Canada

Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and  visual video signals. Although existing methods have demonstrated that aligned visual input of lip movements can enhance the robustness of AVSR systems against noise, the paired videos are not always obtainable during inference, leading to the problem of visual missing modality, which restricts their practicality in real-world scenarios. To tackle this problem, we propose a Discrete Feature based Visual Generative Model (DFVGM) which exploits semantic correspondences between the audio and visual modalities 
during training and generates visual hallucinations in lieu of
real videos during inference. To achieve that, the 
primary challenge is to \textit{generate the visual hallucination 
given the noisy audio while preserving semantic correspondences with the clean speech.} To tackle this challenge, we start with training the audio encoder in the Audio-Only (AO) setting, which generates continuous semamtic features closely associated with the linguistic information. Simultaneously, the visual encoder is trained in the Visual-Only (VO) setting, producing visual features that are phonetically related. Next, we employ k-means to discretize the continuous audio and visual feature spaces. The discretization step 
allows DFVGM to capture high-level semantic structures that are more resilient to  noise and  generate visual hallucinations with high quality. We conduct extensive experiments on two publicly available datasets. The results demonstrate that our method achieves a remarkable 53\% relative reduction (30.5\%$\to$12.9\%) in Word Error Rate (WER) on average compared to the current state-of-the-art Audio-Only (AO) baselines while maintaining comparable results ($&lt;$ 5 difference) under the Audio-Visual (AV) setting without video as input.

AAAI 2024

Visual Hallucination Elevates Speech Recognition

audio viusal speech recognition，missing modality，robust model

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. 

AAAI 2022

Due to the detrimental impact of noise on the conventional audio speech recognition (ASR) task, audio-visual speech recognition~(AVSR) has been proposed by incorporating both audio and  visual video signals. Although existing methods have demonstrated that aligned visual input of lip movements can enhance the robustness of AVSR systems against noise, the paired videos are not always obtainable during inference, leading to the problem of visual missing modality, which restricts their practicality in real-world scenarios. To tackle this problem, we propose a Discrete Feature based Visual Generative Model (DFVGM) which exploits semantic correspondences between the audio and visual modalities 
during training and generates visual hallucinations in lieu of
real videos during inference. To achieve that, the 
primary challenge is to \textit{generate the visual hallucination 
given the noisy audio while preserving semantic correspondences with the clean speech.} To tackle this challenge, we start with training the audio encoder in the Audio-Only (AO) setting, which generates continuous semamtic features closely associated with the linguistic information. Simultaneously, the visual encoder is trained in the Visual-Only (VO) setting, producing visual features that are phonetically related. Next, we employ k-means to discretize the continuous audio and visual feature spaces. The discretization step 
allows DFVGM to capture high-level semantic structures that are more resilient to  noise and  generate visual hallucinations with high quality. We conduct extensive experiments on two publicly available datasets. The results demonstrate that our method achieves a remarkable 53\% relative reduction (30.5\%$\to$12.9\%) in Word Error Rate (WER) on average compared to the current state-of-the-art Audio-Only (AO) baselines while maintaining comparable results ($<$ 5 difference) under the Audio-Visual (AV) setting without video as input.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

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-24 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.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/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 grounding accuracy of existing video captioners is still behind the expectation. The majority of existing methods perform grounded video captioning on sparse entity annotations, whereas the captioning accuracy often suffers from degenerated object appearances on the annotated area such as motion blur and video defocus. Moreover, these methods seldom consider the complex interactions among entities. In this paper, we propose a comprehensive visual grounding network to improve video captioning, by explicitly linking the entities and actions to the visual clues across the video frames. Specifically, the network consists of spatial-temporal entity grounding and action grounding. The proposed entity grounding encourages the attention mechanism to focus on informative spatial areas across video frames, albeit the entity is annotated in only one frame of a video. The action grounding dynamically associates the verbs to related subjects and the corresponding context, which keeps fine-grained spatial and temporal details for action prediction. Both entity grounding and action grounding are formulated as a unified task guided by a soft grounding supervision, which brings architecture simplification and improves training efficiency as well. We conduct extensive experiments on two challenging datasets, and demonstrate significant performance improvements of +2.3 CIDEr on ActivityNet-Entities and +2.2 CIDEr on MSR-VTT compared to state-of-the-arts.

Comprehensive Visual Grounding for Video Description

Prediction of drug-target interactions (DTIs) is a crucial step in drug discovery, and deep learning methods have shown great promise in various DTI datasets. However, existing approaches still face several challenges, including limited labeled data, hidden bias issue, and a lack of generalization ability to out-of-domain data. These challenges hinder the model's capacity to learn truly informative interaction features, leading to shortcut learning and inferior predictive performance on novel drug-target pairs. To address these issues, we propose MlanDTI, a semi-supervised domain adaptive multilevel attention network (Mlan) for DTI prediction. We utilize two pre-trained BERT models to acquire bidirectional representations enriched with information from unlabeled data. Additionally, we introduce a Multilevel attention mechanism, enabling the model to learn domain-invariant drug-target interactions at different hierarchical levels. Moreover, we present a simple yet effective semi-supervised pseudo-labeling method to further enhance our model's predictive ability in cross-domain scenarios. Experiments on four datasets show that MlanDTI achieves state-of-the-art performances over other methods in inter-domain settings and outperforms all other approaches in cross-domain settings.

Multilevel Attention Network with Semi-supervised Domain Adaptation for Drug-Target Prediction

Although there has been significant progress in category-level object pose estimation in recent years, there is still considerable room for improvement. In this paper, we propose a novel transformer-based category-level 6D pose estimation method  called CatFormer to enhance the accuracy pose estimation. CatFormer comprises three main parts: a coarse deformation part, a fine deformation part, and a recurrent refinement part. In the coarse and fine deformation sections, we introduce a transformer-based deformation module that performs point cloud deformation and completion in the feature space. Additionally, after each deformation, we incorporate a transformer-based graph module to adjust fused features and establish geometric and topological relationships between points based on these features. Furthermore, we present an end-to-end recurrent refinement module that enables the prior point cloud to deform multiple times according to real scene features. We evaluate CatFormer's performance by training and testing it on CAMERA25 and REAL275 datasets. Experimental results demonstrate that CatFormer surpasses state-of-the-art methods. Moreover, we extend the usage of CatFormer to instance-level object pose estimation on the LINEMOD dataset, as well as object pose estimation in real-world scenarios. The experimental results validate the effectiveness and generalization capabilities of CatFormer. Our code and the supplemental materials are avaliable at https://github.com/BIT-robot-group/CatFormer.

CatFormer: Category-Level 6D Object Pose Estimation with Transformer

Existing deep pan-sharpening methods lack the learning of complementary information between PAN and MS modalities in the intermediate layers, and exhibit low interpretability due to their black-box designs. To this end, an interpretable deep unfolded network with intrinsic supervision for pan-sharpening is proposed. Building upon the observation degradation process, it formulates the pan-sharpening task as a variational model minimization with spatial consistency prior and spectral projection prior. The former prior requires a joint component decomposition of PAN and MS images to extract intrinsic features. By being supervised in the intermediate layers, it can selectively provide high-frequency information for spatial enhancement. The latter prior constrains the intensity correlation between MS and PAN images derived from physical observations, so as to improve spectral fidelity. To further enhance the transparency of network design, we develop an iterative solution algorithm following the half-quadratic splitting to unfold the deep model. It rigorously adheres to the variational model, significantly enhancing the interpretability behind network design and efficiently alternating the optimization of the network. Extensive experiments demonstrate the advantages of our method compared to state-of-the-arts, showcasing its remarkable generalization capability to real-world scenes. Our code is publicly available at https://github.com/Baixuzx7/DISPNet.

Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening

Single image super-resolution (SISR), especially in the real world, usually builds a large amount of LR-HR image pairs to learn representations that contain rich textural and structural information. However, relying on massive data for model training not only reduces training efficiency, but also causes heavy data storage burdens. In this paper, we attempt a pioneering study on dataset distillation (DD) for SISR problems to explore how data could be slimmed and compressed for the task. Unlike previous coreset selection methods which select a few typical examples directly from the original data, we remove the limitation that the selected data cannot be further edited, and propose to synthesize and optimize samples to preserve more task-useful representations. Concretely, by utilizing pre-trained GANs as a suitable approximation of realistic data distribution, we propose GSDD, which distills data in a latent generative space based on GAN-inversion techniques. By optimizing them to match with the practical data distribution in an informative feature space, the distilled data could then be synthesized. Experimental results demonstrate that when trained with our distilled data, GSDD can achieve comparable performance to the state-of-the-art (SOTA) SISR algorithms, while a nearly ×8 increase in training efficiency and a saving of almost 93.2% data storage space can be realized. Further experiments on challenging real-world data also demonstrate the promising generalization ability of GSDD.

GSDD: Generative Space Dataset Distillation for Image Super-resolution

Attaining the equilibrium geometry of a catalyst-adsorbate system is key to fundamentally assessing its effective properties, such as adsorption energy. While machine learning methods with advanced representation or supervision strategies have been applied to boost and guide the relaxation processes of catalysis systems, existing methods that produce linearly aggregated geometry predictions are susceptible to edge representations ambiguity, and are therefore vulnerable to graph variations. In this paper, we present a novel graph neural network (GNN) supervision and prediction strategy DR-Label. Our approach mitigates the multiplicity of solutions in edge representation and encourages model predictions that are independent of graph structural variations. DR-Label first Deconstructs finer-grained equilibrium state information to the model by projecting the node-level supervision signal to each edge. Reversely, the model Reconstructs a more robust equilibrium state prediction by converting edge-level predictions to node-level via a sphere-fitting algorithm. When applied to three fundamentally different models, DR-Label consistently enhanced performance. Leveraging the graph structure invariance of the DR-Label strategy, we further propose DRFormer, which applied explicit intermediate positional update and achieves a new state-of-the-art performance on the Open Catalyst 2020 (OC20) dataset and the Cu-based single-atom alloys CO adsorption (SAA) dataset. We expect our work to highlight vital principles for advancing geometric GNN models for catalysis systems and beyond. Our code is available at https://github.com/bowenwang77/DR-Label

DR-Label: Label Deconstruction and Reconstruction of GNN Models for Catalysis Systems

Federated learning (FL) provides a decentralized machine learning paradigm where a server collaborates with a group of clients to learn a global model without accessing the clients' data. User heterogeneity is a significant challenge for FL, which together with the class-distribution imbalance further enhances the difficulty of FL. Great progress has been made in large vision-language models, such as Contrastive Language-Image Pre-training (CLIP), which paves a new way for image classification and object recognition. Inspired by the success of CLIP on few-shot and zero-shot learning, we use CLIP to optimize the federated learning between server and client models under its vision-language supervision. It is promising to mitigate the user heterogeneity and class-distribution balance due to the powerful cross-modality representation and rich open-vocabulary prior knowledge. In this paper, we propose the CLIP-guided FL (CLIP2FL) method on heterogeneous and long-tailed data. In CLIP2FL, the knowledge of the off-the-shelf CLIP model is transferred to the client-server models, and a bridge is built between the client and server. Specifically, for client-side learning, knowledge distillation is conducted between client models and CLIP to improve the ability of client-side feature representation. For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model. A prototype contrastive learning with the supervision of the text encoder of CLIP is introduced to generate federated features depending on the client-side gradients, and they are used to retrain a balanced server classifier. Extensive experimental results on several benchmarks demonstrate that CLIP2FL achieves impressive performance and effectively deals with data heterogeneity and long-tail distribution. The code is available at https://github.com/shijiangming1/CLIP2FL.

CLIP-Guided Federated Learning on Heterogeneity and Long-Tailed Data

Enhancing the generalization performance of neural networks remains a formidable challenge, due to the model selection trade-off between training error and generalization gap. To handle this challenge, we present a posterior optimization issue, specifically designed to reduce the generalization error of trained neural networks. To operationalize this concept, we propose eXtreme Boosting machine (XBoost) which consists of a statistical learner and a metaheuristic optimizer. The statistical learner reduces the model capacity and thus the generalization gap; the metaheuristic optimizer minimizes the training error in a gradient-free manner. The two components cooperate to reduce the generalization error of a fully trained neural network. Furthermore, the statistical learner alleviates the multicollinearity in the discriminative layer and enhances the generalization performance. The metaheuristic optimizer eliminates the reliance on gradient calculation and offers more flexibility in learning objective selection. Experiments demonstrate that XBM improves the generalization performance of various prevalent neural network backbones effectively.

Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting | VIDEO

Aspect-based sentiment analysis (ABSA) has attracted much attention due to its wide application scenarios. Most previous studies have focused solely on monolingual ABSA, posing a formidable challenge when extending ABSA applications to multilingual scenarios. In this paper, we study upgrading monolingual ABSA to cross-lingual ABSA. Existing methods usually exploit pre-trained cross-lingual language to model cross-lingual ABSA, and enhance the model with translation data. However, the low-resource languages might be under-represented during the pre-training phase, and the translation-enhanced methods heavily rely on the quality of the translation and label projection. Inspired by the observation that quantum entanglement can correlate multiple single systems, we map the monolingual expression to the quantum Hilbert space as a single quantum system, and then utilize quantum entanglement and quantum measurement to achieve cross-lingual ABSA. Specifically, we propose a quantum-inspired neural model named QPEN (short for quantum projection and quantum entanglement enhanced network). It is equipped with a proposed quantum projection module that projects aspects as quantum superposition on a complex-valued Hilbert space. Furthermore, a quantum entanglement module is proposed in QPEN to share language-specific features between different languages without transmission. We conducted simulation experiments on the classical computer, and experimental results on SemEval-2016 dataset demonstrate that our method achieves state-of-the-art performance in terms of F1-scores for five languages.

QPEN: Quantum Projection and Quantum Entanglement Enhanced Network for Cross-Lingual Aspect-Based Sentiment Analysis

High-resolution representation is essential for achieving good performance in human pose estimation models. To obtain such features, existing works utilize high-resolution input images or fine-grained image tokens. However, this dense high-resolution representation brings a significant computational burden. In this paper, we address the following question: "Only sparse human keypoint locations are detected for human pose estimation, is it really necessary to describe the whole image in a dense, high-resolution manner?" Based on dynamic transformer models, we propose a framework that only uses Sparse High-resolution Representations for human Pose estimation (SHaRPose). In detail, SHaRPose consists of two stages. At the coarse stage, the relations between image regions and keypoints are dynamically mined while a coarse estimation is generated. Then, a quality predictor is applied to decide whether the coarse estimation results should be refined. At the fine stage, SHaRPose builds sparse high-resolution representations only on the regions related to the keypoints and provides refined high-precision human pose estimations. Extensive experiments demonstrate the outstanding performance of the proposed method. Specifically, compared to the state-of-the-art method ViTPose, our model SHaRPose-Base achieves 77.4 AP (+0.5 AP) on the COCO validation set and 76.7 AP (+0.5 AP) on the COCO test-dev set, and infers at a speed of 1.4x faster than ViTPose-Base. Code is available at https://github.com/AnxQ/sharpose.

Downloads

Next from AAAI 2024

Comprehensive Visual Grounding for Video Description

Similar lecture

Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation

.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 2024

Comprehensive Visual Grounding for Video Description

Similar lecture

Cross-Modal Mutual Learning for Audio-Visual Speech Recognition and Manipulation

Downloads