machination
发表于 2025-3-28 18:16:27
TFPGAN: Tiny Face Detection with Prior Information and GANimages. Tiny faces are so fuzzy that the facial patterns are not clear or even ambiguous resulting in greatly reduced detection. In this paper, we proposed an algorithm to directly generate a clear high-resolution face from a blurry small one by adopting a generative adversarial network (GAN). Besid
Pelago
发表于 2025-3-28 20:33:17
http://reply.papertrans.cn/47/4695/469460/469460_42.png
exhibit
发表于 2025-3-29 00:52:45
Aggregated Deep Saliency Prediction by Self-attention Networkto-end deep saliency prediction method named VGG-SSM is proposed. This model identifies three key components: feature extraction, self-attention module, and multi-level integration. An encoder-decoder architecture is used to extract the feature as a baseline. The multi-level integration constructs a
轻快走过
发表于 2025-3-29 04:44:00
http://reply.papertrans.cn/47/4695/469460/469460_44.png
hypertension
发表于 2025-3-29 08:31:15
Depth Guided Attention for Person Re-identificationained significant attention upon the introduction of different sensors (i.e. depth cameras) that provide the additional information irrespective of the visual features. Despite recent advances with deep learning models, state-of-the-art re-identification approaches fail to leverage the sensor-based
Obstreperous
发表于 2025-3-29 14:14:33
http://reply.papertrans.cn/47/4695/469460/469460_46.png
crutch
发表于 2025-3-29 15:57:58
LiDAR-Camera-Based Deep Dense Fusion for Robust 3D Object Detection3D information. To fully fuse view-specific feature maps, this paper aims to explore the two-directional fusion of arbitrary size camera feature maps and LiDAR feature maps in the early feature extraction stage. Towards this target, a deep dense fusion 3D object detection framework is proposed for a
accordance
发表于 2025-3-29 20:22:07
PON: Proposal Optimization Network for Temporal Action Proposal Generationmost advanced methods still have the problem of sharp performance degradation when an action proposal generated. Most methods use sliding windows method or simply group frames according to frame-level scores. These methods are not enough to provide accurate action boundary and maintain reasonable te
Estimable
发表于 2025-3-30 03:38:58
A Second-Order Adaptive Agent Network Model for Social Dynamics in a Classroom Setting factor among young adolescents is the amount of delinquencies committed. In this paper an adaptive social agent network model using friendship relationships as predictor for alcohol consumption and amount of delinquencies committed is explored. The proposed agent network model was empirically valid
极为愤怒
发表于 2025-3-30 07:40:40
A Fast Terminal Sliding Mode Control Strategy for Trajectory Tracking Control of Robotic Manipulatorttering behavior and speed up the fast response of the conventional Terminal Sliding Mode Control, a novel robust, reaching control law with two variable power components is introduced. With this proposal, the state error variables of the system quickly converge on the sliding surface whether their