ResearchTrend.AI
Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition
v1v2 (latest)

Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition

Ryota Hashiguchi
Toru Tamaki
ArXiv (abs)PDFHTML

Papers citing "Vision Transformer with Cross-attention by Temporal Shift for Efficient Action Recognition"

5 / 5 papers shown
Title
Shift and matching queries for video semantic segmentation
Shift and matching queries for video semantic segmentation
Tsubasa Mizuno
Toru Tamaki
101
0
0
10 Oct 2024
Query matching for spatio-temporal action detection with query-based object detector
Query matching for spatio-temporal action detection with query-based object detector
Shimon Hori
Kazuki Omi
Toru Tamaki
63
0
0
27 Sep 2024
S3Aug: Segmentation, Sampling, and Shift for Action Recognition
S3Aug: Segmentation, Sampling, and Shift for Action Recognition
Taiki Sugiura
Toru Tamaki
AI4TS
69
2
0
23 Oct 2023
Joint learning of images and videos with a single Vision Transformer
Joint learning of images and videos with a single Vision Transformer
Shuki Shimizu
Toru Tamaki
ViT
64
0
0
21 Aug 2023
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition
Lei Wang
Piotr Koniusz
ViT
88
50
0
25 Mar 2023