United States

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. 
Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee learnt embedding features are matched with the captions semantics. Comprehensive experiments and extensive ablation studies on ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms prior state-of-the-art methods on accuracy and diversity. Source code is made publicly available at: https://github.com/UARK-AICV/VLTinT

AAAI 2023

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

cv: video understanding & activity analysis

cv: multi-modal vision

cv: language and 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

Safe deployment of deep neural networks in high-stake real-world applications require theoretically sound uncertainty quantification. Conformal prediction (CP) is a principled framework for uncertainty quantification of deep models in the form of prediction set for classification tasks with a user-specified  coverage (i.e., true class label is contained with high probability). This paper proposes a novel algorithm referred to as {\em Neighborhood Conformal Prediction (NCP)} to improve the efficiency of uncertainty quantification from CP for deep classifiers (i.e., reduce prediction set size). The key idea behind NCP is to use the learned representation of the neural network to identify $k$ nearest-neighbor calibration examples for a given testing input and assign them importance weights proportional to their distance to create adaptive prediction sets. We theoretically show that if the learned data representation of the neural network satisfies some mild conditions, NCP will produce smaller prediction sets than traditional CP algorithms. Our comprehensive experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using diverse deep neural networks strongly demonstrate that NCP leads to significant reduction in prediction set size over prior CP methods.

Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis

The problem of answering complex First-order Logic queries over incomplete knowledge graphs  is receiving growing attention in the literature. A promising recent approach to this problem has been to exploit neural link predictors, which can be
effective in identifying individual missing triples in the incomplete graph, in order to efficiently answer complex queries. A crucial advantage of this approach over
other methods is that it does not require example answers to complex queries for training, as it relies only on the availability of a trained link  predictor for the knowledge graph at hand.  This approach, however, can be computationally expensive during inference,  and cannot deal with queries involving negation. 

In this paper, we propose a novel approach that addresses all of these limitations.
Experiments on established benchmark datasets demonstrate that our approach offers  superior performance while  significantly reducing inference times.

Efficient Embeddings of Logical Variables for Query Answering over Incomplete Knowledge Graphs

Document-level relation extraction (RE) aims to extract relational triples from a document. One of its primary challenges is to predict implicit relations between entities, which are not explicitly expressed in the document but can usually be extracted through relational reasoning. Previous methods mainly implicitly model relational reasoning through the interaction among entities or entity pairs. However, they suffer from two deficiencies: 1) they often consider only one reasoning pattern, of which coverage on relational triples is limited; 2) they do not explicitly model the process of relational reasoning. In this paper, to deal with the first problem, we propose a document-level RE model with a reasoning module that contains a core unit, the reasoning multi-head self-attention unit. This unit is a variant of the conventional multi-head self-attention and utilizes four attention heads to model four common reasoning patterns, respectively, which can cover more relational triples than previous methods. Then, to address the second issue, we propose a self-distillation training framework, which contains two branches sharing parameters. In the first branch, we first randomly mask some entity pair feature vectors in the document, and then train our reasoning module to infer their relations  by exploiting the feature information of other related entity pairs. By doing so, we can explicitly model the process of relational reasoning. However, because the additional masking operation is not used during testing, it causes an input gap between training and testing scenarios, which would hurt the model performance. To reduce this gap, we perform conventional supervised training without masking operation in the second branch and utilize Kullback-Leibler divergence loss to minimize the difference between the predictions of the two branches. Finally, we conduct comprehensive experiments on three benchmark datasets, of which experimental results demonstrate that our model consistently outperforms all competitive baselines. Our source code is available at https://github.com/DeepLearnXMU/DocRE-SD

Exploring Self-distillation based Relational Reasoning Training for Document-level Relation Extraction

Canonical models of Markov decision processes (MDPs) usually consider geometric discounting based on a constant discount factor. While this standard modeling approach has led to many elegant results, some recent studies indicate the necessity of modeling time-varying discounting in certain applications. This paper studies a model of infinite-horizon MDPs with time-varying discount factors. We take a game-theoretic perspective---whereby each time step is treated as an independent decision maker with their own (fixed) discount factor---and we study the {\em subgame perfect equilibrium} (SPE) of the resulting game as well as the related algorithmic problems. We present a constructive proof of the existence of an SPE and demonstrate the EXPTIME-hardness of computing an SPE. We also turn to the approximate notion of $\epsilon$-SPE and show that an $\epsilon$-SPE exists under milder assumptions. An algorithm is presented to compute an $\epsilon$-SPE, of which an upper bound of the time complexity, as a function of the convergence property of the time-varying discount factor, is provided. 

Markov Decision Processes with Time-Varying Geometric Discounting

The success of pre-trained contextualized representations has prompted researchers to analyze them for the presence of linguistic information. 
Indeed, it is natural to assume that these pre-trained representations do encode some level of linguistic knowledge as they have brought about large empirical improvements on a wide variety of NLP tasks, which suggests they are learning true linguistic generalization.
In this work, we focus on intrinsic probing, an analysis technique where the goal is not only to identify whether a representation encodes a linguistic attribute but also to pinpoint where this attribute is encoded.
We propose a novel latent-variable formulation for constructing intrinsic probes and derive a tractable variational approximation to the log-likelihood.
Our results show that our model is versatile and yields tighter mutual information estimates than two intrinsic probes previously proposed in the literature.
Finally, we find empirical evidence that pre-trained representations 
develop a cross-lingually entangled notion of morphosyntax.

A Latent-Variable Model for Intrinsic Probing

We study a fundamental model of online preference aggregation, where an algorithm maintains an ordered list of $n$ elements. An input is a stream of preferred sets $R_1, R_2, \dots, R_t, \dots$. Upon seeing $R_t$ and without knowledge of any future sets, an algorithm has to rerank elements (change the list ordering), so that at least one element of $R_t$ is found near the list front. The incurred cost is a sum of the list update costs (the number of swaps of neighboring list elements) and access cost (the position of the first element of $R_t$ on the list). This scenario occurs naturally in applications such as ordering items in an online shop using aggregated preferences of shop customers. The theoretical underpinning of this problem is known as Min-Sum Set Cover.

Unlike previous work (Fotakis et al., ICALP 2020, NIPS 2020) that mostly studied the performance of an online algorithm ALG in comparison to the static optimal solution (a single optimal list ordering), in this paper, we study an arguably harder variant where the benchmark is the provably stronger optimal dynamic solution OPT (that may also modify the list ordering). In terms of an online shop, this means that the aggregated preferences of its user base evolve with time. We construct a computationally efficient randomized algorithm whose competitive ratio (ALG-to-OPT cost ratio) is $O(r^2)$ and prove the existence of a deterministic $O(r^4)$-competitive algorithm. Here, $r$ is the maximum cardinality of sets $R_t$. This is the first algorithm whose ratio does not depend on $n$: the previously best algorithm for this problem was $O(r^{3/2} \cdot \sqrt{n})$-competitive and $\Omega(r)$ is a lower bound on the performance of any deterministic online algorithm.

An Improved Algorithm for Online Reranking

For named entity recognition (NER) in zero-resource languages, utilizing knowledge distillation methods to transfer language-independent knowledge from the rich-resource source languages to zero-resource languages is an effective means. Typically, these approaches adopt a teacher-student architecture, where the teacher network is trained in the source language, and the student network seeks to learn knowledge from the teacher network and is expected to perform well in the target language. Despite the impressive performance achieved by these methods, we argue that they have two limitations. Firstly, the teacher network fails to effectively learn language-independent knowledge shared across languages due to the differences in the feature distribution between the source and target languages. Secondly,  the student network acquires all of its knowledge from the teacher network and ignores the learning of target language-specific knowledge.
Undesirably, these limitations would hinder the model's performance in the target language. This paper proposes an unsupervised prototype knowledge distillation network (ProKD) to address these issues. Specifically, ProKD presents a contrastive learning-based prototype alignment method to achieve class feature alignment by adjusting the prototypes' distance from the source and target languages, boosting the teacher network's capacity to acquire language-independent knowledge. In addition, ProKD introduces a prototype self-training method to learn the intrinsic structure of the language by retraining the student network on the target data using samples' distance information from prototypes, thereby enhancing the student network's ability to acquire language-specific knowledge. Extensive experiments on three benchmark cross-lingual NER datasets demonstrate the effectiveness of our approach.

ProKD: An Unsupervised Prototypical Knowledge Distillation Network for Zero-Resource Cross-Lingual Named Entity Recognition

Successful machine learning methods require a trade-off between memorization and generalization. Too much memorization and the model cannot generalize to unobserved examples. Too much over-generalization and we risk under-fitting the data. While we commonly measure their performance through cross validation and accuracy metrics, how should these algorithms cope in domains that are extremely under-determined where accuracy is always unsatisfactory? We present a novel probabilistic graphical model structure learning approach that can learn, generalize and explain in these elusive domains by operating at the random variable instantiation level. Using Minimum Description Length (MDL) analysis, we propose a new decomposition of the learning problem over all training exemplars, fusing together minimal entropy inferences to construct a final knowledge base. By leveraging Bayesian Knowledge Bases (BKBs), a framework that operates at the instantiation level and inherently subsumes Bayesian Networks (BNs), we develop both a theoretical MDL score and associated structure learning algorithm that demonstrates significant improvements over learned BNs on 40 benchmark datasets. Further, our algorithm incorporates recent off-the-shelf DAG learning techniques enabling tractable results even on large problems. We then demonstrate the utility of our approach in a significantly under-determined domain by learning gene regulatory networks on breast cancer gene mutational data available from The Cancer Genome Atlas (TCGA).

Learning the Finer Things: Bayesian Structure Learning at the Instantiation Level

Traffic signal control is safety-critical for our daily life. Roughly one-quarter of road accidents in the U.S. happen at intersections due to problematic signal timing, urging the development of safety-oriented intersection control. However, existing studies on adaptive traffic signal control using reinforcement learning technologies have focused mainly on minimizing traffic delay but neglecting the potential exposure to unsafe conditions. We, for the first time, incorporate road safety standards as enforcement to ensure the safety of existing reinforcement learning methods, aiming toward operating intersections with zero collisions. We have proposed a safety-enhanced residual reinforcement learning method (SafeLight) and employed multiple optimization techniques, such as multi-objective loss function and reward shaping for better knowledge integration. Extensive experiments are conducted using both synthetic and real-world benchmark datasets. Results show that our method can significantly reduce collisions while increasing traffic mobility.

SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control

The daily practice of online image sharing enriches our lives, but also raises a severe issue of privacy leakage. To mitigate the privacy risks during image sharing, some researchers modify the sensitive elements in images with visual obfuscation methods including traditional ones like blurring and pixelating, as well as generative ones based on deep learning. However, images processed by such methods may be recovered or recognized by models, which cannot guarantee privacy. Further, traditional methods make the images very unnatural with low image quality. Although generative methods produce better images, most of them suffer from insufficiency in the frequency domain, which influences image quality. Therefore, we propose the AdvERsArial Sensitive Element Remover (ERASER) to guarantee both image privacy and image quality. 1) To preserve image privacy, for the regions containing sensitive elements, ERASER guarantees enough difference after being modified in an adversarial way. Specifically, we take both the region and global content into consideration with a Prior Transformer and obtain the corresponding region prior and global prior. Based on the priors, ERASER is trained with an adversarial Difference Loss to make the content in the regions different. As a result, ERASER can reserve the main structure and change the texture of the target regions for image privacy preservation. 2) To guarantee the image quality, ERASER improves the frequency insufficiency of current generative methods. Specifically, the region prior and global prior are processed with Fast Fourier Convolution to capture characteristics and achieve consistency in both pixel and frequency domains. Quantitative analyses demonstrate that the proposed ERASER achieves a balance between image quality and image privacy preservation, while qualitative analyses demonstrate that ERASER indeed reduces the privacy risk from the visual perception aspect.

Premium content

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

Downloads

Next from AAAI 2023

Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis

Similar lecture

Tagging before Alignment: Integrating Multi-Modal Tags for Video-Text Retrieval

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES