Recording

Workshop Recording

Papers

Hierarchical Spatiotemporal Transformers for Video Object Segmentation

Junsang Yoo (Korea University)*; Hongjae Lee (Korea University); Seung-Won Jung (Korea University)

A Hybrid Visual Transformer for Efficient Home-based Monitoring

Youcef Djenouri (NORCE)*; Nabil Belbachir (NORCE Norwegian Research Centre AS)

SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers

Xijun Wang (University of Maryland, College Park)*; Xiaojie Chu (Megvii Technology); Chunrui Han (ICT, Chinese Academy of Sciences, China); Xiangyu Zhang (Megvii Technology)

TSOSVNet: Teacher-student collaborative knowledge distillation for Online Signature Verification

chandra V sekhar (Indian Institute of Information Technology-SriCity)*; Viswanath P (Indian Institute of Information Technology Chittor, Sri City); Avinash Gautam (BITS Pilani); Gorthi  Rama Krishna  Sai Subrahmanyam (IIT Tirupati); Sreeja S R (IIIT Sri City)

SeMask: Semantically Masked Transformers for Semantic Segmentation

JItesh Jain (Georgia Tech)*; Anukriti Singh (University of Oregon); Nikita Orlov (PicsArt); Zilong Huang (Tencent); Jiachen Li (UIUC); Steven Walton (University of Oregon); Humphrey Shi (U of Oregon | UIUC | PAIR)

Interactive Image Segmentation with Cross-Modality Vision Transformers

Kun Li (University of Twente)*; George Vosselman ("University of Twente, the Netherlands"); Michael Ying Yang (University of Twente)

MSQNet: Actor-agnostic Action Recognition with Multi-modal Query

Anindya  Mondal (University of Surrey); Sauradip Nag (University of Surrey); Joaquin M Prada (University of Surrey); Xiatian Zhu (University of Surrey); Anjan Dutta (University of Surrey)*

Explaining through Transformer Input Sampling

Alexandre Englebert (UCLouvain)*; Sédrick Stassin (UMONS); Géraldin Nanfack (University of Namur); Sidi Ahmed Mahmoudi (UMONS); Xavier Siebert (University of Mons); Olivier H CORNU (Cliniques universitaires Saint-Luc UCL); Christophe De Vleeschouwer (Université Catholique de Louvain)

IDTransformer: Transformer for Intrinsic Image Decomposition

Partha Das (University of Amsterdam)*; Maxime Lucienne Gevers (Concordia University ); Sezer Karaoglu (University of Amsterdam); Theo Gevers (University of Amsterdam)

MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers

Jakob Drachmann Havtorn (Technical University of Denmark); Amelie Royer (Qualcomm Research)*; Tijmen Blankevoort (Qualcomm); Babak Ehteshami Bejnordi (Qualcomm AI Reseach)

TransInpaint: Transformer-based Image Inpainting with Context Adaptation

Pourya Shamsolmoali (East China Normal University)*; Masoumeh Zareapoor (Shanghai Jiao Tong University); Eric Granger (ETS Montreal )

Dual-Contrastive Dual-Consistency Dual-Transformer: A Semi-Supervised Approach to Medical Image Segmentation

Ziyang Wang (University of Oxford)*; Congying Ma (University of Bath)

On Moving Object Segmentation from Monocular Video with Transformers

Christian  Homeyer (Heidelberg University, Bosch Research)*; Christoph Schnörr (Heidelberg University)

MOSAIC: Multi-Object Segmented Arbitrary Stylization Using CLIP

Prajwal Ganugula (Oppo Mobiles Pvt. Ltd)*; Siva Sai Surya Santosh Kumar Yellapu (Oppo Mobiles Pvt. Ltd); Sagar Nallamilli (OPPO Mobiles Pvt Ltd); Prabhath Chellingi (IIT Hyderabad); AVINASH THAKUR (OPPO); chandran shyam anand (OPPO Mobiles Pvt. Ltd.); Neeraj Kasera (Oppo Mobiles Pvt. Ltd)

Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction

Felix Hertlein (FZI Research Center for Information Technology)*; Alexander Naumann (FZI Research Center for Information Technology)