File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Real-time end-to-end video text spotter with contrastive representation learning
Title | Real-time end-to-end video text spotter with contrastive representation learning |
---|---|
Authors | |
Issue Date | 2022 |
Publisher | IEEE. |
Citation | 17th European Conference on Computer Vision (ECCV) (Hybrid), Tel Aviv, Israel, October 23-27, 2022. In Proceedings of the European Conference on Computer Vision (ECCV) How to Cite? |
Abstract | Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models long-range dependencies and learning temporal information across multiple frames. 3) A simple, lightweight architecture is designed for effective and accurate performance, including GPU-parallel detection post-processing, CTC-based recognition head with Masked RoI. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting IDF1 of 72.0% at 41.0 FPS on ICDAR2015video, with 10.5% and 32.0 FPS improvement the previous best method. |
Description | Oral |
Persistent Identifier | http://hdl.handle.net/10722/315797 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wu, W | - |
dc.contributor.author | Li, Z | - |
dc.contributor.author | Li, J | - |
dc.contributor.author | Shen, C | - |
dc.contributor.author | Zhou, H | - |
dc.contributor.author | Gao, T | - |
dc.contributor.author | Wang, Z | - |
dc.contributor.author | Luo, P | - |
dc.date.accessioned | 2022-08-19T09:04:37Z | - |
dc.date.available | 2022-08-19T09:04:37Z | - |
dc.date.issued | 2022 | - |
dc.identifier.citation | 17th European Conference on Computer Vision (ECCV) (Hybrid), Tel Aviv, Israel, October 23-27, 2022. In Proceedings of the European Conference on Computer Vision (ECCV) | - |
dc.identifier.uri | http://hdl.handle.net/10722/315797 | - |
dc.description | Oral | - |
dc.description.abstract | Video text spotting(VTS) is the task that requires simultaneously detecting, tracking and recognizing text in the video. Existing video text spotting methods typically develop sophisticated pipelines and multiple models, which is not friend for real-time applications. Here we propose a real-time end-to-end video text spotter with Contrastive Representation learning (CoText). Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e.g., text detection, tracking, recognition) in a real-time end-to-end trainable framework. 2) With contrastive learning, CoText models long-range dependencies and learning temporal information across multiple frames. 3) A simple, lightweight architecture is designed for effective and accurate performance, including GPU-parallel detection post-processing, CTC-based recognition head with Masked RoI. Extensive experiments show the superiority of our method. Especially, CoText achieves an video text spotting IDF1 of 72.0% at 41.0 FPS on ICDAR2015video, with 10.5% and 32.0 FPS improvement the previous best method. | - |
dc.language | eng | - |
dc.publisher | IEEE. | - |
dc.relation.ispartof | Proceedings of the European Conference on Computer Vision (ECCV) | - |
dc.rights | Proceedings of the European Conference on Computer Vision (ECCV). Copyright © IEEE. | - |
dc.title | Real-time end-to-end video text spotter with contrastive representation learning | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Luo, P: pluo@hku.hk | - |
dc.identifier.authority | Luo, P=rp02575 | - |
dc.identifier.doi | 10.48550/arXiv.2207.08417 | - |
dc.identifier.hkuros | 335582 | - |
dc.publisher.place | Israel | - |