Grand Challenges Program
Grand Challenges Part 1 (10:30-12:30)
15 min per paper, including Q&A; 30 min for organizers presentations, including Q&A
10:30-11:00 – ACM Multimedia Computational Paralinguistics Challenge (ComParE) Organizers presentation, paper mmgc052i, The ACM Multimedia 2023 Computational Paralinguistics Challenge: Emotion Share & Requests (Presenter: Shahin Amiriparian)
11:00-11:15: Paper mmgc011, Cascaded Cross-Modal Transformer for Request and Complaint Detection
11:15-11:30: Paper mmgc013, Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference
11:30-11:45: Paper mmgc 017, Multi-Layer Acoustic & Linguistic Feature Fusion for ComParE-23 Emotion and Requests Challenge
11:45-12:00: Paper mmgc 021, Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks
12:00-12:30: Paper mmgc50i, SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge(Presenter: Bo Wu)
Grand Challenges Part 2 (13:30-15:00)
15 min per paper, including Q&A; 30 min for organizers presentations, including Q&A
13:30-14:00: Multi-modal Behaviour Analysis for Artificial Mediation (MultiMediate) Organizers presentation, paper mmgc43i, MultiMediate ’23: Engagement Estimation and Bodily Behaviour Recognition in Social Interactions (Presenters Philip Mueller and Michal Balazia)
14:00-14:15: Paper mmgc025, MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings (Presenter: Surbhi Madan)
14:15-14:30: Paper mmgc024, DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation (Presenter: proxy)
14:30-14:45: Paper mmgc027, BEAMER: Behavioral Encoder to Generate Multiple Appropriate Facial Reactions (Presenter: proxy)
14:45-15:00: Paper mmgc008, Gradient Boost Tree Network based on Extensive Feature Analysis for Popularity Prediction of Social Posts (Presenter: Chia-Ming Li)
Grand Challenges Part 3 (15:30-17:30)
15 min per paper, including Q&A; 30 min for organizers presentations, including Q&A
15:30-16:00: Deep Video Understanding (DVU) 2023 Organizers presentation, paper mmgc044i, The ACM Multimedia 2023 Deep Video Understanding Grand Challenge (Presenter: George Awad)
16:00-16:30: Facial Micro-Expression Grand Challenge Organizers presentation, paper mmgc049i, MEGC2023: ACM Multimedia 2023 ME Grand Challenge (Presenter: Adrian Davison)
16:30-16:45: Paper mmgc028 , Efficient Micro-Expression Spotting Based on Main Directional Mean Optical Flow Feature (Presenter: proxy)
16:45-17:00: Paper mmgc010, Double-Fine-Tuning Multi-Objective Vision-and-Language Transformer for Social Media Popularity Prediction (Presenter: Weilong Chen)
17:00-17:30: Time for discussion
Videos are available on Conflux System for all Grand Challenges papers, as listed below:
| mmgc002 | Finetuning Language Models for Multimodal Question Answering |
| mmgc003 | A Hierarchical Deep Video Understanding Method with Large Language Model |
| mmgc004 | Enhanced CatBoost with Stacking Features for Social Media Prediction |
| mmgc005 | Semi-Supervised Multimodal Emotion Recognition with Expression MAE |
| mmgc006 | Towards Realistic Conversational Head Generation: A Comprehensive Framework for Lifelike Video Synthesis |
| mmgc007 | Invisible Video Watermark Method Based on Maximum Voting and Probabilistic Superposition |
| mmgc008 | Gradient Boost Tree Network based on Extensive Feature Analysis for Popularity Prediction of Social Posts |
| mmgc009 | VTQAGen: BART-based Generative Model For Visual Text Question Answering |
| mmgc010 | Double-Fine-Tuning Multi-Objective Vision-and-Language Transformer for Social Media Popularity Prediction |
| mmgc011 | Cascaded Cross-Modal Transformer for Request and Complaint Detection |
| mmgc012 | Multi-scale Conformer Fusion Network for Multi-participant Behavior Analysis |
| mmgc013 | Advancing Audio Emotion and Intent Recognition with Large Pre-Trained Models and Bayesian Inference |
| mmgc014 | Automatic Audio Augmentation for Requests Sub-Challenge |
| mmgc016 | Answer-Based Entity Extraction and Alignment for Visual Text Question Answering |
| mmgc017 | Multi-Layer Acoustic & Linguistic Feature Fusion for ComParE-23 Emotion and Requests Challenge |
| mmgc018 | Sliding Window Seq2seq Modeling for Engagement Estimation |
| mmgc019 | Micro-Expression Spotting with Face Alignment and Optical Flow |
| mmgc020 | UniFaRN: Unified Transformer for Facial Reaction Generation |
| mmgc021 | Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks |
| mmgc023 | Data Augmentation for Human Behavior Analysis in Multi-Person Conversations |
| mmgc024 | DCTM: Dilated Convolutional Transformer Model for Multimodal Engagement Estimation in Conversation |
| mmgc025 | MAGIC-TBR: Multiview Attention Fusion for Transformer-based Bodily Behavior Recognition in Group Settings |
| mmgc026 | Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023 |
| mmgc027 | BEAMER: Behavioral Encoder to Generate Multiple Appropriate Facial Reactions |
| mmgc028 | Efficient Micro-Expression Spotting Based on Main Directional Mean Optical Flow Feature |
| mmgc030 | Mining High-quality Samples from Raw Data and Majority Voting Method for Multimodal Emotion Recognition |
| mmgc031 | Deep Video Understanding with Video-Language Model |
| mmgc032 | Semi-Supervised Multimodal Emotion Recognition with Class-Balanced Pseudo-labeling |
| mmgc033 | Leveraging the Latent Diffusion Models for Offline Facial Multiple Appropriate Reactions Generation |
| mmgc034 | Improvements on SadTalker-based Approach for ViCo Conversational Head Generation Challenge |
| mmgc035 | Multimodal Emotion Recognition in Noisy Environment Based on Progressive Label Revision |
| mmgc036 | Integrating VideoMAE based model and Optical Flow for Micro- and Macro-expression Spotting |
| mmgc037 | Hierarchical Semantic Perceptual Listener Head Video Generation: A High-performance Pipeline |
| mmgc038 | Unveiling Subtle Cues: Backchannel Detection Using Temporal Multimodal Attention Networks |
| mmgc039 | Query-aware Long Video Localization and Relation Discrimination for Deep Video Understanding |
| mmgc040 | Building Robust Multimodal Sentiment Recognition via a Simple yet Effective Multimodal Transformer |
| mmgc041 | MultiMediate 2023: Engagement Level Detection using Audio and Video Features |
| mmgc044i | The ACM Multimedia 2023 Deep Video Understanding Grand Challenge |
| mmgc045i | MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning |
| mmgc046i | Learning and Evaluating Human Preferences for Conversational Head Generation |
| mmgc047i | REACT2023: The First Multiple Appropriate Facial Reaction Generation Challenge |
| mmgc049i | MEGC2023: ACM Multimedia 2023 ME Grand Challenge |
| mmgc051i | ACM Multimedia 2023 Grand Challenge Report: Invisible Video Watermark |
| mmgc052i | The ACM Multimedia 2023 Computational Paralinguistics Challenge: Emotion Share & Requests |
| mmgc43i | <sc>MultiMediate ’23:</sc> Engagement Estimation and Bodily Behaviour Recognition in Social Interactions |
| mmgc48i | VTQA2023: ACM Multimedia 2023 Visual Text Question Answering Challenge |
| mmgc50i | SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge |