Results 251 to 260 of about 8,004 (293)
Real-time object detection for unmanned aerial vehicles based on vision transformer and edge computing. [PDF]
Sci RepZhu W, Chen K.
europepmc +1 more source
3D Perception-Based Adaptive Point Cloud Simplification and Slicing for Soil Compaction Pit Volume Calculation. [PDF]
Sensors (Basel)Han C, Wei J, Shen T, Guo C.
europepmc +1 more source
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Optimized Product Quantization
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014Product quantization (PQ) is an effective vector quantization method. A product quantizer can generate an exponentially large codebook at very low memory/time cost. The essence of PQ is to decompose the high-dimensional vector space into the Cartesian product of subspaces and then quantize these subspaces separately.
Kaiming He, Qifa Ke
exaly +3 more sources
Distance Encoded Product Quantization
2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014 Many binary code embedding techniques have been proposed for large-scale approximate nearest neighbor search in computer vision. Recently, product quantization that encodes the cluster index in each subspace has been shown to provide impressive accuracy for nearest neighbor search.
Jae-Pil Heo, Zhe Lin 0001, Sung-Eui Yoon
openaire +2 more sources
Adaptive bit allocation product quantization
Neurocomputing, 2016Product quantization (PQ) is a popular vector quantization method for approximate nearest neighbor search. The key idea of PQ is to decompose the original data space into the Cartesian product of some low-dimensional subspaces and then every subspace is quantized separately with the same number of codewords.
Zhi Zeng, Shuwu Zhang, Guixuan Zhang
exaly +2 more sources
Product Quantization Network for Fast Visual Search
International Journal of Computer Vision, 2020Product quantization has been widely used in fast image retrieval due to its effectiveness of coding high-dimensional visual features. By constructing the approximation function, we extend the hard-assignment quantization to soft-assignment quantization. Thanks to the differentiable property of the soft-assignment quantization, the product quantization
Tan Yu, Hailin Jin, Junsong Yuan
exaly +2 more sources
EPQuant: A Graph Neural Network compression approach based on product quantization
Neurocomputing, 2022 Graph Neural Networks (GNNs) have been widely used in graph analysis due to their strong performance on a wide variety of tasks. Unfortunately, as the size of graphs keeps growing, large graphs can easily consume Terabytes, and training on such graphs ...
Linyong Huang +2 more
exaly +2 more sources
Product Quantized Collaborative Filtering
IEEE Transactions on Knowledge and Data Engineering, 2021Because of strict response-time constraints, efficiency of top-k recommendation is crucial for real-world recommender systems. Locality sensitive hashing and index-based methods usually store both index data and item feature vectors in main memory, so they handle a limited number of items.
Defu Lian +3 more
openaire +1 more source