United States

This paper considers a video caption generating network referred to as Semantic Grouping Network (SGN) that attempts (1) to group video frames with discriminating word phrases of partially decoded caption and then (2) to decode those semantically aligned groups in predicting the next word. As consecutive frames are not likely to provide unique information, prior methods have focused on discarding or merging repetitive information based only on the input video. The SGN learns an algorithm to capture the most discriminating word phrases of the partially decoded caption and a mapping that associates each phrase to the relevant video frames - establishing this mapping allows semantically related frames to be clustered, which reduces redundancy. In contrast to the prior methods, the continuous feedback from decoded words enables the SGN to dynamically update the video representation that adapts to the partially decoded caption. Furthermore, a contrastive attention loss is proposed to facilitate accurate alignment between a word phrase and video frames without manual annotations. The SGN achieves state-of-the-art performances by outperforming runner-up methods by a margin of 2.1%p and 2.4%p in a CIDEr-D score on MSVD and MSR-VTT datasets, respectively. Extensive experiments demonstrate the effectiveness and interpretability of the SGN.

AAAI 2021

Semantic Grouping Network for Video Captioning

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

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-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

AAAI 2025

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-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

Monocular estimation of three dimensional human self-contact is fundamental for detailed scene analysis including body language understanding and behaviour modeling. 
Existing 3d reconstruction methods do not focus on body regions in self-contact and consequently recover configurations that are either far from each other or self-intersecting, when they should just touch. This leads to perceptually incorrect estimates and limits impact in those very fine-grained analysis domains where detailed 3d models are expected to play an important role. To address such challenges we detect self-contact and design 3d losses to explicitly enforce it. Specifically, we develop a model for Self-Contact Prediction (SCP), that estimates the body surface signature of self-contact, leveraging the localization of self-contact in the image, during both training and inference. We collect two large datasets to support learning and evaluation: (1) HumanSC3D, an accurate 3d motion capture repository containing 1,032 sequences with 5,058 contact events and 1,246,487 ground truth 3d poses synchronized with images collected from multiple views, and (2) FlickrSC3D, a repository of 3,969 images, containing 25,297 surface-to-surface correspondences with annotated image spatial support. We also illustrate how more expressive 3d reconstructions can be recovered under self-contact signature constraints and present monocular detection of face-touch as one of the multiple applications made possible by more accurate self-contact models.

Learning Complex 3D Human Self-Contact

Recent results show that features of adversarially trained networks for classification, in addition to being robust, enable desirable properties such as invertibility. 
The latter property may seem counter-intuitive as it is widely accepted by the community that classification models should only capture the minimal information (features) required for the task. 
Motivated by this discrepancy, we investigate the dual relationship between Adversarial Training and Information Theory. We show that the Adversarial Training can improve linear transferability to new tasks, from which arises a new trade-off between transferability of representations and accuracy on the source task. We validate our results employing robust networks trained on CIFAR-10, CIFAR-100 and ImageNet on several datasets. 
Moreover, we show that Adversarial Training reduces Fisher information of representations about the input and of the weights about the task, and we provide a theoretical argument which explains the invertibility of deterministic networks without violating the principle of minimality. Finally, we leverage our theoretical insights to remarkably improve the quality of reconstructed images through inversion.

Adversarial Training Reduces Information and Improves Transferability

Submodular maximization has attracted much attention due to its wide application and attractive property. Previous works mainly considered one single objective function, while there can be multiple ones in practice. As the objectives are usually conflicting, there exists a set of Pareto optimal solutions, attaining different optimal trade-offs among multiple objectives. In this paper, we consider the problem of minimizing the regret ratio in multi-objective submodular maximization, which is to find at most k solutions to approximate the whole Pareto set as well as possible. We propose a new algorithm RRMS by sampling representative weight vectors and solving the corresponding weighted sums of objective functions using some given \alpha-approximation algorithm for single-objective submodular maximization. We prove that the regret ratio of the output of RRMS is upper bounded by 1-\alpha+O(\sqrt{d-1}\cdot(\frac{d}{k-d})^{\frac{1}{d-1}}), where d is the number of objectives. This is the first theoretical guarantee for the situation with more than two objectives. When d=2, it reaches the (1-\alpha+O(1/k))-guarantee of the only existing algorithm Polytope. Empirical results on the applications of multi-objective weighted maximum coverage and Max-Cut show the superior performance of RRMS over Polytope.

Multi-Objective Submodular Maximization by Regret Ratio Minimization with Theoretical Guarantee

Learning-based classifiers are susceptible to adversarial examples. Existing defence methods are mostly devised on individual classifiers. Recent studies showed that it is viable to increase adversarial robustness by promoting diversity over an ensemble of models. In this paper, we propose adversarial defence by encouraging ensemble diversity on learning high-level feature representations and gradient dispersion in simultaneous training of deep ensemble networks. We perform extensive evaluations under white-box and black-box attacks including transferred examples and adaptive attacks. Our approach achieves a significant gain of up to 52% in adversarial robustness, compared with the baseline and the state-of-the-art method on image benchmarks with complex data scenes. The proposed approach complements the defence paradigm of adversarial training, and can further boost the performance. The source code is available at https://github.com/ALIS-Lab/AAAI2021-PDD.

Adversarial Defense by Diversified Simultaneous Training of Deep Ensembles

Coronavirus Disease 2019 (COVID-19) causes a sudden turnover to bad at some checkpoints and thus needs the intervention of intensive care unit (ICU). This resulted in urgent and large needs of ICUs posed great risks to the medical system. Estimating the mortality of critical in-patients who were not admitted into the ICU will be valuable to optimize the management and assignment of ICU. Retrospective, 733 in-patients diagnosed with COVID-19 at a local hospital (Wuhan, China), as of March 18, 2020. Demographic, clinical and laboratory results were collected and analyzed using machine learning to build a predictive model. Considering the shortage of ICU beds at the beginning of disease emergence, we defined the mortality for those patients who were predicted to be in needing ICU care yet they did not as Missing-ICU (MI)-mortality. To estimate MI-mortality, a prognostic classification model was built to identify the in-patients who may need ICU care. Its predictive accuracy was 0.8288, with an AUC of 0.9119. On our cohort of 733 patients, 25 in-patients who have been predicted by our model that they should need ICU, yet they did not enter ICU due to lack of shorting ICU wards. Our analysis had shown that the MI-mortality is 41%, yet the mortality of ICU is 32%, implying that enough bed of ICU in treating patients in critical conditions.

Savable but Lost Lives when ICU Is Overloaded: A Model from 733 Patients in Epicenter Wuhan, China

Researches have demonstrated that low bit-width (e.g., INT8) quantization can be employed to accelerate the inference process. It makes the gradient quantization very promising since the backward propagation requires approximately twice more computation than forward one. Due to the variability and uncertainty of gradient distribution, a lot of methods have been proposed to attain training stability. However, most of them ignore the channel-wise gradient distributions and the impact of gradients with different magnitudes, resulting in the degradation of final accuracy. In this paper, we propose a novel INT8 quantization training framework for convolutional neural network to address the above issues. Specifically, we adopt Gradient Vectorized Quantization to quantize the gradient, based on the observation that layer-wise gradients contain multiple distributions along the channel dimension. Then, Magnitude-aware Clipping Strategy is introduced by taking the magnitudes of gradients into consideration when minimizing the quantization error, and we present a theoretical derivation to solve the quantization parameters of different distributions. Experimental results on broad range of computer vision tasks, such as image classification, object detection and video classification, demonstrate that the proposed Distribution Adaptive INT8 Quantization training method has achieved almost lossless training accuracy for different backbones, including ResNet, MobileNetV2, InceptionV3, VGG and AlexNet, which is superior to the state-of-the-art techniques. Moreover, we further implement the INT8 kernel that can accelerate the training iteration more than 200% under the latest Turing architecture, i.e., our method excels on both training accuracy and speed.

Distribution Adaptive INT8 Quantization for Training CNNs

We study the setting in which a mobile searcher must locate a hidden target in a bounded or unbounded search domain, with no information about the hider's position. In particular, we consider online search, in which the performance of the search strategy is evaluated by its worst case competitive ratio. We introduce a multi-criteria search problem in which the searcher has a budget on its allotted search time, and the objective is to design strategies that are competitively efficient, respect the budget, and maximize the total searched ground. We give analytically optimal strategies for the line and the star domains, and efficient heuristics for general networks.

Online Search with Maximum Clearance

Envy-freeness up to one good (EF1) and envy-freeness up to any good (EFX) are two well-known extensions of envy-freeness for the case of indivisible items. It is shown that EF1 can always be guaranteed for agents with subadditive valuations. In sharp contrast, it is unknown whether or not an EFX allocation always exists, even for four agents and additive valuations. In addition, the best approximation guarantee for EFX is (Ï† âˆ’ 1) â‰ƒ 0.61 by Amanitidis et al..
In order to find a middle ground to bridge this gap, in this paper we suggest another fairness criterion, namely envy-freeness up to a random good or EFR, which is weaker than EFX, yet stronger than EF1. For this notion, we provide a polynomial-time 0.73-approximation allocation algorithm. For our algorithm we introduce Nash Social Welfare Matching which makes a connection between Nash Social Welfare and envy freeness.

Almost Envy-Freeness, Envy-Rank, and Nash Social Welfare Matchings

AI solutions are heavily dependant on the quality and accuracy of the input training data, however the training data may not always fully reflect the most up-to-date policy landscape or may be missing business logic. The advances in explainability have opened the possibility of allowing users to interact with interpretable explanations of ML predictions in order to inject modifications or constraints that more accurately reflect current realities of the system. In this paper, we present a solution which leverages the predictive power of ML models while allowing the user to specify modifications to decision boundaries. Our interactive overlay approach achieves this goal without requiring model retraining, making it appropriate for systems that need to apply instant changes to their decision making. We demonstrate that user feedback rules can be layered with the ML predictions to provide immediate changes which in turn supports learning with less data.

User Driven Model Adjustment via Boolean Rule Explanations

Cross-entropy loss combined with softmax is one of the most commonly used supervision components in most existing segmentation methods. The softmax loss is typically good at optimizing the inter-class difference, but not good at reducing the intra-class variation, which can be suboptimal for semantic segmentation task. In this paper, we propose a Consistent-Separable Feature Representation Network to model the Consistent-Separable (C-S) features, which are intra-class consistent and inter-class separable, improving the discriminative power of the deep features. Specifically, we develop a Consistent-Separable Feature Learning Module to obtain C-S features through a new loss, called Class-Aware Consistency loss. This loss function is proposed to force the deep features to be consistent among the same class and apart between different classes. Moreover, we design an Adaptive feature Aggregation Module to fuse the C-S features and original features from backbone for the better semantic prediction. We show that compared with various baselines, the proposed method brings consistent performance improvement. Our proposed approach achieves state-of-the-art performance on Cityscapes (82.6% mIoU in test set), ADE20K (46.65% mIoU in validation set), COCO Stuff (41.3% mIoU in validation set) and PASCAL Context (55.9% mIoU in test set).

Downloads

Next from AAAI 2021

Learning Complex 3D Human Self-Contact

Similar lecture

MAMS: Model-Agnostic Module Selection Framework for Video Captioning

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Learning Complex 3D Human Self-Contact

Similar lecture

MAMS: Model-Agnostic Module Selection Framework for Video Captioning

Downloads