NIVT23
* *New Ideas in Vision Transformers
* Actor-agnostic Multi-label Action Recognition with Multi-modal Query
* All-Pairs Consistency Learning for Weakly Supervised Semantic Segmentation
* Dual-Contrastive Dual-Consistency Dual-Transformer: A Semi-Supervised Approach to Medical Image Segmentation
* Explaining through Transformer Input Sampling
* Hierarchical Spatiotemporal Transformers for Video Object Segmentation
* Hybrid Visual Transformer for Efficient Deep Human Activity Recognition, A
* IDTransformer: Transformer for Intrinsic Image Decomposition
* Interactive Image Segmentation with Cross-Modality Vision Transformers
* MOSAIC: Multi-Object Segmented Arbitrary Stylization Using CLIP
* MSViT: Dynamic Mixed-scale Tokenization for Vision Transformers
* On Moving Object Segmentation from Monocular Video with Transformers
* SCSC: Spatial Cross-scale Convolution Module to Strengthen both CNNs and Transformers
* SeMask: Semantically Masked Transformers for Semantic Segmentation
* Spatio-Temporal Convolution-Attention Video Network
* Template-guided Illumination Correction for Document Images with Imperfect Geometric Reconstruction
* TransInpaint: Transformer-based Image Inpainting with Context Adaptation
* TSOSVNet: Teacher-student collaborative knowledge distillation for Online Signature Verification
* Which Tokens to Use? Investigating Token Reduction in Vision Transformers
19 for NIVT23