This workshop Report Out focuses on the foundational elements of trustworthy AI and OR technology, and how to ensure all AI and OR systems implement these elements in their system designs. Four sessions on various topics within Trustworthy AI were held, these being Fairness, Explainable AI/Causality, Robustness/Privacy, and Human Alignment and Human-Computer Interaction. Following discussions of each of these topics, workshop participants also brainstormed challenge problems which require the collaboration of AI and OR researchers and will result in the integration of basic techniques from both fields to eventually benefit societal needs.
In order to produce facial-expression-specified talking head videos, previous audio-driven one-shot talking head methods need to use a reference video with a matching speaking style (i.e., facial expressions). However, finding videos with a desired style may not be easy, potentially restricting their application. In this work, we propose an expression-controllable one-shot talking head method, dubbed TalkCLIP, where the expression in a speech is specified by the natural language. This would significantly ease the difficulty of searching for a video with a desired speaking style. Here, we first construct a text-video paired talking head dataset, in which each video has alternative prompt-alike descriptions. Specifically, our descriptions involve coarse-level emotion annotations and facial action unit (AU) based fine-grained annotations. Then, we introduce a CLIP-based style encoder that first projects natural language descriptions to the CLIP text embedding space and then aligns the textual embeddings to the representations of speaking styles. As extensive textual knowledge has been encoded by CLIP, our method can even generalize to infer a speaking style whose description has not been seen during training. Extensive experiments demonstrate that our method achieves the advanced capability of generating photo-realistic talking heads with vivid facial expressions guided by text descriptions.
Human affective behavior analysis focuses on analyzing human expressions or other behaviors, which helps improve the understanding of human psychology. CVPR 2023 Competition on Affective Behavior Analysis in-the-wild (ABAW) makes great efforts to provide the diversity data for the recognition of the commonly used emotion representations, including Action Units~(AU), basic expression categories and Valence-Arousal~(VA). In this paper, we introduce our submission to the CVPR 2023: ABAW5 for AU detection, expression classification, VA estimation and emotional reaction intensity (ERI) estimation. First of all, we introduce the vision information from an MAE model, which has been pre-trained on a large-scale face image dataset in a self-supervised manner. Then the MAE encoder part is finetuned on the ABAW challenges on the single frame of Aff-wild2 dataset. We also exploit the multi-modal and temporal information from the videos and design a transformer-based framework to fusion the multi-modal features. Moreover, we construct a novel two-branch collaboration training strategy to further enhance the model generalization by randomly interpolating the logits space. The extensive quantitative experiments, as well as ablation studies on the Aff-Wild2 dataset and Hume-Reaction dataset prove the effectiveness of our proposed method.
For few-shot learning, it is still a critical challenge to realize photo-realistic face visually dubbing on high-resolution videos. Previous works fail to generate high-fidelity dubbing results. To address the above problem, this paper proposes a Deformation Inpainting Network (DINet) for high-resolution face visually dubbing. Different from previous works relying on multiple up-sample layers to directly generate pixels from latent embeddings, DINet performs spatial deformation on feature maps of reference images to better preserve high-frequency textural details. Specifically, DINet consists of one deformation part and one inpainting part. In the first part, five reference facial images adaptively perform spatial deformation to create deformed feature maps encoding mouth shapes at each frame, in order to align with the input driving audio and also the head poses of the input source images. In the second part, to produce face visually dubbing, a feature decoder is responsible for adaptively incorporating mouth movements from the deformed feature maps and other attributes (i.e., head pose and upper facial expression) from the source feature maps together. Finally, DINet achieves face visually dubbing with rich textural details. We conduct qualitative and quantitative comparisons to validate our DINet on high-resolution videos. The experimental results show that our method outperforms state-of-the-art works.
Synthesizing controllable motion for a character using deep learning has been a promising approach due to its potential to learn a compact model without laborious feature engineering. To produce dynamic motion from weak control signals such as desired paths, existing methods often require auxiliary information such as phases for alleviating motion ambiguity, which limits their generalisation capability. As past poses often contain useful auxiliary hints, in this paper, we propose a task-agnostic deep learning method, namely Multi-scale Control Signal-aware Transformer (MCS-T), with an attention based encoder-decoder architecture to discover the auxiliary information implicitly for synthesizing controllable motion without explicitly requiring auxiliary information such as phase. Specifically, an encoder is devised to adaptively formulate the motion patterns of a character's past poses with multi-scale skeletons, and a decoder driven by control signals to further synthesize and predict the character's state by paying context-specialised attention to the encoded past motion patterns. As a result, it helps alleviate the issues of low responsiveness and slow transition which often happen in conventional methods not using auxiliary information. Both qualitative and quantitative experimental results on an existing biped locomotion dataset, which involves diverse types of motion transitions, demonstrate the effectiveness of our method. In particular, MCS-T is able to successfully generate motions comparable to those generated by the methods using auxiliary information.
Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL) due to the heterogeneity and dynamic importance of different modalities. Specifically, we observe that these issues make conventional RL methods difficult to learn a useful state representation in the end-to-end training with multimodal information. To address this, we propose a novel multimodal RL approach that can do multimodal alignment and importance enhancement according to their similarity and importance in terms of RL tasks respectively. By doing so, we are able to learn an effective state representation and consequentially improve the RL training process. We test our approach on several multimodal RL domains, showing that it outperforms state-of-the-art methods in terms of learning speed and policy quality.
Different people speak with diverse personalized speaking styles. Although existing one-shot talking head methods have made significant progress in lip sync, natural facial expressions, and stable head motions, they still cannot generate diverse speaking styles in the final talking head videos. To tackle this problem, we propose a one-shot style-controllable talking face generation framework. In a nutshell, we aim to attain a speaking style from an arbitrary reference speaking video and then drive the one-shot portrait to speak with the reference speaking style and another piece of audio. Specifically, we first develop a style encoder to extract dynamic facial motion patterns of a style reference video and then encode them into a style code. Afterward, we introduce a style-controllable decoder to synthesize stylized facial animations from the speech content and style code. In order to integrate the reference speaking style into generated videos, we design a style-aware adaptive transformer, which enables the encoded style code to adjust the weights of the feed-forward layers accordingly. Thanks to the style-aware adaptation mechanism, the reference speaking style can be better embedded into synthesized videos during decoding. Extensive experiments demonstrate that our method is capable of generating talking head videos with diverse speaking styles from only one portrait image and an audio clip while achieving authentic visual effects. Project Page: https://github.com/FuxiVirtualHuman/styletalk.
Humans are sophisticated at reading interlocutors' emotions from multimodal signals, such as speech contents, voice tones and facial expressions. However, machines might struggle to understand various emotions due to the difficulty of effectively decoding emotions from the complex interactions between multimodal signals. In this paper, we propose a multimodal emotion analysis framework, InterMulti, to capture complex multimodal interactions from different views and identify emotions from multimodal signals. Our proposed framework decomposes signals of different modalities into three kinds of multimodal interaction representations, including a modality-full interaction representation, a modality-shared interaction representation, and three modality-specific interaction representations. Additionally, to balance the contribution of different modalities and learn a more informative latent interaction representation, we developed a novel Text-dominated Hierarchical High-order Fusion(THHF) module. THHF module reasonably integrates the above three kinds of representations into a comprehensive multimodal interaction representation. Extensive experimental results on widely used datasets, (i.e.) MOSEI, MOSI and IEMOCAP, demonstrate that our method outperforms the state-of-the-art.
Determining causal effects of temporal multi-intervention assists decision-making. Restricted by time-varying bias, selection bias, and interactions of multiple interventions, the disentanglement and estimation of multiple treatment effects from individual temporal data is still rare. To tackle these challenges, we propose a comprehensive framework of temporal counterfactual forecasting from an individual multiple treatment perspective (TCFimt). TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy. Through implementing experiments on two real-world datasets from distinct fields, the proposed method shows satisfactory performance in predicting future outcomes with specific treatments and in choosing optimal treatment type and timing than state-of-the-art methods.
Humans are skilled in reading the interlocutor's emotion from multimodal signals, including spoken words, simultaneous speech, and facial expressions. It is still a challenge to effectively decode emotions from the complex interactions of multimodal signals. In this paper, we design three kinds of multimodal latent representations to refine the emotion analysis process and capture complex multimodal interactions from different views, including a intact three-modal integrating representation, a modality-shared representation, and three modality-individual representations. Then, a modality-semantic hierarchical fusion is proposed to reasonably incorporate these representations into a comprehensive interaction representation. The experimental results demonstrate that our EffMulti outperforms the state-of-the-art methods. The compelling performance benefits from its well-designed framework with ease of implementation, lower computing complexity, and less trainable parameters.