Program Overview

MON 12 Jun Workshops & Tutorial
08:30 – 09:00 Registration Open
09:00 – 10:30 ICDAR ’23 MAD ’23 Tutorial
10:30 – 11:00 Coffee Break
11:00 – 13:00 ICDAR ’23 MAD ’23 Tutorial
13:00 – 14:00 Lunch
14:00 – 15:40 ICDAR ’23 MAD ’23 LSC ’23
15:40 – 16:00 Coffee Break
16:00 – 17:00 ICDAR ’23 MAD ’23 LSC ’23
17:00 – 19:30 LSC ’23
19:30 – 21:30 Reception
TUE 13 Jun DAY 1
08:30 – 09:00 Registration Open
09:00 – 09:30 Welcome to ICMR 2023
09:30 – 10:30 Keynote 1: “How Responsible LLMs are beneficial to search and exploration in Retail industry”, Nozha Boujemaa (IKEA Retail)
10:30 – 11:00 Coffee Break
11:00 – 13:00 Oral Long Paper – Session 1 (Emerging Topics in Multimedia)
13:00 – 14:00 Lunch
14:00 – 15:40 Oral Long Paper – Session 2 (Best Paper Candidates)
15:40 – 16:10 Coffee Break
16:10 – 17:20 Oral – BNI & Doctoral Symposium & Reproducibility Papers
WED 14 Jun DAY 2
08:30 – 09:00 Registration Open
09:00 – 10:00 Keynote 2: “Efficient CNNs and Transformers for Video Understanding and Image Synthesis”, Jürgen Gall (Univ. Bonn)
10:00 – 10:30 Spotlight presentations for LP Poster & Demo Part 1 afternoon session
10:30 – 11:00 Coffee Break
11:00 – 12:00 Oral Long Paper – Session 3 (Media Synthesis)
12:00 – 13:00 Panel
13:00 – 14:00 Lunch
14:00 – 15:20 Oral Long Paper – Session 4 (Multimedia Verification)
15:20 – 15:50 Spotlight presentations for LP Poster & Demo Part 2 afternoon session
15:50 – 16:10 Coffee Break
16:10 – 17:40 Poster Session: Long Papers and Technical Demonstrations Online Papers Session 1 (in parallel to poster session)
THU 15 Jun DAY 3
08:30 – 09:00 Registration Open
09:00 – 10:00 Keynote 3: “Recognizing actions in videos under domain shift”, Elisa Ricci (Univ. Trento)
10:00 – 10:50 Spotlight presentations for Short Paper poster afternoon session
10:50 – 11:20 Coffee Break
11:20 – 13:00 Oral Long Paper – Session 5 (Retrieval)
13:00 – 14:00 Lunch
14:00 – 15:40 Oral Long Paper – Session 6 (Learning)
15:40 – 16:10 Coffee Break
16:10 – 17:40 Poster Session: Short Papers Online Papers Session 2 (in parallel to poster session)

Tuesday 13 June – Day 1

Oral Long Paper – Session 1 (Emerging Topics in Multimedia)

  1. Nitish Nag, Hyungik Oh, Mengfan Tang, Mingshu Shi and Ramesh Jain, Integrative Multi-Modal Computing for Personal Health Navigation
  2. Hugo Schindler, Adrian Popescu, Khoa Nguyen and Jerome Deshayes-Chossart, Raising User Awareness about the Consequences of Online Photo Sharing
  3. Sven Schultze, Ani Withöft, Larbi Abdenebaoui and Susanne Boll, Explaining Image Aesthetics Assessment: An Interactive Approach
  4. Omar Adjali, Paul Grimal, Olivier Ferret, Sahar Ghannay and Hervé Le Borgne, Explicit Knowledge Integration for Knowledge-Aware Visual Question Answering about Named Entities
  5. Shuo Chen, Yingjun Du, Pascal Mettes and Cees Snoek, Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation
  6. Ying He, Gongqing Wu, Desheng Cai and Xuegang Hu, Cross-View Sample-Enriched Graph Contrastive Learning Network for Personalized Micro-video Recommendation

Oral Long Paper – Session 2 (Best Paper Candidates)

  1. Konstantin Schall, Kai Uwe Barthel, Nico Hezel and Klaus Jung, Improving Image Encoders for General-Purpose Nearest Neighbor Search and Classification
  2. Giacomo Nebbia and Adriana Kovashka, Hypernymization of Named Entity-rich captions for grounding-based multi-modal pretraining.
  3. Yizhao Gao and Zhiwu Lu, CMMT: Cross-Modal Meta-Transformer for Video-Text Retrieval
  4. Jiazhi Guan, Hang Zhou, Zhizhi Guo, Tianshu Hu, Lirui Deng, Meng Fang, Chengbin Quan and Youjian Zhao, Dual-Modality Co-Learning for Unveiling Deepfake in Spatio-Temporal Space
  5. Jiaxin Deng, Dong Shen, Haojie Pan, Xiangyu Wu, Ximan Liu, Gaofeng Meng, Fan Yang, Size Li, Ruiji Fu and Zhongyuan Wang, A Unified Model for Video Understanding and Knowledge Embedding with Heterogeneous Knowledge Graph Dataset

Oral – BNI & Doctoral Symposium & Reproducibility Papers

  1. David Alonso del Barrio and Daniel Gatica-Perez, Framing the News: From Human Perception to Large Language Model Inferences (Brave New Ideas)
  2. Shenshen Li, Dual-Path Semantic Construction Network for Composed Query-Based Image Retrieval (Doctoral Symposium)
  3. Mitchell Lee, Chris Lee, Sanjay Penmetsa, Min Chen, Mizuki Miyashita and Naatosi Fish, Reproducibility Companion Paper: MeTILDA – Platform for Melodic Transcription in Language Documentation and Application (Reproducibility)
  4. Daichi Suzuki, Go Irie and Kiyoharu Aizawa, Text-to-Image Fashion Retrieval with Fabric Textures (Short Paper)

Wednesday 14 June – Day 2

Spotlight presentations for LP Poster & Demo Part 1 afternoon session

  • Long Paper Posters 1 – 11 will be presented (2′ each)

Oral Long Paper – Session 3 (Media Synthesis)

  1. Chiyu Zhang, Yang Jun, Zaiyan Dai and Peng Cao, Edge Enhanced Image Style Transfer via Transformers
  2. Juheon Hwang, Jiwoo Kang, Kyoungoh Lee and Sanghoon Lee, Unlocking Potential of 3D-aware GAN for More Expressive Face Generation
  3. Yuze Wang, Junyi Wang, Yansong Qu and Yue Qi, RIP-NeRF: Learning Rotation-Invariant Point-based Neural Radiance Field for Fine-grained Editing and Compositing

Oral Long Paper – Session 4 (Multimedia Verification)

  1. Tiancong Cheng, Ying Zhang, Yifang Yin, Roger Zimmermann, Zhiwen Yu and Bin Guo, A Multi-Teacher Assisted Knowledge Distillation Approach for Enhanced Face Image Authentication
  2. Ying Zhang, Lilei Zheng, Vrizlynn Thing, Roger Zimmermann, Bin Guo and Zhiwen Yu, FaceLivePlus: A Unified System for Face Liveness Detection and Face Verification
  3. Bing Han, Jianshu Li, Wenqi Ren, Man Luo, Jian Liu and Xiaochun Cao, SIGMA-DF: Single-Side Guided Meta-Learning for Deepfake Detection
  4. Yizhe Zhu, Jialin Gao and Xi Zhou, AVForensics: Audio-driven Deepfake Video Detection with Masking Strategy in Self-supervision

Spotlight presentations for LP Poster & Demo Part 2 afternoon session

  • Long Paper Posters 12 – 17 and Technical Demonstrations Posters 1 – 5 will be presented (2′ each)

Poster Session: Long Papers and Technical Demonstrations

Long Paper

  1. Marco Arazzi, Marco Cotogni, Antonino Nocera and Luca Virgili, Predicting Tweet Engagement with Graph Neural Networks
  2. Peiwang Tang, Qinghua Zhang and Xianchao Zhang, A Recurrent Neural Network based Generative Adversarial Network for Long Multivariate Time Series Forecasting
  3. Victoria Sherratt, Kevin Pimbblet and Nina Dethlefs, Multi-channel Convolutional Neural Network for Precise Meme Classification
  4. Yankun Wu, Yuta Nakashima and Noa Garcia, Not Only Generative Art: Stable Diffusion for Content-Style Disentanglement in Art Analysis
  5. Wen-Jiin Tsai and Yi-Cheng Tien, Attention-based Video Virtual Try-On
  6. Soyun Choi, Youjia Zhang and Sungeun Hong, Intra-inter Modal Attention Blocks for RGB-D Semantic Segmentation
  7. Cheng-Yu Fang and Xian-Feng Han, Joint Geometric-Semantic Driven Character Line Drawing Generation
  8. Zeqing Xia and Zhouhui Lian, CurveSDF: Binary Image Vectorization Using Signed Distance Fields
  9. Yusong Wang, Dongyuan Li, Kotaro Funakoshi and Manabu Okumura, EMP: Emotion-guided Multi-modal Fusion and Contrastive Learning for Personality Traits Recognition
  10. Zefan Zhang, Yi Ji and Chunping Liu, Knowledge-Aware Causal Inference Network for Visual Dialog
  11. Chun Zhang, Keyan Ren, Qingyun Bian and Yu Shi, Decoupled High-Semantic Encoding for Action Recognition
  12. Han Wang and Ziwei Xiong, Dual-Stream Multimodal Learning for Topic-Adaptive Video Highlight Detection
  13. Ruilin Zhang, Haiyang Zheng and Hongpeng Wang, TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information
  14. Beibei Zhang, Yaqun Fang, Fan Yu, Jia Bei and Tongwei Ren, MMSF: A Multimodal Sentiment-Fused Method to Recognize Video Speaking Style
  15. Guoxing Yang, Haoyu Lu, Zelong Sun and Zhiwu Lu, Shot Retrieval and Assembly with Text Script for Video Montage Generation
  16. Shenshen Li, Xing Xu, Fumin Shen and Yang Yang, Multi-granularity Separation Network for Text-Based Person Retrieval with Bidirectional Refinement Regularization
  17. Tiening Sun, Zhong Qian, Peifeng Li and Qiaoming Zhu, Graph Interactive Network with Adaptive Gradient for Multi-Modal Rumor Detection

Technical Demonstrations

  1. Kento Terauchi and Keiji Yanai, CalorieCam360: Simultaneous Eating Action Recognition of Multiple People Using Omnidirectional Camera
  2. Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Fabrizio Falchi, Claudio Gennaro, Nicola Messina, Lucia Vadicamo and Claudio Vairo, VISIONE: A Large-Scale Video Retrieval System with Advanced Search Functionalities
  3. Kai Uwe Barthel, Nico Hezel, Konstantin Schall and Klaus Jung, NAvigation in Visual Image Graphs gets User-friendly
  4. Manos Schinas, Panagiotis Galopoulos and Symeon Papadopoulos, MAAM: Media Asset Annotation and Management
  5. Stefanos Stoikos, David Kauchak, Douglas Turnbull and Alexandra Papoutsaki, Cross-Language Music Recommendation Exploration

Online Papers Session 1 (in parallel to poster session)

  1. Harsh Sinha and Adriana Kovashka, Towards shape-regularized learning for mitigating texture bias in CNNs
  2. Mingqi Chen, Feng Shuang, Shaodong Li and Xi Liu, ASCS-Reinforcement Learning: A Cascaded Framework for Accurate 3D Hand Pose Estimation
  3. Yangming Zhou, Yuzhou Yang, Qichao Ying, Zhenxing Qian and Xinpeng Zhang, Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion
  4. Mingjun Li, Shuo Xu and Feng Su, Learning and Fusing Multi-Scale Representations for Accurate Arbitrary-Shaped Scene Text Recognition
  5. Chunhong Cao, Huawei Fu, Gai Li, Mengyang Wang and Xieping Gao, Modeling Functional Brain Networks with Multi-Head Attention-based Region-Enhancement for ADHD Classification
  6. Chunhong Cao, Gai Li, Huawei Fu, Xingxing Li and Xieping Gao, SPAE: Spatial Preservation-based Autoencoder for ADHD functional brain networks modelling
  7. Bingchao Wu, Yangyuxuan Kang, Bei Guan and Yongji Wang, We Are Not So Similar: Alleviating User Representation Collapse in Social Recommendation
  8. Pengzhi Li, Yikang Ding, Linge Li, Jingwei Guan and Zhiheng Li, Towards Practical Consistent Video Depth Estimation

Thursday 15 June – Day 3

Spotlight presentations for Short Paper poster afternoon session

  • All Short Paper Posters (1 – 16) will be presented in the same order (2′ each)

Oral Long Paper – Session 5 (Retrieval)

  1. Jiancheng Pan, Qing Ma and Cong Bai, Reducing Semantic Confusion: Scene-aware Aggregation Network for Remote Sensing Cross-modal Retrieval
  2. Jialin Tian, Xing Xu, Zuo Cao, Gong Zhang, Fumin Shen and Yang Yang, Zero-shot Sketch-based Image Retrieval with Adaptive Balanced Discriminability and Generalizability
  3. Liang Li and Weiwei Sun, Label-wise Deep Semantic-Alignment Hashing for Cross-Modal Retrieval
  4. Ying Li, Chunming Guan and Jiaquan Gao, TsP-Tran: Two-Stage Pure Transformer for Multi-Label Image Retrieval
  5. Maria Pegia, Björn Þór Jónsson, Anastasia Moumtzidou, Ilias Gialampoukidis, Stefanos Vrochidis and Ioannis Kompatsiaris, MuseHash: Supervised Bayesian Hashing for Multimodal Image Representation

Oral Long Paper – Session 6 (Learning)

  1. Siteng Huang, Qiyao Wei and Donglin Wang, Reference-Limited Compositional Zero-Shot Learning
  2. Haram Choi, Cheolwoong Na, Jinseop Kim and Jihoon Yang, Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training
  3. Feng Zhao, Min Zhang, Tiancheng Huang and Donglin Wang, TAGM: Task-Aware Graph Model for Few-shot Node Classification
  4. Yutian Luo, Yizhao Gao and Zhiwu Lu, Learning with Adaptive Knowledge for Continual Image-Text Modeling
  5. Wenxiu Geng, Xiangxian Li and Yulong Bian, A Dual-branch Enhanced Multi-task Learning Network for Multimodal Sentiment Analysis

Poster Session: Short Papers

  1. Panagiota Alexoudi, Ioannis Mademlis and Ioannis Pitas, Escaping local minima in deep reinforcement learning for video summarization
  2. Florian Spiess, Ralph Gasser, Silvan Heller, Heiko Schuldt and Luca Rossetto, A Comparison of Video Browsing Performance between Desktop and Virtual Reality Interfaces
  3. Zhexu Shen, Liang Yang, Zhihan Yang and Hongfei Lin, More Than Simply Masking: Exploring Pre-training Strategies for Symbolic Music Understanding
  4. Pu Ching, Hung-Kuo Chu and Min-Chun Hu, SOFA: Style-based One-shot 3D Facial Animation Driven by 2D landmarks
  5. Kun He, Changyu Li and Jie Shao, Strong-Weak Cross-View Interaction Network for Stereo Image Super-Resolution
  6. Jiabao Sheng, Yuanpeng Zhang, Jing Cai, Sai-Kit Lam, Zhe Li, Jiang Zhang and Xinzhi Teng, Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction
  7. Shuiying Liao, Yujuan Ding and Pik Yin Mok, Recommendation of Mix-and-Match Clothing by Modeling Indirect Personal Compatibility
  8. Arun Zachariah and Praveen Rao, Video Retrieval for Everyday Scenes With Common Objects
  9. Nico Zhou, Tse-Yu Pan, Herman Prawiro, Jian-Wei Peng, Wen-Cheng Chen, Hung-Kuo Chu and Min-Chun Hu, Offensive Tactics Recognition in Broadcast Basketball Videos Based on 2D Camera View Player Heatmaps
  10. Meishan Liu, Meng Jian, Ge Shi and Lifang Wu, Graph Contrastive Learning on Complementary Embedding for Recommendation
  11. Sahar Tahmasebi, Sherzod Hakimov, Ralph Ewerth and Eric Müller-Budack, Improving Generalization for Multimodal Fake News Detection
  12. Christos Koutlis, Manos Schinas and Symeon Papadopoulos, MemeFier: Dual-stage modality fusion for image meme classification
  13. Aristotelis Ballas and Christos Diou, CNNs with Multi-Level Attention for Domain Generalization
  14. Werner Bailer, Rahel Arnold, Vera Benz, Davide Coccomini, Silvan Heller, Anastasios Gkagkas, Gylfi Þór Guðmundsson, Björn Þór Jónsson, Jakub Lokoc, Nicola Messina, Nick Pantelidis and Jiaxin Wu, Improving Query and Assessment Quality in Text-Based Interactive Video Retrieval Evaluation
  15. Iacopo Ghinassi, Lin Wang, Chris Newell and Matthew Purver, Multimodal Topic Segmentation of Podcast Shows with Pre-trained Neural Encoders
  16. Georgios Orfanidis, Konstantinos Ioannidis, Anastasios Tefas, Stefanos Vrochidis and Ioannis Kompatsiaris, Tweaking EfficientDet for frugal training

Online Papers Session 2 (in parallel to poster session)

  1. Yu Zang, Zhe Xue, Shilong Ou, Yunfei Long, Hai Zhou and Junping Du, FedPcf: An Integrated Federated Learning Framework with Multi-Level Prospective Correction Factor
  2. Lina Sun, Yewen Li and Yumin Dong, Learning From Expert: Vision-Language Knowledge Distillation for Unsupervised Cross-Modal Hashing Retrieval
  3. Yaoqing Li, Sheng-Hua Zhong, Shuai Li and Yan Liu, A Robust Deep Learning Enhanced Monocular SLAM System for Dynamic Environments
  4. Yingnan Fu, Wenyuan Cai, Ming Gao and Aoying Zhou, Symbol Location-Aware Network for Improving Handwritten Mathematical Expression Recognition
  5. Mingyuan Ge, Mingyong Li, Yewen Li and Longfei Ma, Deep Enhanced-Similarity Attention Cross-modal Hashing Learning (Short Paper)
  6. Feng Kai, Liu Tao, Zhang Heng, Meng Zihao and Miao Zemin, TNOD: Transformer Network with Object Detection for Tag Recommendation (Short Paper)
  7. Tianqi Zhao, Ming Kong, Tian Liang, Qiang Zhu, Kun Kuang and Fei Wu, CLAP: Contrastive Language-Audio Pre-training Model for Multi-modal Sentiment Analysis (Short Paper)