United States

Text-based motion generation models are drawing a surge of interest for their potential for automating the motion-making process in the game, animation, or robot industries. In this paper, we propose a diffusion-based motion synthesis and editing model named FLAME. Inspired by the recent successes in diffusion models, we integrate diffusion-based generative models into the motion domain. FLAME can generate high-fidelity motions well aligned with the given text. Also, it can edit the parts of the motion, both frame-wise and joint-wise, without any fine-tuning. FLAME involves a new transformer-based architecture we devise to better handle motion data, which is found to be crucial to manage variable-length motions and well attend to free-form text. In experiments, we show that FLAME achieves state-of-the-art generation performances on three text-motion datasets: HumanML3D, BABEL, and KIT. We also demonstrate that FLAME’s editing capability can be extended to other tasks such as motion prediction or motion in-betweening, which have been previously covered by dedicated models.

AAAI 2023

FLAME: Free-form Language-based Motion Synthesis &amp; Editing

motion synthesis

multimodal learning

generative model

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.

FLAME: Free-form Language-based Motion Synthesis & Editing

poster

To facilitate offline reinforcement learning, uncertainty estimation is commonly used to detect out-of-distribution data. By inspecting, we show that current explicit uncertainty estimators such as Monte Carlo Dropout and model ensemble are not competent to provide trustworthy uncertainty estimation in offline reinforcement learning. Accordingly, we propose a non-parametric distance-aware uncertainty estimator which is sensitive to the change in the input space for offline reinforcement learning. Based on our new estimator, adaptive truncated quantile critics are proposed to underestimate the out-of-distribution samples. We show that the proposed distance-aware uncertainty estimator is able to offer better uncertainty estimation compared to previous methods. Experimental results demonstrate that our proposed DARL method is competitive to the state-of-the-art methods in offline evaluation tasks.

DARL: Distance-Aware Uncertainty Estimation for Offline Reinforcement Learning

The Maximum Satisfiability (MAXSAT) problem is an optimization version of the Satisfiability problem (SAT) in which one is given a CNF formula with $n$ variables and needs to find the maximum number of simultaneously satisfiable clauses. The recent works of Xiao [IJCAI 2022], Xu et al. [IJCAI 2019], Alferov and Bliznets [AAAI 2021] achieved significant progress in proving new upper bounds on the worst-case computational complexity of MAXSAT. All three works reduce general MAXSAT to a special case of MAXSAT where each variable appears a small number of times. So, it is important to design fast algorithms for $(n,k)$-MAXSAT to construct an efficient exact algorithm for MAXSAT. $(n,k)$-MAXSAT is a special case of MAXSAT where each variable appears at most $k$ times in the input formula. 
For the $(n,3)$-MAXSAT problem, we design a $O^*(1.1749^n)$ algorithm improving on the previous record running time of $O^*(1.191^n)$ (Belova and Bliznets [TCS 2020]). For the $(n,4)$-MAXSAT problem, we construct a $O^*(1.3803^n)$ algorithm improving on the previous best running time of $O^*(1.4254^n)$ (Alferov and Bliznets [AAAI - 2021]). Using the results, we develop a $O^*(1.0911^L)$ algorithm for the MAXSAT where $L$ is a length of the input formula which improves $O^*(1.0927^L)$ algorithm by Alferov and Bliznets [AAAI - 2021].

Improved Algorithms for Maximum Satisfiability and Its Special Cases

Structure learning is a core problem in AI central to the fields of neuro-symbolic AI and statistical relational learning. It consists in automatically learning a logical theory from data. The basis for structure learning is mining repeating patterns in the data, known as structural motifs. Finding these patterns reduces the exponential search space and therefore guides the learning of formulas. Despite the importance of motif learning, it is still not well understood. We present the first principled approach for mining structural motifs in lifted graphical models, 
languages that blend first-order logic with probabilistic models,  which uses a stochastic process to measure the similarity of entities in the data. 

Our first contribution is an algorithm, which depends on two intuitive hyperparameters: one controlling the uncertainty in the entity similarity measure, and one controlling the softness of the resulting rules. Our second contribution is a preprocessing step where we perform hierarchical clustering on the data to reduce the search space to the most relevant data. Our third contribution is to introduce an O(n ln(n)) (in the size of the entities in the data) algorithm for clustering structurally-related data. We evaluate our approach using standard benchmarks and show that we outperform state-of-the-art structure learning approaches by up to 6% in terms of accuracy and up to 80% in terms of runtime.

Principled and Efficient Motif Finding for Structure Learning in Lifted Graphical Models

Traffic classification is a critical task in network security and management since it allows for the monitoring and analyzing of metadata in the network. Recent research has demonstrated the effectiveness of the deep learning-based traffic classification method. However, the following limitations remain: (1) the traffic representation is simply generated from raw packet bytes, resulting in the absence of important information; (2) the model structure of directly applying deep learning algorithms does not take traffic characteristics into account; and (3) scenario-specific classifier training usually requires a labor-intensive and time-consuming process to label data. In this paper, we introduce a masked autoencoder (MAE) based traffic transformer with multi-level flow representation to tackle these problems. To model raw traffic data, we design a formatted traffic representation matrix with hierarchical flow information. After that, we develop an efficient Traffic Transformer, in which packet-level and flow-level attention mechanisms implement more efficient feature extraction with lower complexity. At last, we utilize MAE paradigm to pre-train our classifier with a large amount of unlabeled data, and perform fine-tuning with a few labeled data for a series of traffic classification tasks. Experiment findings reveal that our method outperforms state-of-the-art methods on five real-world traffic datasets by a large margin. The code is available at https://github.com/NSSL-SJTU/YaTC.

Yet Another Traffic Classifier: A Masked Autoencoder Based Traffic Transformer with Multi-Level Flow Representation

Traditional federated learning (FL) algorithms, such as FedAvg, fail to handle non-i.i.d data because they learn a global model by simply averaging biased local models that are trained on non-i.i.d local data, therefore failing to model the global data distribution. 
In this paper, we present a novel Bayesian FL algorithm that successfully handles such a non-i.i.d FL setting by enhancing the local training task with an auxiliary task that explicitly estimates the global data distribution. 
One key challenge in estimating the global data distribution is that the data are partitioned in FL, and therefore the ground-truth global data distribution is inaccessible.
To address this challenge, we propose an expectation-propagation-inspired probabilistic neural network, dubbed federated neural propagation (FedNP), which efficiently estimates the global data distribution given non-i.i.d data partitions. Our algorithm is sampling-free and end-to-end differentiable, can be applied with any conventional FL frameworks and learns richer global data representation.
Experiments on both image classification tasks with synthetic non-i.i.d image data partitions and real-world non-i.i.d speech recognition tasks demonstrate that our framework effectively alleviates the performance deterioration caused by non-i.i.d data.

FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation

Audio-visual speech recognition (AVSR) has gained remarkable success for ameliorating the noise-robustness of speech recognition. Mainstream methods focus on fusing audio and visual inputs to obtain modality-invariant representations. However, such representations are prone to over-reliance on audio modality as it is much easier to recognize than video modality in clean conditions. As a result, the AVSR model underestimates the importance of visual stream in face of noise corruption. To this end, we leverage visual modality-specific representations to provide stable complementary information for the AVSR task. Specifically, we propose a reinforcement learning (RL) based framework called MSRL, where the agent dynamically harmonizes modality-invariant and modality-specific representations in the auto-regressive decoding process. We customize a reward function directly related to task-specific metrics (i.e., word error rate), which encourages the MSRL to effectively explore the optimal integration strategy. Experimental results on the LRS3 dataset show that the proposed method achieves state-of-the-art in both clean and various noisy conditions. Furthermore, we demonstrate the better generality of MSRL system than other baselines when test set contains unseen noises.    

Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning

Multi-task learning (MTL) models have demonstrated impressive results in computer vision, natural language processing and recommender systems. However, how MTL balances the optimization of shared parameters has not been explored yet.  In this work, we quantify the dominance of parameter training in MTL and demonstrate that dominance still occurs in existing works and leads to optimization problems using adaptive learning rate methods for optimization. We propose a Task-aware Adaptive Learning Rate method, named AdaTask, to use task-specific accumulative gradients when adjusting the learning rate of each parameter. Specifically, for tasks with a large accumulative gradient of parameters, a small learning rate is required; otherwise, for tasks with a small accumulative gradient, a large learning rate is required. Our approach can be treated as balancing the loss between tasks at parameter level. We demonstrate that task dominance is resolved by our method using our proposed task dominance quantification metric. Comprehensive experiments on synthetic and three real-world datasets show that AdaTask achieves better performance compared with several state-of-the-art MTL approaches.

AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning

Bilevel Optimization Programming is used to model complex and conflicting interactions between agents, for example in Robust AI or Privacy preserving AI. Integrating bilevel mathematical programming within deep learning is thus an essential objective for the Machine Learning community. 
Previously proposed approaches only consider single-level programming. In this paper, we extend existing single-level optimization programming approaches and thus propose Differentiating through Bilevel Optimization Programming (BiGrad) for end-to-end learning of models that use Bilevel Programming as a layer. 
BiGrad has wide applicability and can be used in modern machine learning frameworks. BiGrad is applicable to both continuous and combinatorial Bilevel optimization problems. We describe a class of gradient estimators for the combinatorial case which reduces the requirements in terms of computation complexity; for the case of the continuous variable, the gradient computation takes advantage of the push-back approach (i.e. vector-jacobian product) for an efficient implementation. Experiments show that the BiGrad successfully extends existing single-level approaches to Bilevel Programming.

Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming

THMA: Tencent HD map AI System for Creating HD Map Annotations

Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets.

FLAME: Free-form Language-based Motion Synthesis & Editing

Downloads

Next from AAAI 2023

DARL: Distance-Aware Uncertainty Estimation for Offline Reinforcement Learning

Similar lecture

Skating-Mixer: Long-term Sport Audio-Visual Modeling with MLPs