employ context pairs to update target similarity. These two modules are built on top of a joint detection and instance feature learning framework, which improves the discriminativeness of the learned features. The proposed framework achieves state-of-the-art performance on two widely used person search datasets.

Video generation is a challenging task due to the extremely high-dimensional distribution of the solution space. Good constraints in the solution domain would thus reduce the difficulty of approximating optimal solutions. In this paper, instead of directly generating high-dimensional video data, we propose using object landmarks as explicit structure constraints to address this issue. Specifically, we propose a two-stage framework for an action-conditioned video generation task. In our framework, the first stage aims to generate landmark sequences according to predefined motion types, and a recurrent model (RNN/LSTM) is adopted for this purpose. The landmark sequence can be regarded as a low-dimensional structure embedding of high-dimensional video data, and generating landmark sequences is much easier than generating videos. The second stage is inspired by a conditional generative adversarial network (CGAN), and we take the generated landmark sequence as a structure condition to learn a landmark-to-image translation network. Such a one-to-one translation framework avoids the difficulty of generating videos and instead transfers the video generation task to image generation, which is resolvable due to the maturity of current GAN-based models. The experimental results demonstrate that our model not only achieves promising results on rigid/nonrigid motion generation tasks but also can be extended to multiobject motion situations.

Key to automatically generate natural scene images is to properly arrange amongst various spatial elements, especially in the depth cue. To this end, we introduce a novel depth structure preserving scene image generation network (DSP-GAN), which favors a hierarchical architecture, for the purpose of depth structure preserving scene image generation. The main trunk of the proposed infrastructure is built upon a Hawkes point process that models high-order spatial dependency between different depth layers. Within each layer generative adversarial sub-networks are trained collaboratively to generate realistic scene components, conditioned on the layer information produced by the point process. We experiment our model on annotated natural scene images collected from SUN dataset and demonstrate that our models are capable of generating depth-realistic natural scene image.

This work makes the first attempt to generate articulated human motion sequence from a single image. On one hand, we utilize paired inputs including human skeleton information as motion embedding and a single human image as appearance reference, to generate novel motion frames based on the conditional GAN infrastructure. On the other hand, a triplet loss is employed to pursue appearance smoothness between consecutive frames. As the proposed framework is capable of jointly exploiting the image appearance space and articulated/kinematic motion space, it generates realistic articulated motion sequence, in contrast to most previous video generation methods which yield blurred motion effects. We test our model on two human action datasets including KTH and Human3.6M, and the proposed framework generates very promising results on both datasets.