Call for Submissions: ACM ToMM 2024 Special Issue on Deep Multimodal Generation and Retrieval
=======================================
**Call for Submissions:**
We are holding a Special Issue on Deep Multimodal Generation and Retrieval at ACM Transactions on Multimedia Computing, Communications, and Applications (ToMM). We solicit submissions for the special issue.
Recent advancements in Artificial Intelligence Generated Content (AIGC) have spotlighted two main strategies, information generation (IG) and information retrieval (IR), which respectively synthesize new content or search existing data to answer user queries. Despite successes in textual data, the full potential of IG and IR is limited by the underutilization of diverse data sources across various modalities. The push for deep multimodal learning aims to harness text, images, audio, and video for richer IG and IR applications, as demonstrated by technologies like DALL-E, GPT-4V, and Sora. However, challenges remain in aligning and fusing semantic features across modalities without redundancy, and in developing robust systems capable of handling real-world multimodal inputs. Addressing these issues, alongside exploring large-scale multimodal language models and structured metadata extraction, presents significant opportunities for enhancing multimodal IG and IR.
This special issue of ACM ToMM focuses on 'Deep Multimodal Generation and Retrieval' with the objective of advancing the field by uniting researchers and practitioners, fostering collaboration. It aims to promote the exchange of ideas and best practices between academia and industry, narrowing the gap in multimodal information generation and retrieval standards. Official call-for-paper: https://dl.acm.org/pb-assets/static_journal_pages/tomm/pdf/ACM-SI_ToMM_M...
=======================================
**Topics:**
The main topics covered in this special issue (but not limited to) are shown as follows:
• Vision-Language Alignment Learning; Multimodal Fusion and Embeddings
• Commonsense-aware Vision-Language Learning
• Semantic-aware Vision-Language Discovery
• Multimodal Large Language Models (MLLMs); Large-scale Vision-Language Pre-training; Visually Grounded Interaction of Language Modeling
• Text-free/conditioned Image/Video Synthesis; Temporal Coherence in Video Generation; Image/Video Editing/Inpainting; LLM-empowered Multimodal Generation
• Multimodal Dialogue Response Generation; Image/Video Dialogue
• Image/Video-Text Compositional Retrieval; Video Moment Retrieval; Multimodal Retrieval with MLLMs
• Image/Video Captioning; Image/Video Question Answering
• Image/Video Relation Detection; Multimodal Event/Situation Recognition
• Hybrid Synthesis with Retrieval and Generation
• Explainable Multimodal Retrieval; Relieving Hallucination of LLMs; Adversarial Attack and Defense; Efficient Learning of MLLMs
• New Benchmark; New Evaluation Metrics
• Multimodal-based Reasoning; Multimodal Instruction Tuning
=======================================
**Important Date:**
• Open for submissions: Jan 10, 2024
• Submission deadline: Jun 15, 2024
• First-round review decisions: Aug 15, 2024
• Deadline for revision submissions: Sep 30, 2024
• Notification of final decisions: Oct 30, 2024
• Tentative publication: Dec 30, 2024
=======================================
**Submission Site:**
https://mc.manuscriptcentral.com/tomm
Prospective authors are invited to submit their manuscripts electronically adhering to the ACM ToMM journal guidelines (see https://tomm.acm.org/authors.cfm). Please select “SI: Deep Multimodal Generation and Retrieval”.
=======================================
**Organization Committee:**
• Hao Fei, National University of Singapore, Singapore, haofei37@nus.edu.sg
• Wei Ji, National University of Singapore, Singapore, jiwei@nus.edu.sg
• Yinwei Wei, Monash University, Australia, weiyinwei@hotmail.com
• Zhedong Zheng, University of Macau, Macau, China, zhedongzheng@um.edu.mo
• Jerry Jialie Shen, City, University of London, UK, jialie.shen.2@city.ac.uk
• Alan Hanjalic, Delft University of Technology, Netherlands, A.Hanjalic@tudelft.nl
• Roger Zimmermann, National University of Singapore, Singapore, dcsrz@nus.edu.sg
=======================================