StyleCLIP with bangs double chin black hair with wrinkles pale* The work was done during Zipeng Xu's internship at VIS, Baidu.

Original Ours StyleCLIP with bangs double chin black hair with wrinkles pale Figure 1. Comparisons on disentangled image manipulation between the StyleCLIP [30] baseline and our Predict, Prevent, and Evaluate (PPE). Ours manages to manipulate only the command-attribute (as indicated under each column) while remaining unchanged to the others.

Considering the importance of building a good Visual Dialog (VD) Questioner, many researchers study the topic under a Q-Bot-A-Bot image-guessing game setting, where the Questioner needs to raise a series of questions to collect information of an undisclosed image. Despite progress has been made in Supervised Learning (SL) and Reinforcement Learning (RL), issues still exist. Firstly, previous methods do not provide explicit and effective guidance for Questioner to generate visually related and informative questions. Secondly, the effect of RL is hampered by an incompetent component, i.e., the Guesser, who makes image predictions based on the generated dialogs and assigns rewards accordingly. To enhance VD Questioner: 1) we propose a Related entity enhanced Questioner (ReeQ) that generates questions under the guidance of related entities and learns entity-based questioning strategy from human dialogs; 2) we propose an Augmented Guesser (AugG) that is strong and is optimized for the VD setting especially. Experimental results on the VisDial v1.0 dataset show that our approach achieves state-of-theart performance on both image-guessing task and question diversity. Human study further proves that our model generates more visually related, informative and coherent questions.

A goal-oriented visual dialogue involves multi-turn interactions between two agents, Questioner and Oracle. During which, the answer given by Oracle is of great significance, as it provides golden response to what Questioner concerns. Based on the answer, Questioner updates its belief on target visual content and further raises another question. Notably, different answers drive into different visual beliefs and future questions. However, existing methods always indiscriminately encode answers after much longer questions, resulting in a weak utilization of answers. In this paper, we propose an Answer-Driven Visual State Estimator (ADVSE) to impose the effects of different answers on visual states. First, we propose an Answer-Driven Focusing Attention (ADFA) to capture the answerdriven effect on visual attention by sharpening question-related attention and adjusting it by answer-based logical operation at each turn. Then based on the focusing attention, we get the visual state estimation by Conditional Visual Information Fusion (CVIF), where overall information and difference information are fused conditioning on the question-answer state. We evaluate the proposed ADVSE to both question generator and guesser tasks on the large-scale GuessWhat?! dataset and achieve the state-of-the-art performances on both tasks. The qualitative results indicate that the ADVSE boosts the agent to generate highly efficient questions and obtains reliable visual attentions during the reasonable question generation and guess processes. CCS CONCEPTS • Computing methodologies → Computer vision tasks; Discourse, dialogue and pragmatics; Natural language generation; Computer vision representations.

To encourage AI agents to conduct meaningful Visual Dialogue (VD), the use of Reinforcement Learning has been proven potential. In Reinforcement Learning, it is crucial to represent states and assign rewards based on the action-caused transitions of states. However, the state representation in previous Visual Dialogue works uses the textual information only and its transitions are implicit. In this paper, we propose Explicit Concerning States (ECS) to represent what visual contents are concerned at each round and what have been concerned throughout the Visual Dialogue. ECS is modeled from multimodal information and is represented explicitly. Based on ECS, we formulate two intuitive and interpretable rewards to encourage the Visual Dialogue agents to converse on diverse and informative visual information. Experimental results on the VisDial v1.0 dataset show our method enables the Visual Dialogue agents to generate more visual coherent, less repetitive and more visual informative dialogues compared with previous methods, according to multiple automatic metrics, human study and qualitative analysis.