On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “saccading”

Geometry of saccades and saccadic cyclesq-bio.NC

The paper studies the geometry of eye movements and cycles.

problem Understanding the visual stability and eye movement patterns.

method Develops differential geometry of saccades and saccadic cycles, characterizing them as geodesic segments and polygons.

result Provides necessary and sufficient conditions for a system of lines to be axes of rotation for saccades in a saccadic cycle.

saccades saccadic cycles differential geometry Hopf fibration geodesic

2023-06-26abs ↗pdf ↗

Saccader: Improving Accuracy of Hard Attention Models for Visioncs.CV

Saccader improves hard attention models for vision tasks.

problem Challenges in training hard attention models with class label supervision.

method Proposes Saccader, a novel hard attention model trained with only class labels and policy gradient optimization.

result Achieves 75% top-1 and 91% top-5 accuracy while attending to less than one-third of the image.

hard attention vision interpretability policy gradient image classification

2019-08-20abs ↗pdf ↗

Variational Saccading: Efficient Inference for Large Resolution Imagescs.CV

Efficiently samples from large resolution images for faster inference.

problem Inferential and memory costs for large resolution images.

method Proposes a smaller proxy distribution to learn co-ordinates for regions of interest.

result Produces comparable results with ~10x faster inference and lower memory consumption.

deep learning image classification large resolution variational inference saccading

2018-12-08abs ↗pdf ↗

Automatic selection of eye tracking variables in visual categorization in adults and infantsq-bio.QM

Automated method selects eye tracking variables for categorization tasks.

problem Limited duration of infant cooperation and biases in handpicked eye tracking variables.

method Automated selection of eye tracking variables using statistical techniques.

result Same eye tracking variables classify category learners from non-learners in adults and infants with high accuracy.

eye tracking categorization infants adults statistical methods

2020-10-28abs ↗pdf ↗