United States

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.

AAAI 2023

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

audio-visual learning talking head generation

face animation

computer vision

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

In time-series forecasting, future target values may be affected by both intrinsic and extrinsic effects. When forecasting blood glucose, for example, intrinsic effects can be inferred from the history of the target signal alone (i.e. blood glucose), but accurately modeling the impact of extrinsic effects requires auxiliary signals, like the amount of carbohydrates ingested. Standard forecasting techniques often assume that extrinsic and intrinsic effects vary at similar rates. However, when auxiliary signals are generated at a much lower frequency than the target variable (e.g., blood glucose measurements are made every 5 minutes, while meals occur once every few hours), even well-known extrinsic effects (e.g., carbohydrates increase blood glucose) may prove difficult to learn. To better utilize these sparse but informative variables (SIVs), we introduce a novel encoder/decoder forecasting approach that accurately learns the per-timepoint effect of the SIV, by (i) isolating it from intrinsic effects and (ii) restricting its learned effect based on domain knowledge. On a simulated dataset pertaining to the task of blood glucose forecasting, when the SIV is accurately recorded our approach outperforms baseline approaches in terms of rMSE (13.07 [95% CI: 11.77,14.16] vs. 14.14 [12.69,15.27]). In the presence of a corrupted SIV, the proposed approach can still result in lower error compared to the baseline but the advantage is reduced as noise increases. By isolating their effects and incorporating domain knowledge, our approach makes it possible to better utilize SIVs in forecasting. 

Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose

In this paper, we study the effect of preferences in abstract argumentation under a claim-centric perspective. Recent work has revealed that semantical and computational properties can change when reasoning is performed on 
  claim-level rather than on the argument-level, while under certain 
  natural restrictions (arguments with the same claims have the 
  same outgoing attacks) these properties are conserved. We now investigate
  these effects when, in addition, preferences have to be taken into account and consider four prominent reductions to handle preferences between arguments.
  As we shall see, these reductions give rise to 
  different classes of claim-augmented argumentation frameworks, and behave 
  differently in terms of semantic properties and computational complexity.
  This strengthens the view that the actual choice for handling preferences 
  has to be taken with care.

The Effect of Preferences in Abstract Argumentation Under a Claim-Centric View

The development of connected and autonomous vehicles opens an opportunity to manage intersections without signals. One promising approach is to use a central autonomous intersection manager to optimize the movement of the vehicles in the intersection. Existing work uses Mixed Integer Linear Programming (MILP) to find optimal solutions for this problem but is time-consuming and cannot be applied in real-time. On the other hand, the coordination of the vehicles is essentially a Multi-Agent Path Finding (MAPF) problem, for which dozens of efficient algorithms have been proposed in recent years. Inspired by these MAPF algorithms, we propose a three-level algorithm called PSL to solve the intersection coordination problem. Theoretically, PSL is complete and polynomial-time in the number of vehicles. Empirically, PSL runs significantly faster with only a slight compromise in the solution quality than the optimal MILP method. It also generates significantly better solutions with a slightly larger runtime than the traditional First-Come-First-Served strategy. 

Intersection Coordination with Priority-Based Search for Autonomous Vehicles

Conformal prediction (CP) is a wrapper around traditional machine learning models, giving coverage guarantees under the sole assumption of exchangeability; in classification problems, for a chosen significance level $\varepsilon$, CP guarantees that the error rate is at most $\varepsilon$, irrespective of whether the underlying model is misspecified. However, the prohibitive computational costs of ``full'' CP led researchers to design scalable alternatives, which alas do not attain the same guarantees or statistical power of full CP. In this paper, we use influence functions to efficiently approximate full CP. We prove that our method is a consistent approximation of full CP, and empirically show that the approximation error becomes smaller as the training set increases; e.g., for $10^{3}$ training points the two methods output p-values that are $<10^{-3}$ apart: a negligible error for any practical application. Our methods enable scaling full CP to large real-world datasets. We compare our full CP approximation (ACP) to mainstream CP alternatives, and observe that our method is computationally competitive whilst enjoying the statistical predictive power of full CP.

Approximating Full Conformal Prediction at Scale via Influence Functions

We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using human data. Although such agents can be obtained through self-play training, they can suffer significantly from the distributional shift when paired with unencountered partners, such as humans. In this paper, we propose Maximum Entropy Population-based training (MEP) to mitigate such distributional shift. In MEP, agents in the population are trained with our derived Population Entropy bonus to promote the pairwise diversity between agents and the individual diversity of agents themselves. After obtaining this diversified population, a common best agent is trained by paring with agents in this population via prioritized sampling, where the prioritization is dynamically adjusted based on the training progress. We demonstrate the effectiveness of our method MEP, with comparison to Self-Play PPO (SP), Population-Based Training (PBT), Trajectory Diversity (TrajeDi), and Fictitious Co-Play (FCP) in both matrix game and Overcooked game environments, with partners being human proxy models and real humans.

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination

Stochastic Boolean satisfiability (SSAT) is a formalism allowing decision-making for optimization under quantitative constraints. Although SSAT solvers are under active development, existing solvers do not provide Skolem-function witnesses, which are crucial for practical applications. In this work, we develop a new witness-generating SSAT solver, SharpSSAT, which integrates techniques, including component caching, clause learning, and pure literal detection. It can generate a set of Skolem functions witnessing the attained satisfying probability of a given SSAT formula. We also equip the solver ClauSSat with witness generation capability for comparison. Experimental results show that SharpSSAT outperforms current state-of-the-art solvers and can effectively generate compact Skolem strategies. The new witness-generating solver may broaden the applicability of SSAT to practical applications. 


SharpSSAT: A Witness-Generating Stochastic Boolean Satisfiability Solver

Neural Radiation Fields (NeRF) can implicitly represent 3D-consistent RGB images and geometric by optimizing an underlying continuous volumetric scene function using a sparse set of input views, which has greatly benefited view synthesis tasks. However, NeRF fails to estimate correct geometry when given fewer views, resulting in failure to synthesize novel views. Existing works rely on introducing depth images or adding depth estimation networks to resolve the problem of poor synthetic view in NeRF with fewer views. However, due to the lack of spatial consistency of the single-depth image and the poor performance of depth estimation with fewer views, the existing methods still have challenges in addressing this problem. So this paper proposes Bidirectional Optical Flow NeRF(BOF-NeRF), which addresses this problem by mining optical flow information between 2D images. Our key insight is that utilizing 2D optical flow images to design a loss can effectively guide NeRF to learn the correct geometry and synthesize the right novel view. We also propose a view-enhanced fusion method based on geometry and color consistency to solve the problem of novel view details loss in NeRF. We conduct extensive experiments on the NeRF-LLFF and DTU MVS benchmarks for novel view synthesis tasks with fewer images in different complex real scenes. We further demonstrate the robustness of BOF-NeRF under different baseline distances on the Middlebury dataset. In all cases, BOF-NeRF outperforms current state-of-the-art baselines for novel view synthesis and scene geometry estimation.

Bidirectional Optical Flow NeRF: High Accuracy and High Quality under Fewer Views

With the prevalence of smart mobile devices and location-based services, uncovering social relationships from human mobility data is of great value in real-world spatio-temporal applications ranging from friend recommendation, advertisement targeting to transportation scheduling. While a handful of sophisticated graph embedding techniques are developed for social relationship inference, they are significantly limited to the sparse and noisy nature of user mobility data, as they all ignore the essential problem of the existence of a large amount of noisy data unrelated to social activities in such mobility data. In this work, we present \textbf{\uline{S}}ocial \textbf{\uline{R}}elationship \textbf{\uline{I}}nference \textbf{\uline{Net}}work (SRINet), a novel Graph Neural Network (GNN) framework, to improve inference performance by learning to remove noisy data. Specifically, we first construct a multiplex user meeting graph to model the spatial-temporal interactions among users in different semantic contexts. Our proposed SRINet tactfully combines the representation learning ability of Graph Convolutional Networks (GCNs) with the power of removing noisy edges of graph structure learning, which can learn effective user embeddings on the multiplex user meeting graph in a semi-supervised manner. Extensive experiments on three real-world datasets demonstrate the superiority of SRINet against state-of-the-art techniques in inferring social relationships from user mobility data. The source code of our method is available at \url{https://github.com/qinguangming1999/SRINet}.

Graph Structure Learning on User Mobility Data for Social Relationship Inference

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances self-attention mechanism to its robust variant for Transformer-based pre-trained language models (e.g. BERT). We propose \textit{Adversarial Self-Attention} mechanism (ASA), which adversarially biases the attentions to effectively suppress the model reliance on features (e.g. specific keywords) and encourage its exploration of broader semantics. We conduct comprehensive evaluation across a wide range of tasks for both pre-training and fine-tuning stages. For pre-training, ASA unfolds remarkable performance gain compared to naive training for longer steps. For fine-tuning, ASA-empowered models outweigh naive models by a large margin considering both generalization and robustness.

Adversarial Self-Attention for Language Understanding

Topic segmentation aims to reveal the latent structure of a document and divide it into multiple parts. However, current neural solutions are limited in the context modeling of sentences and feature representation of candidate boundaries. This causes the model to suffer from inefficient sentence context encoding and noise information interference. In this paper, we design a new text segmentation model SegFormer with unidirectional attention blocks to better model sentence representations. To alleviate the problem of noise information interference, SegFormer uses a novel additional context aggregator and a topic classification loss to guide the model to aggregate the information within the appropriate range.  In addition, SegFormer applies an iterative prediction algorithm to search for optimal boundaries progressively. We evaluate SegFormer's generalization ability, multilingual ability, and application ability on multiple challenging real-world datasets. Experiments show that our model significantly improves the performance by 7.5% on the benchmark WIKI-SECTION compared to several strong baselines. The application of SegFormer to a real-world dataset to separate normal and advertisement segments in product marketing essays also achieves superior performance in the evaluation with other cutting-edge models.

Premium content

StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles

Downloads

Next from AAAI 2023

Forecasting with Sparse but Informative Variables: A Case Study in Predicting Blood Glucose

Similar lecture

MuMIC - Multimodal Embedding for Multi-label Image Classification with Tempered Sigmoid