Picture for Toru Tamaki

Toru Tamaki

Shift and matching queries for video semantic segmentation

Add code
Oct 10, 2024
Viaarxiv icon

Query matching for spatio-temporal action detection with query-based object detector

Add code
Sep 27, 2024
Viaarxiv icon

Online pre-training with long-form videos

Add code
Aug 28, 2024
Viaarxiv icon

Fine-grained length controllable video captioning with ordinal embeddings

Add code
Aug 27, 2024
Viaarxiv icon

Multi-model learning by sequential reading of untrimmed videos for action recognition

Add code
Jan 26, 2024
Viaarxiv icon

S3Aug: Segmentation, Sampling, and Shift for Action Recognition

Add code
Oct 23, 2023
Viaarxiv icon

Joint learning of images and videos with a single Vision Transformer

Add code
Aug 21, 2023
Viaarxiv icon

Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition

Add code
Jul 27, 2022
Figure 1 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Figure 2 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Figure 3 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Figure 4 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Viaarxiv icon

On the Performance Evaluation of Action Recognition Models on Transcoded Low Quality Videos

Add code
Apr 19, 2022
Figure 1 for On the Performance Evaluation of Action Recognition Models on Transcoded Low Quality Videos
Figure 2 for On the Performance Evaluation of Action Recognition Models on Transcoded Low Quality Videos
Figure 3 for On the Performance Evaluation of Action Recognition Models on Transcoded Low Quality Videos
Figure 4 for On the Performance Evaluation of Action Recognition Models on Transcoded Low Quality Videos
Viaarxiv icon

Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition

Add code
Apr 15, 2022
Figure 1 for Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
Figure 2 for Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
Figure 3 for Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
Figure 4 for Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognition
Viaarxiv icon