No abstract

We introduce ShadowGAN, a generative adversarial network (GAN) for synthesizing shadows for virtual objects inserted in images. Given a target image containing several existing objects with shadows, and an input source object with a specified insertion position, the network generates a realistic shadow for the source object. The shadow is synthesized by a generator; using the proposed local adversarial and global adversarial discriminators, the synthetic shadow's appearance is locally realistic in shape, and globally consistent with other objects' shadows in terms of shadow direction and area. To overcome the lack of training data, we produced training samples based on public 3D models and rendering technology. Experimental results from a user study show that the synthetic shadowed results look natural and authentic.

This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in dialog systems, namely, 1. Task-oriented dialog Modeling with unstructured knowledge access, 2. Multi-domain task-oriented dialog, 3. Interactive evaluation of dialog, and 4. Situated interactive multi-modal dialog. This paper describes the task definition, provided datasets, baselines and evaluation set-up for each track. We also summarize the results of the submitted systems to highlight the overall trends of the state-of-the-art technologies for the tasks.

Input label map Exemplars Synthetic resultsInput label map Synthetic results ExemplarsInput label map Exemplars Synthetic results → Sketch Face → Pose Dance → Scene parsing Street view Figure 1: We present a generative adversarial framework for synthesizing images from semantic label maps as well as image exemplars. Our synthetic results are photorealistic, semantically consistent to the label maps (facial expression, pose or scene segmentation map) and style-consistent with corresponding exemplars.

Many studies have applied reinforcement learning to train a dialog policy and show great promise these years. One common approach is to employ a user simulator to obtain a large number of simulated user experiences for reinforcement learning algorithms. However, modeling a realistic user simulator is challenging. A rule-based simulator requires heavy domain expertise for complex tasks, and a data-driven simulator requires considerable data and it is even unclear how to evaluate a simulator. To avoid explicitly building a user simulator beforehand, we propose Multi-Agent Dialog Policy Learning, which regards both the system and the user as the dialog agents. Two agents interact with each other and are jointly learned simultaneously. The method uses the actorcritic framework to facilitate pretraining and improve scalability. We also propose Hybrid Value Network for the role-aware reward decomposition to integrate role-specific domain knowledge of each agent in task-oriented dialog. Results show that our method can successfully build a system policy and a user policy simultaneously, and two agents can achieve a high task success rate through conversational interaction.