United States

Human intelligence is beyond pattern recognition. From a single image, we’re able to explain what we see, reconstruct the scene in 3D, predict what’s going to happen, and plan our actions accordingly. In this talk, I will present our recent work on physical scene understanding—building versatile, data-efficient, and generalizable machines that learn to see, reason about, and interact with the physical world. The core idea is to exploit the generic, causal structure behind the world, including knowledge from computer graphics, physics, and language, in the form of approximate simulation engines, and to integrate them with deep learning. Here, deep learning plays two major roles: first, it learns to invert simulation engines for efficient inference; second, it learns to augment simulation engines for constructing powerful forward models. I’ll focus on a few topics to demonstrate this idea: building scene representation for both object geometry and physics; learning expressive dynamics models for planning and control; perception and reasoning beyond vision.

AAAI 2023

Learning to See the Physical World

cognitive modeling & cognitive systems

intelligent robotics

machine learning

computer vision

ECAI2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI, including:




**An extensive programme of workshops, tutorials, and invited speakers**

**The Prestigious Applications of Intelligent Systems conference (PAIS)**

**The Frontiers in AI track sessions**

**The Lab To Market event**

**The Women in AI time**

**The EU Challenges forum**

… and many more!

ECAI 2020

ECAI 2020 featured a full programme of technical papers, as well as many AI-related events of interest for researchers, students and all attendants who are interested on contemporary AI.

technical paper

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.

The ability of snapshot compressive imaging (SCI) systems to efficiently capture high-dimensional (HD) data has led to an inverse problem, which consists of recovering the HD signal from the compressed and noisy measurement. While reconstruction algorithms grow fast to solve it with the recent advances of deep learning, the fundamental issue of accurate and stable recovery remains. To this end, we propose deep equilibrium models (DEQ) for video SCI, fusing data-driven regularization and stable convergence in a theoretically sound manner. Each equilibrium model implicitly learns a nonexpansive operator and analytically computes the fixed point, thus enabling unlimited iterative steps and infinite network depth with only a constant memory requirement in training and testing. Specifically, we demonstrate how DEQ can be applied to two existing models for video SCI reconstruction: recurrent neural networks (RNN) and Plug-and-Play (PnP) algorithms. On a variety of datasets and real data, both quantitative and qualitative evaluations of our results demonstrate the effectiveness and stability of our proposed method.

Deep Equilibrium Models for Snapshot Compressive Imaging

Participatory budgeting engages the public in the process of
allocating public money to different types of projects. PB designs
differ in how voters are asked to express their preferences
over candidate projects and how these preferences are
aggregated to determine which projects to fund. This paper
studies two fundamental questions in PB design. Which voting
format and aggregation method to use, and how to evaluate
the outcomes of these design decisions? We conduct an
extensive empirical study in which 1 800 participants vote in
four participatory budgeting elections in a controlled setting
to evaluate the practical effects of the choice of voting format
and aggregation rule. We find that k-approval leads to
the best user experience. With respect to the aggregation rule,
greedy aggregation leads to outcomes that are highly sensitive
to the input format used and the fraction of the population
that participates. ES, in contrast, leads to outcomes that
are not sensitive to the type of voting format used, and these
outcomes are remarkably stable even when the majority of the
population does not participate in the election. These results
carry valuable insights for PB practitioners and social choice
researchers.

Participatory Budgeting Designs for the Real World

Many real-world optimisation problems are defined over both categorical and continuous variables, yet efficient optimisation methods such as Bayesian Optimisation (BO) are ill-equipped to handle such mixed-variable search spaces. The optimisation breadth introduced by categorical variables in the mixed-input setting has seen recent approaches operating on local trust regions, but these methods can be greedy in suboptimal regions of the search space. In this paper, we adopt a holistic view and aim to consolidate optimisation of the categorical and continuous sub-spaces under a single acquisition metric. We develop a tree-based method which retains a global view of the optimisation spaces by identifying regions in the search space with high potential candidates which we call value proposals. Our method uses these proposals to make selections on both the categorical and continuous components of the input. We show that this approach significantly outperforms existing mixed-variable optimisation approaches across several mixed-variable black-box optimisation tasks.

Mixed-Variable Black-Box Optimisation Using Value Proposal Trees

Due to the particularity of the simultaneous occurrence of multiple events in music sequences, compound Transformer is proposed to deal with the challenge of long sequences. However, there are two deficiencies in the compound Transformer. First, since the order of events is more important for music than natural language, the information provided by the original absolute position embedding is not precise enough. Second, there is an important correlation between the tokens in the compound word, which is ignored by the current compound Transformer. Therefore, in this work, we propose an improved compound Transformer model for music understanding. Specifically, we propose an attribute embedding fusion module  and a novel position encoding scheme with absolute-relative consideration. In the attribute embedding fusion module, different attributes are fused through feature permutation by using a multi-head self-attention mechanism in order to capture rich interactions between attributes. In the novel position encoding scheme, we propose RoAR position encoding, which realizes rotational absolute position encoding, relative position encoding, and absolute-relative position interactive encoding, providing clear and rich orders for musical events.  Empirical study on four typical music understanding tasks shows that our attribute fusion approach and RoAR \textcolor{black}{position} encoding brings large performance gains. In addition, we further investigate the impact of masked sequence modeling and casual sequence modeling  pre-training on music understanding. 

Fine-grained Position Helps Memorizing More, A Novel Music Compound Transformer Model with Feature Interaction Fusion

This article presents our generative model for rhythm action games together with applications in business operation. Rhythm action games are video games in which the player is challenged to issue commands at the right timings during a music session. The timings are rendered in the chart, which consists of visual symbols, called notes, flying through the screen. We introduce our deep generative model, GenéLive!, which outperforms the state-of-the-art model by taking into account musical structures through beats and temporal scales. Thanks to its favorable performance, GenéLive! was put into operation at KLab Inc., a Japan-based video game developer, and reduced the business cost of chart generation by as much as half. The application target included the phenomenal "Love Live!", which has more than 10 million users across Asia and beyond, and is one of the few rhythm action franchises that has led the online era of the genre. In this article, we evaluate the generative performance of GenéLive! using production datasets at KLab as well as open datasets for reproducibility, while the model continues to operate in their business. Our code and the model, tuned and trained using a supercomputer, are publicly available.

Gen√©Live! Generating Rhythm Actions in Love Live!

Zero-shot (ZS) sketch-based three-dimensional (3D) shape retrieval (SBSR) is challenging due to the abstraction of sketches, cross-domain discrepancies between two-dimensional sketches and 3D shapes, and ZS-driven semantic knowledge transference from seen to unseen categories. Extant SBSR datasets suffer from lack of data, and no current SBSR methods consider ZS scenarios. In this paper, we contribute a new Doodle2Object (D2O) dataset consisting of 8,992 3D shapes and over 7M sketches spanning 50 categories. Then, we propose a novel prototype contrastive learning (PCL) method that effectively extracts features from different domains and adapts them to unseen categories. Specifically, our PCL method combines the ideas of contrastive and cluster-based prototype learning, and several randomly selected prototypes of different classes are assigned to each sample. By comparing these prototypes, a given sample can be moved closer to the same semantic class of samples while moving away from negative ones. Extensive experiments on two common SBSR benchmarks and our D2O dataset demonstrate the efficacy of the proposed PCL method for ZS-SBSR. Resource is available at https://github.com/yigohw/doodle2object.

Doodle to Object: Practical Zero-Shot Sketch-Based 3D Shape Retrieval

The pre-trained language models, e.g., ELMo and BERT, have recently achieved promising performance improvement in a wide range of NLP tasks, because they can output strong contextualized embedded features of words. Inspired by their great success, in this paper we target at fine-tuning them to effectively handle the text clustering task, i.e., a classic and fundamental challenge in machine learning. Accordingly, we propose a novel BERT-based method, namely Text Clustering with Dual Word-level Augmentation (TCDWA). To be specific, we formulate a self-training objective and enhance it with a dual word-level augmentation technique. First, we suppose that each text contains several most informative words, called anchor words, supporting the full text semantics. We use the embedded features of anchor words as augmented data, which are selected by ranking the norm-based attention weights of words. Second, we formulate an expectation form of word augmentation, which is equivalent to generating infinite augmented features, and further suggest a tractable approximation of Taylor expansion for efficient optimization. To evaluate the effectiveness of TCDWA, we conduct extensive experiments on several benchmark text datasets. The results demonstrate that TCDWA consistently outperforms the state-of-the-art baseline methods.

TC-DWA:Text Clustering with Dual Word-level Augmentation

Crowdsourcing is a favorable computing paradigm for processing computer-hard tasks by harnessing human intelligence. However, generic crowdsourcing systems may lead to privacy-leakage through the sharing of worker data. To tackle this problem, we propose a novel approach, called iFedCrowd (incentive-boosted Federated Crowdsourcing), to manage the privacy and quality of crowdsourcing projects. iFedCrowd allows participants to locally process sensitive data and only upload encrypted training models, and then aggregates the model parameters to build a shared server model to protect data privacy. To motivate workers to build a high-quality global model in an efficacy way, we introduce an incentive mechanism that encourages workers to constantly collect fresh data to train accurate client models and boosts the global model training. We model the incentive-based interaction between the crowdsourcing platform and participating workers as a Stackelberg game, in which each side maximizes its own profit. We derive the Nash Equilibrium of the game to find the optimal solutions for the two sides. Experimental results confirm that iFedCrowd can complete secure crowdsourcing projects with high quality and efficiency.

Incentive-boosted Federated Crowdsourcing

This paper presents a new method for end-to-end Video Question Answering (VideoQA), aside from the current popularity of using large-scale pre-training with huge feature extractors. We achieve this with a pyramidal multimodal transformer (PMT) model, which simply incorporates a learnable word embedding layer, a few convolutional and transformer layers. We use the anisotropic pyramid to fulfill video-language interactions across different spatio-temporal scales. In addition to the canonical pyramid, which includes both bottom-up and top-down pathways with lateral connections, novel strategies are proposed to decompose the visual feature stream into spatial and temporal sub-streams at different scales and implement their interactions with the linguistic semantics while preserving the integrity of local and global semantics. We demonstrate better or on-par performances with high computational efficiency against state-of-the-art methods on five VideoQA benchmarks. Our ablation study shows the scalability of our model that achieves competitive results for text-to-video retrieval by leveraging feature extractors with reusable pre-trained weights, and also the effectiveness of the pyramid.

Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer

Deep neural networks (DNNs) can easily be manipulated (by an adversary) to output drastically different predictions and can be done so in a controlled and directed way. This process is known as adversarial attack and is considered one of the major hurdles in using DNNs in high-stakes and real-world applications. Although developing methods to secure DNNs against adversaries is now a primary research focus, it suffers from limitations such as a lack of optimization generality and scalability. My research highlights will offer a holistic understanding of optimization foundations for robust AI, peer into their emerging challenges, and present recent solutions developed by my research group.

Premium content

Learning to See the Physical World

Downloads

Next from AAAI 2023

Deep Equilibrium Models for Snapshot Compressive Imaging

Similar lecture

Classifying the classifier: dissecting the weight space of neural networks