Program: Thursday, June 30



Local time (NJ, USA) Thursday, June 30
7:00 am - 7:30 am Breakfast
7:30 am - 8:00 am
8:00 am - 8:30 am
8:30 am - 9:00 am Full Paper Session 5A: Applications Full Paper Session 5B: Robust MM Full Paper Session 5C: Action, Pose and Body
9:00 am - 9:30 am
9:30 am - 10:00 am
10:00 am - 10:30 am Break
10:30 am - 11:00 am Full Paper Session 6: Multifarious Multimedia Special Session 2A: Transformer-based Multimedia Understanding: Model Design, Learning, Distillation Special Session 3A: Weakly Supervised Learning for Medical Image Analysis
11:00 am - 11:30 am
11:30 am - 12:00 pm
12:00 pm - 12:30 pm Lunch Break
12:30 pm - 1:00 pm
1:00 pm - 1:30 pm Special Session 1: Adversarial Learning for Multimedia Understanding and Retrieval Special Session 2B: Transformer-based Multimedia Understanding: Model Design, Learning, Distillation Special Session 3B: Weakly Supervised Learning for Medical Image Analysis
1:30 pm - 2:00 pm
2:00 pm - 2:30 pm Doctoral Symposium
2:30 pm - 3:00 pm Break
3:00 pm - 3:30 pm Keynote 2 + Closing Remarks
3:30 pm - 4:00 pm
4:00 pm - 4:30 pm

Full Paper Session 5A: Applications

Session chair: Panagiotis Giannakeris, Room: CKB Agile Lab

  • Shanchuan Gao, Fankai Zeng, Lu Cheng, Jicong Fan and Mingbo Zhao. “Fashion Image Search via Anchor-Free Detector”
  • Jingyu Li, Haokai Ma, Xiangxian Li, Zhuang Qi, Lei Meng and Xiangxu Meng. “Unsupervised Contrastive Masking for Visual Haze Classification”
  • Anwer Slimi, Mounir Zrigui and Henri Nicolas. “MuLER: Multiplet-Loss for Emotion Recognition”
  • Xingyu Zhu, Yingshuo Liang, Jianlei Zhang and Zengqiang Chen. “STAFNet: Swin Transformer Based Anchor-Free Network For Detection Of Forward-looking Sonar Imagery”

Full Paper Session 5B: Robust MM

Session chair: Cathal Gurrin, Room: CKB 116

  • Chao Jiang, Yi He, Richard Chapman and Hongyi Wu. “Camouflaged Poisoning Attack on Graph Neural Networks”
  • Siyuan Li, Guangji Huang, Xing Xu, Yang Yang and Fumin Shen. “Accelerated Sign Hunter: a Sign-based Black-box Attack via Branch-Prune Strategy and Stabilized Hierarchical Search”
  • Zhen Luo, Yingfang Zhang, Peihao Zhong, Jingjing Chen and Donglong Chen. “DiGAN: Directional Generative Adversarial Network for Object Transfiguration”
  • Xiaoheng Sun, Xia Liang, Qiqi He, Bilei Zhu and Zejun Ma. “GIO: A Timbre-informed Approach for Pitch Tracking in Highly Noisy Environments”

Full Paper Session 5C: Action, Pose and Body

Session chair: Silvan Heller, Room: CKB 217

  • Peipeng Chen and Andy J Ma. “Source-free Temporal Attentive Domain Adaptation for Video Action Recognition”
  • Neng Zhou, Hairu Wen, Yi Wang, Yang Liu and Longfei Zhou. “Review of Deep Learning Models for Spine Segmentation”
  • Zhidan Liu, Zhen Xing, Xiangdong Zhou, Yijiang Chen and Guichun Zhou. “3D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimation”
  • Yiran Zhu, Guangji Huang, Xing Xu, Yanli Ji and Fumin Shen. “Selective Hypergraph Convolutional Networks for Skeleton-based Action Recognition”

Full Paper Session 6: Multifarious Multimedia

Session chair: Yi He, Room: CKB Agile Lab

Due to this session being five presentations, it might extend a bit into the lunch break (approx. until 12:15 PM).

  • Guangyu Chen, Deyuan Zhang, Tao Liu and Xiaoyong Du. “Self-Lifting: A Novel Framework For Unsupervised Voice-Face Association Learning”
  • Hongya Wang, Shunxin Dai, Ming Du, Bo Xu and Mingyong Li. “Revisiting Performance Measures for Cross-Modal Hashing”
  • Yifeng Zhuang, Qiang Sun, Yanwei Fu, Lifeng Chen and Xiangyang Xue. “Local Slot Attention for Vision and Language Navigation”
  • Yuhui Guo, Xun Liang, Tang Hui, Bo Wu and Xiangping Zheng. “Cross-Pixel Dependency with Boundary-Feature Transformation for Weakly Supervised Semantic Segmentation”
  • Kangning Yang, Benjamin Tag, Yue Gu, Chaofan Wang, Tilman Dingler, Greg Wadley and Jorge Goncalves. “Mobile Emotion Recognition via Multiple Physiological Signals using Convolution-augmented Transformer”

Special Session 2A: Transformer-based Multimedia Understanding: Model Design, Learning, Distillation

Session chair: Yunqiu Xu (online), Room: CKB 116

  • Guangqi Jiang, Huibing Wang, Jinjia Peng and Xianping Fu. “Parallelism Network with Partial-aware and Cross-correlated Transformer for Vehicle Re-identification”
  • Siqi Sun, Yongqing Sun, Mitsuhiro Goto, Shigekuni Kondo, Dan Mikami and Susumu Yamamoto. “Motor learning based on presentation of a tentative goal”
  • Kui Xiao, Youheng Bai and Yan Zhang. “Extracting Precedence Relations between Video Lectures in MOOCs”
  • Junke Wang, Zuxuan Wu, Wenhao Ouyang, Xintong Han, Jingjing Chen, Yu-Gang Jiang and Ser-Nam Li. “M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection”

Special Session 3A: Weakly Supervised Learning for Medical Image Analysis

Session chair: Kai Hu (online), Room: CKB 217

  • Yue Wu, Yang Zhou, Jianchun Zhao, Jingyuan Yang, Weihong Yu, Youxin Chen and Xirong Li. “Lesion Localization in OCT by Semi-Supervised Object Detection”
  • Yunyan Yan, Chuanbin Liu, Hongtao Xie, Sicheng Zhang and Zhendong Mao. “Weakly Supervised Pediatric Bone Age Assessment Using Ultrasonic Images via Automatic Anatomical RoI Detection”
  • Chao Suo, Xuanya Li, Donghui Tan, Yuan Zhang and Xieping Gao. “I^2-Net: Intra- and Inter-scale Collaborative Learning Network for Abdominal Multi-organ Segmentation”
  • Fenxia Duan, Chunhong Cao and Xieping Gao. “SA-NAS-BFNR: Spatiotemporal Attention Neural Architecture Search for Task-based Brain Functional Network Representation”

Special Session 1: Adversarial Learning for Multimedia Understanding and Retrieval

Session chair: Shuihua Wang (online), Room: CKB Agile Lab

  • Weidong Shi, Yunzhou Zhang, Shangdong Zhu, Yixiu Liu, Sonya Coleman and Dermot Kerr. “VAC-Net: Visual Attention Consistency Network for PersonRe-identification”
  • Lijia Deng and Yu-Dong Zhang. “MFGAN: A lightweight fast multi-task multi-scale feature-fusion model based on GAN”
  • Zhipeng Wei, Jingjing Chen, Hao Zhang, Linxi Jiang and Yu-Gang Jiang. “Adaptive Temporal Grouping For Black-box Adversarial Attacks on Videos”
  • Panel discussion

Special Session 2B: Transformer-based Multimedia Understanding: Model Design, Learning, Distillation

Session chair: Bo Fu (online), Room: CKB 116

  • Bo Fu, Yuanxin Mao, Shilin Fu, Yonggong Ren and Zhongxuan Luo. “Blindfold Attention: Novel Mask Strategy for Facial Expression Recognition”
  • Lei Zhu, Liewu Cai, Jiayu Song, Xinghui Zhu, Chengyuan Zhang and Shichao Zhang. “MSSPQ: Multiple Semantic Structure-Preserving Quantization for Cross-Modal Retrieval”
  • Panel discussion

Special Session 3B: Weakly Supervised Learning for Medical Image Analysis

Session chair: Zhineng Chen (online), Room: CKB 217

  • Qian Wu, Yufei Chen, Ning Huang and Xiaodong Yue. “Weakly-supervised Cerebrovascular Segmentation Network with Shape Priori and Model Indicator”
  • Panel discussion

Doctoral symposium

Session chairs: Ilaria Bartolini + Yi Yu (online), Room: CKB Agile Lab

  • Runsheng Zhang. “FreqCAM: Frequent Class Activation Map for Weakly Supervised object localization”

Keynote 2 + Closing Remarks

Session chairs: Vincent Oria + Shin’ichi Satoh (General chairs), Room: CKB Agile Lab


ACM ICMR 2022, Newark, NJ, United States. Copyright © 2022 All rights reserved.