w-on-new-ideas-in-vision-transformers.md

ICCVW-2023-Papers

Application

Workshop on New Ideas in Vision Transformers

Title	Repo	Paper	Video
Explaining Through Transformer Input Sampling			➖
Actor-Agnostic Multi-Label Action Recognition with Multi-Modal Query
All-Pairs Consistency Learning forWeakly Supervised Semantic Segmentation	➖		➖
Dual-Contrastive Dual-Consistency Dual-Transformer: A Semi-Supervised Approach to Medical Image Segmentation
A Hybrid Visual Transformer for Efficient Deep Human Activity Recognition	➖		➖
Which Tokens to Use? Investigating Token Reduction in Vision Transformers			➖
Hierarchical Spatiotemporal Transformers for Video Object Segmentation	➖
IDTransformer: Transformer for Intrinsic Image Decomposition			➖
MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers
Template-Guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction
Spatio-Temporal Convolution-Attention Video Network	➖		➖
TSOSVNet: Teacher-Student Collaborative Knowledge Distillation for Online Signature Verification	➖
SeMask: Semantically Masked Transformers for Semantic Segmentation
TransInpaint: Transformer-based Image Inpainting with Context Adaptation	➖
Interactive Image Segmentation with Cross-Modality Vision Transformers			➖
MOSAIC: Multi-Object Segmented Arbitrary Stylization using CLIP	➖		➖
On Moving Object Segmentation from Monocular Video with Transformers	➖
SCSC: Spatial Cross-Scale Convolution Module to Strengthen Both CNNs and Transformers	➖