Real-time engagement estimation holds significant potential across various research areas, particularly in the realm of human-computer interaction. It empowers artificial agents to dynamically adjust their responses based on user engagement levels, fostering more intuitive and immersive interactions. Despite the strides in automating real-time engagement estimation, the task remains challenging in real-world settings, especially when handling multi-modal human social signals. Capitalizing on human body and audio signals, this paper explores the appropriate feature representations of different modalities and effective modelling of dual conversations. This results in a novel and efficient multi-modal engagement detection model.We thoroughly evaluated our method in the MultiMediate'23 grand challenge. It performs consistently, with a notable improvement over the baseline model. Specifically, while the baseline achieves a concordance correlation coefficient (CCC) of 0.59, our approach yields a CCC of 0.70, suggesting its promising efficacy in real-life engagement detection.
论文检索
输入标题、作者或关键词，从 1,014 篇学术成果中精准定位
In this paper, we present the solutions to the MER-MULTI and MER-NOISE sub-challenges of the Multimodal Emotion Recognition Challenge (MER 2023). For the tasks MER-MULTI and MER-NOISE, participants are required to recognize both discrete and dimensional emotions. Particularly, in MER-NOISE, the test videos are corrupted with noise, necessitating the consideration of modality robustness. Our empirical findings indicate that different modalities contribute differently to the tasks, with a significant impact from the audio and visual modalities, while the text modality plays a weaker role in emotion prediction. To facilitate subsequent multimodal fusion, and considering that language information is implicitly embedded in large pre-trained speech models, we have made the deliberate choice to abandon the text modality and solely utilize visual and acoustic modalities for these sub-challenges. To address the potential underfitting of individual modalities during multimodal training, we propose to jointly train all modalities via a weighted blending of supervision signals. Furthermore, to enhance the robustness of our model, we employ a range of data augmentation techniques at the image level, waveform level, and spectrogram level. Experimental results show that our model ranks 1st in both MER-MULTI (0.7005) and MER-NOISE (0.6846) sub-challenges, validating the effectiveness of our method. Our code is publicly available at https://github.com/dingchaoyue/Multimodal-Emotion-Recognition-MER-and-MuSe-2023-Challenges.
The surge in video and social media content underscores the need for a deeper understanding of multimedia data. Most of the existing mature video understanding techniques perform well with short formats and content that requires only shallow understanding, but do not perform well with long format videos that require deep understanding and reasoning. Deep Video Understanding (DVU) Challenge aims to push the boundaries of multimodal extraction, fusion, and analytics to address the problem of holistically analyzing long videos and extract useful knowledge to solve different types of queries. This paper introduces a query-aware method for long video localization and relation discrimination, leveraging an image-language pretrained model. This model adeptly selects frames pertinent to queries, obviating the need for a complete movie-level knowledge graph. Our approach achieved first and fourth positions for two groups of movie-level queries. Sufficient experiments and final rankings demonstrate its effectiveness and robustness.
Automatic detection of backchannel has great potential to enhance artificial mediators, which indicate listeners' attention and agreement in human communication. It is often expressed by subtle non-verbal cues that occur briefly and sparsely. Focusing on identifying and locating these subtle cues (i.e., their occurrence moment and the involved body parts), this paper proposes a novel approach for backchannel detection. In particular, our model utilizes temporal- and modality-attention modules to determine and lead the model to pay more attention to both the indicative moment and the accompanying body parts at that specific time. It achieves an accuracy of 68.6% on the testing set in MultiMediate'23 backchannel detection challenge, outperforming the counterparts. Furthermore, we conducted an ablation study to thoroughly understand the contributions of our model. This study underscores the effectiveness of our selection of modality inputs and the importance of the two attention modules in our model.
In dyadic speaker-listener interactions, the listener's head reactions, together with the speaker's head movements, form an important non-verbal semantic expression. The listener Head generation task aims to synthesize the responsive listener's head videos based on audios of the speaker and reference images of the listener. Compared to the talking-head generation, it is more challenging to capture the correlation cues from the speaker's audio and visual information. Following the ViCo baseline scheme, we propose a high-performance solution by enhancing the hierarchical semantic extraction capability of the audio encoder module and improving the decoder part, renderer and post-processing modules. Our solution gets the first place on the official leaderboard for the track of listening head generation. This paper is a technical report of ViCo@2023 Conversational Head Generation Challenge at the ACM Multimedia 2023 conference.
The task of interval localization of macro- and micro-expression in long videos has a wide range of applications in the field of human-computer interaction. Compared with macro-expression, micro-expression has shorter duration, lower intensity, and smaller number of samples, which make them more difficult to spot accurately in long videos. In this paper, we propose a pre-trained model combined with the optical flow method to improve the accuracy and robustness of macro- and micro-expression spotting. Firstly, self-supervised pre-training is performed on rich unlabeled data based on VideoMAE. Then, multiple models are trained on the datasets SAMM-LV and CAS(ME)³ for macro- and micro-expression with different fine-grains. Finally, different lengths of slices are generated based on the models with different fine-grains, and the optimal matching method through the combination of model fine-grainedness and slice lengths is explored. At the same time, macro- and micro-expression generating regions were spotted using the optical flow method, fused with the model outputs to supplement the spatio-temporal information not captured by the model and to exclude the interference of non-interested regions. We evaluated the performance of our method on the MEGC2023 testset (consisting of 10 long videos from SAMM and 20 long videos from CAS(ME)3) and won first place in the MEGC2023 Challenge. The results demonstrate the effectiveness of the method.
The multimodal emotion recognition has attracted more attention in recent decades. Though remarkable progress has been achieved with the rapid development of deep learning, existing methods are still hard to tackle noise problems that occurred commonly in emotion recognition's practical application. To improve the robustness of the multimodal emotion recognition algorithm, we propose an MLP-based label revision algorithm. The framework consists of three complementary feature extraction networks that were verified in MER2023. After that, an MLP-based attention network with specially designed loss functions was used to fuse features from different modalities. Finally, the scheme that used the output probability of each emotion to revise the sample's output category was employed to revise the test set's label obtained by classifier. The samples that are most likely to be affected by noise and misclassified have a chance to get correct classification. The best experimental result shows that the F1-score of our algorithm on the test dataset of the MER 2023 Noise subchallenge is 86.35 and combined metric is 0.6694, which ranks 2nd at the MER 2023 NOISE subchallenge.
This paper presents our solution in the ACM Multimedia ViCo 2023 Conversational Head Generation Challenge, which aims to generate vivid face-to-face conversation videos based on audio and reference images. Our approach builds upon the SadTalker framework with several improvements. Since SadTalker is already a mature and well-developed framework, consisting of multiple stages of algorithms and models, our enhancements mainly focus on the preprocessing and postprocessing stages. With our improved method, we achieved second place in both the Talking Head Generation track and the Listening Head Generation track.
Offline Multiple Appropriate Facial Reaction Generation (OMAFRG) aims to predict the reaction of different listeners given a speaker, which is useful in the senario of human-computer interaction and social media analysis. In recent years, the Offline Facial Reactions Generation (OFRG) task has been explored in different ways. However, most studies only focus on the deterministic reaction of the listeners. The research of the non-deterministic (i.e. OMAFRG) always lacks of sufficient attention and the results are far from satisfactory. Compared with the deterministic OFRG tasks, the OMAFRG task is closer to the true circumstance but corresponds to higher difficulty for its requirement of modeling stochasticity and context. In this paper, we propose a new model named FRDiff to tackle this issue. Our model is developed based on the diffusion model architecture with some modification to enhance its ability of aggregating the context features. And the inherent property of stochasticity in diffusion model enables our model to generate multiple reactions. We conduct experiments on the datasets provided by the ACM Multimedia REACT2023 and obtain the second place on the board, which demonstrates the effectiveness of our method.
This paper presents our solution for the Semi-Supervised Multimodal Emotion Recognition Challenge (MER2023-SEMI), addressing the issue of limited annotated data in emotion recognition. Recently, the self-training-based Semi-Supervised Learning~(SSL) method has demonstrated its effectiveness in various tasks, including emotion recognition. However, previous studies focused on reducing the confirmation bias of data without adequately considering the issue of data imbalance, which is of great importance in emotion recognition. Additionally, previous methods have primarily focused on unimodal tasks and have not considered the inherent multimodal information in emotion recognition tasks. We propose a simple yet effective semi-supervised multimodal emotion recognition method to address the above issues. We assume that the pseudo-labeled samples with consistent results across unimodal and multimodal classifiers have a more negligible confirmation bias. Based on this assumption, we suggest using a class-balanced strategy to select top-k high-confidence pseudo-labeled samples from each class. The proposed method is validated to be effective on the MER2023-SEMI Grand Challenge, with the weighted F1 score reaching 88.53% on the test set.
Pre-trained video-language models (VLMs) have shown superior performance in high-level video understanding tasks, analyzing multi-modal information, aligning with Deep Video Understanding Challenge (DVUC) requirements.In this paper, we explore pre-trained VLMs' potential in multimodal question answering for long-form videos. We propose a solution called Dual Branches Video Modeling (DBVM), which combines knowledge graph (KG) and VLMs, leveraging their strengths and addressing shortcomings.The KG branch recognizes and localizes entities, fuses multimodal features at different levels, and constructs KGs with entities as nodes and relationships as edges.The VLM branch applies a selection strategy to adapt input movies into acceptable length and a cross-matching strategy to post-process results providing accurate scene descriptions.Experiments conducted on the DVUC dataset validate the effectiveness of our DBVM.
Automatic emotion recognition has a wide range of applications in human-computer interaction. In this paper, we present our work in the Multimodel Emotion Recognition (MER) 2023, which contains three sub-challenges: MER-MULTI, MER-NOISE, and MER-SEMI. We first use a vanilla semi-supervised method to mine high quality samples from the MER-SEMI unlabeled dataset to expand the training set. Specifically, we ensemble three models trained with the official training set by a majority voting method, which is used to select samples with high prediction consistency. The selected samples together with the original training set are further augmented by adding noise. Then, the features of different modalities of expanded dataset are extracted from several pre-trained or fine-tuned models, and they are subsequently used to create different feature combinations to capture more effective emotion representations. Besides, we employ early fusion of different modal features and late fusion of different recognition models to obtain the final prediction. Experimental results show that our proposed method improves the performance over the official baselines by 30.4%, 55.3% and 1.57% for the three sub-challenges and ranks 4, 3, and 5, respectively. The present work sheds light on high-quality data mining and model ensemble by majority voting for multimodal emotion recognition.
Human facial expressions can convey a great deal of information in daily life. Spotting macro-expression (MaE) and micro-expression (ME) intervals from long video sequences is a difficult challenge. In this paper, we propose an efficient framework for the expression spotting task. This framework consists of three main modules: Face Cropping and Alignment Module (FCAM), optical flow Feature Extraction Module (FEM), and expression Proposal Generation Module (PGM). The noise of optical flow features is reduced by face cropping and alignment, and the Main Directional Mean Optical Flow Feature of the regions of interest is extracted as the feature for expression spotting. Finally, the expression intervals are spotted by our designed expression proposal generation module. Our approach achieves very good results on the SAMM Long Videos and CAS(ME)^2. To demonstrate the transferability of our method, we tested it on the MEGC2023 unseen dataset and finally achieved the third place, proving the effectiveness of our method.
This paper presents a framework for generating appropriate facial expressions for a listener engaged in a dyadic conversation. The ability to produce contextually suitable facial gestures in response to user interactions may enhance the user experience for avatars and social robots interaction. We propose a Transformer and Siamese architecture-based approach for generating appropriate facial expressions. Positive and negative Speaker-Listener pairs are created, applying a contrastive loss to facilitate learning. Furthermore, an ensemble of reconstruction quality sensitive loss functions is added to the network for learning discriminative features. The listener's facial reactions are represented with a combination of the 3D Morphable Model's coefficients and affect-related attributes (facial action units). The inputs to the network are pre-trained Transformer-based feature MARLIN and affect-related features. Experimental analysis demonstrate the effectiveness of the proposed method across various metrics in the form of an increase in performance compared to a variational auto-encoder-based baseline.
In this paper, we propose a novel framework for recognizing both discrete and dimensional emotions. In our framework, deep features extracted from foundation models are used as robust acoustic and visual representations of raw video. Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion. Then, we introduce a joint decoding structure for emotion classification and valence regression in the decoding stage. A multi-task loss based on uncertainty is also designed to optimize the whole process. Finally, by combining three different structures on the posterior probability level, we obtain the final predictions of discrete and dimensional emotions. When tested on the dataset of multimodal emotion recognition challenge (MER 2023), the proposed framework yields consistent improvements in both emotion classification and valence regression. Our final system achieves state-of-the-art performance and ranks third on the leaderboard on MER-MULTI sub-challenge.
MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings
PDF ↗Bodily behavioral language is an important social cue, and its automated analysis helps in enhancing the understanding of artificial intelligence systems. Furthermore, behavioral language cues are essential for active engagement in social agent-based user interactions. Despite the progress made in computer vision for tasks like head and body pose estimation, there is still a need to explore the detection of finer behaviors such as gesturing, grooming, or fumbling. This paper proposes a multiview attention fusion method named MAGIC-TBR that combines features extracted from videos and their corresponding Discrete Cosine Transform coefficients via a transformer-based approach. The experiments are conducted on the BBSI dataset and the results demonstrate the effectiveness of the proposed feature fusion with multiview attention. The code is available at: https://github.com/surbhimadan92/MAGIC-TBR
DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation
PDF ↗Conversational engagement estimation is posed as a regression problem, entailing the identification of the favorable attention and involvement of the participants in the conversation. This task arises as a crucial pursuit to gain insights into human's interaction dynamics and behavior patterns within a conversation. In this research, we introduce a dilated convolutional Transformer for modeling and estimating human engagement in the MULTIMEDIATE 2023 competition. Our proposed system surpasses the baseline models, exhibiting a noteworthy 7% improvement on test set and 4% on validation set. Moreover, we employ different modality fusion mechanism and show that for this type of data, a simple concatenated method with self-attention fusion gains the best performance.
In this paper, we present the solution of our team HFUT-VUT for the MultiMediate Grand Challenge 2023 at ACM Multimedia 2023. The solution covers three sub-challenges: bodily behavior recognition, eye contact detection, and next speaker prediction. We select Swin Transformer as the baseline and exploit data augmentation strategies to address the above three tasks. Specifically, we crop the raw video to remove the noise from other parts. At the same time, we utilize data augmentation to improve the generalization of the model. As a result, our solution achieves the best results of 0.6262 for bodily behavior recognition in terms of mean average precision and the accuracy of 0.7771 for eye contact detection on the corresponding test set. In addition, our approach also achieves comparable results of 0.5281 for the next speaker prediction in terms of unweighted average recall.
Human emotion understanding is pivotal in making conversational technology mainstream. We view speech emotion understanding as a perception task which is a more realistic setting. With varying contexts (languages, demographics etc.) different share of people perceive the same speech segment as a non-unanimous emotion. As part of the ACM Multimedia 2023 Computational Paralinguistics ChallengE (ComParE) in the EMotion Share track, we leverage their rich dataset of multilingual speakers and multi-label regression target of 'emotion share' or perception of that emotion. We demonstrate that the training scheme of different foundation models dictates their effectiveness for tasks beyond speech recognition, especially for non-semantic speech tasks like emotion understanding. This is a very complex task due to multilingual speakers, variability in the target labels, and inherent imbalance in the regression dataset. Our results show that HuBERT-Large with a self-attention-based light-weight sequence model provides 4.6% improvement over the reported baseline.
We propose the Unified Transformer for Facial Reaction GeneratioN (UniFaRN) framework for facial reaction prediction in dyadic interactions. Given the video and audio of one side, the task is to generate facial reactions of the other side. The challenge of the task lies in the fusion of multi-modal inputs and balancing appropriateness and diversity. We adopt the Transformer architecture to tackle the challenge by leveraging its flexibility of handling multi-modal data and ability to control the generation process. By successfully capturing the correlations between multi-modal inputs and outputs with unified layers and balancing the performance with sampling methods, we have won first place in the REACT2023 challenge.