Arbitrary Design of DNA-Programmable 3D Crystals through Symmetry Mapping by Jason S. Kahn (2744830)

Supplementary file 1_Optimizing quantum convolutional neural network architectures for arbitrary data dimension.pdf by Changwon Lee (20812727)

“…The number of input qubits determines the dimensions (i.e., the number of features) of the input data that can be processed, restricting the applicability of QCNN algorithms to real-world data. …”

DataSheet1_Improving the convergence of an iterative algorithm for solving arbitrary linear equation systems using classical or quantum binary optimization.pdf by Erick R. Castro (11243697)

Statistical properties of high-flash-rate (≥500 lightning strokes) grid clusters identified in 2013 within the study region: (A) Spatial distribution of cluster centroids; (B, C) P... by Manxing Shi (22367181)

Distribution of (A) temporal difference set (DistT) and (B) spatial distance set (DistS) values by sample number, for the lightning data subset (Fig 3(B)) identified by the CC3D al... by Manxing Shi (22367181)

Environment ConFIGuration Information. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Results of ablation experiment. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Comparison diagram of mAP50. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Improved YOLOv8s. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

YOLOv5s. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Partial Training Images of the Dataset. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

LKA Network Structure. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Comparison diagram of detection accuracy. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

AKConv module structure. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Target Sample Statistics of VisDrone2019. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

YOLOv9c. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Bi-SCDown-FPN Structure Diagram. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

Parameter Settings. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

YOLOv7tiny. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”

LSKA Network Structure. by Xinwei Wang (352488)

“…AKConv allows for convolution kernels with arbitrary numbers and sampling shapes, enabling convolution operations to more precisely adapt to targets at different locations, thereby achieving more efficient feature extraction. …”