Vertical 发表于 2025-3-25 05:49:11
Live-Stream Identification Based on Reasoning Network with Core Traffic Setfic set for each session. Then the features related to the live-stream content will be extracted, and a Live-Stream Reasoning Network (LSRN) is designed to infer the corresponding type of live-stream. To evaluate the effectiveness of the proposed approach, a set of experiments are conducted on the dOrgasm 发表于 2025-3-25 10:16:48
http://reply.papertrans.cn/55/5441/544051/544051_22.png古代 发表于 2025-3-25 11:58:32
SIE-YOLOv5: Improved YOLOv5 for Small Object Detection in Drone-Captured-Scenariose baseline model by introducing Wise-IoU [.] to address calculation issues. Through extensive experiments, we demonstrate that our proposed SIE-YOLOv5 has better small object detection capabilities in UAV-captured scenes. On the VisDrone2021 dataset, the mAP is improved by 6.6%.无意 发表于 2025-3-25 17:41:10
Learning-Based Dichotomy Graph Sketch for Summarizing Graph Streams with High Accuracye them in different graph sketches accordingly. With the learnable classifier and the dichotomy graph sketches, the proposed mechanism can resolve the hashing collision problem and significantly improve the accuracy for graph query tasks. We conducted extensive experiments on three real-world graphBILK 发表于 2025-3-25 23:19:28
http://reply.papertrans.cn/55/5441/544051/544051_25.png浮雕 发表于 2025-3-26 02:55:50
http://reply.papertrans.cn/55/5441/544051/544051_26.pngInnovative 发表于 2025-3-26 06:49:37
Conf-UNet: A Model for Speculation on Unknown Oracle Bone Charactersth a reliable method to speculate the sealed characters that correlate with unidentified OBC. The proposed model also enables linguists to use deep learning to research the evolution of pictographs. Experiments on the HWOBC-A dataset demonstrate that our model outperforms other models on this task o乱砍 发表于 2025-3-26 12:26:28
An Efficient One-Shot Network and Robust Data Associations in Multi-pedestrian Trackinginformation to associate. On the MOT20 testing set, our proposed one-shot model with robust associations termed as BFMOT reduces the number of ID switches by 52.1% and improves the tracking accuracy (i.e. MOTA) by 6.7% compared with the state-of-the-art tracker. BFMOT runs close to 30 FPS on MOT16,1或者发神韵 发表于 2025-3-26 13:48:20
http://reply.papertrans.cn/55/5441/544051/544051_29.png辩论的终结 发表于 2025-3-26 18:10:39
ST-MAN: Spatio-Temporal Multimodal Attention Network for Traffic Predictioned to feed in more implicit information. Extensive experiments on three real-world datasets show that ST-MAN not only outperforms state-of-the-art methods in all aspects, but also has high computational efficiency. Moreover, the framework is easily generalized to include more data modalities.