窃喜
发表于 2025-3-28 14:35:12
http://reply.papertrans.cn/29/2824/282308/282308_41.png
山羊
发表于 2025-3-28 22:36:47
http://reply.papertrans.cn/29/2824/282308/282308_42.png
和平
发表于 2025-3-29 00:22:43
E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. The cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. The end-to-end models are efficient but suffer from trai
物种起源
发表于 2025-3-29 03:09:06
Open-Set Text Recognition via Shape-Awareness Visual Reconstructionmpared to conventional counterparts, the OSTR task demands actively spotting and incrementally recognizing novel characters. Existing methods have demonstrated some success, yet confusion among similar characters remains to be a major challenge, potentially due to insufficient shape information pres
爱国者
发表于 2025-3-29 10:58:21
Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruningnd all current state-of-the-art models and have achieved excellent performance. However, the computational requirements of the transformer architecture makes training these methods slow and resource heavy. In this paper, we introduce a new token pruning strategy that significantly decreases training
engender
发表于 2025-3-29 15:21:34
Text Enhancement: Scene Text Recognition in Hazy Weatherer adverse weather conditions with poor visibility remains challenging. To address this problem, we propose a text image enhancement network that can be embedded into a scene text recognizer in a pluggable manner. This network comprises multiple sets of digital image processing (DIP) units, which ar
parsimony
发表于 2025-3-29 18:40:03
Reading Between the Lanes: Text VideoQA on the Roadtion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason o