JD.com uses a new CNN model to improve ad click prediction.
problem Improving CTR prediction for ads with visual content.
method Proposes Category-specific CNN (CSCNN) to incorporate category knowledge early in the feature extraction process.
result CSCNN outperforms existing methods in CTR prediction.
A hybrid approach links fMRI data to deep features for visual category decoding.
problem Lack of practical fMRI decoder with CNN structure due to limited brain data.
method Kernel Canonical Correlation Analysis linking fMRI and deep learnt representations.
result Effective in distinguishing semantic visual categories using only brain imaging data.
In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifi…
Survey visual analytics methods for detecting anomalous user behaviors.
problem Understanding and detecting anomalous user behaviors in various domains.
method Survey and classification of visual analytics methods in four categories.
result Discussion of findings and potential research directions.
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.
Prototype-based memory network learns visual categories from unlabeled data.
problem Learning from nonstationary, unlabeled data with sequential dependencies.
method Online prototype-based memory network with contrastive loss.
result Significantly better category recognition compared to state-of-the-art methods.
Study shows perceptual boost of visual attention varies with task difficulty and size.
problem Understanding how task-dependent the perceptual boost of visual attention is in natural settings.
method Designed and trained neural networks on various visual tasks, comparing results to baseline.
result Perceptual boost of attention is stronger with more difficult tasks and weaker with larger task sets.
APA improves brain decoding accuracy for visual stimuli.
problem Decoding patterns in human brain using MVPA.
method Developed novel anatomical feature extraction and AdaBoost algorithm.
result Superior performance in decoding visual stimuli categories.
Adaptive system diversifies and personalizes visual browsing for better user engagement.
problem Poor performance of search queries in ambiguous or inspirational browsing scenarios.
method Bayesian regression for scoring relevance, submodular diversification, and personalized category preferences learned from user behavior.
result Significant improvement in click-through-rate and session duration on live traffic.
Bayesian approach updates pretrained convnet for new image categories.
problem Learning new categories with limited data.
method Bayesian procedure using pretrained convnet weights as prior.
result Competitive performance with state-of-the-art methods.
Teaches categories with visual explanations to improve learning.
problem Challenges of traditional machine teaching methods in providing clear explanations.
method Proposes a teaching framework that provides interpretable explanations as feedback.
result Participants achieve better test set performance with interpretable explanations.
APA improves brain decoding accuracy using fMRI.
problem Decoding human brain patterns from fMRI images.
method APA combines anatomical feature extraction and AdaBoost for binary and multi-class predictions.
result APA outperforms existing methods in decoding visual stimuli.
People can learn complex visual concepts from just a few examples.
problem Understanding how people learn and categorize visual concepts from limited data.
method Bayesian program learning model that searches for the best explanation of observations.
result People's judgments are broadly consistent with a Bayesian program learning model, indicating they can learn rich algorithmic abstractions from sparse input data.
This paper analyzes interactive model analysis for machine learning.
problem Understanding, diagnosing, and refining machine learning models.
method Classification of relevant work into understanding, diagnosis, and refinement categories.
result Exploration of future research opportunities in interactive model analysis.
System identifies shifts in sketches for creative drawing.
problem Helping users create more creative sketches.
method Recognizes conceptual shifts between visual categories.
result Produces ambiguous sketches blending features from different categories.
New report on machine learning visualization techniques and trends.
problem Improving trust in machine learning models through visualization.
method Analysis of peer-reviewed articles on machine learning visualization techniques.
result Rapid growth in machine learning visualization techniques over the past three years.
New models use visual concepts to enable few-shot learning.
problem CNNs struggle with few annotated data and interpretability.
method Developed models based on visual concepts within CNNs.
result Models achieve competitive few-shot learning performance.
The output scores of a neural network classifier are converted to probabilities via normalizing over the scores of all competing categories. Computing this partition function, Z, is then linear in the number of categories, which is problematic as real-world problem sets continue to grow in categorical types, such as …
Improved vision-language embeddings boost cross-task learning.
problem Creating general vision systems with better cross-task learning.
method Aligning image-word representations for better cross-task transfer.
result Improved inductive transfer from visual recognition to visual question answering.
In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one can construct a classifier for the zebra category by enumerating which properties it posses…
Paper proposes redundancy-free features for zero-shot object recognition.
problem Redundant visual features degrade zero-shot object recognition.
method Project original features into a new, statistically independent space.
result RFF-GZSL achieves competitive results on benchmark datasets.
New method visualizes brain activity changes over time.
problem Understanding representational dynamics in neural responses.
method Procrustes-aligned Multidimensional Scaling (pMDS) on RDM movies.
result Multidimensional scaling alignment captures representational dynamics.
Large dataset of e-retailer images for improving visual search and product classification.
problem Improving the relevancy of visual search and product recommendation systems.
method Sharing a large dataset of 12M images from an online store classified into 5K categories.
result Demonstrates the effectiveness of deep learning in image classification.
Novel model for decoding visual stimuli in human brains.
problem Challenges in MVP techniques, including noise and sparsity, and the cost of brain studies.
method Automatic detection of active regions, new Gaussian smoothing method, combining fMRI data sets.
result Superior performance compared to state-of-the-art methods.
We explore visual representations of tilings corresponding to Schläfli symbols. In three dimensions, we call these tilings "honeycombs". Schläfli symbols encode, in a very efficient way, regular tilings of spherical, euclidean and hyperbolic spaces in all dimensions. In three dimensions, there are only a finite number …
This paper proposes a method to reduce complexity in GLMs with categorical predictors.
problem Wasteful, hard-to-interpret, and prone to overfitting of traditional one-hot encoding for high-cardinality categorical predictors.
method Clustering categories of categorical predictors through a numerical method that preserves or improves accuracy while reducing the number of coefficients.
result Clustering categories of categorical predictors reduces complexity substantially without harming accuracy.
V-CNN improves CNN performance in network intrusion detection.
problem Applying CNN directly to non-image data leads to poor performance.
method Integrates data visualization before CNN modeling.
result Significantly outperforms other studies in network intrusion detection.
C Croke and B Kleiner have constructed an example of a CAT(0) group with more than one visual boundary. J Wilson has proven that this same group has uncountably many distinct boundaries. In this article we prove that the knot group of any connected sum of two non-trivial torus knots also has uncountably many distinct C…
The paper tackles confidence calibration for exploratory machine learning problems.
problem Difficulty in curating datasets and confusion about category validity.
method Introduces four new algorithms for category-specific confidence estimation, including kernel density ratios.
result Kernel density ratios provide a novel approach to confidence calibration, especially for exploratory problems.
Unsupervised method discovers object landmarks by factorizing image deformations.
problem Learning object structure in unsupervised settings.
method Factorizing image deformations to learn landmarks consistently across different viewpoints and object deformations.
result Learned landmarks establish meaningful correspondences between different object instances without explicit requirement.
KeypointNet learns 3D keypoints for object pose estimation without ground-truth.
problem Learning 3D keypoints for object pose estimation without manual annotations.
method End-to-end geometric reasoning framework to discover keypoints.
result End-to-end framework outperforms fully supervised baseline.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
problem Lack of visualization tools for high-dimensional categorical data.
method cGAP uses Homogeneity Analysis (HOMALS) to embed data in a 3D space and maps it to colors.
result cGAP reveals coherent clusters, outliers, and local-to-global structure in categorical data.
cGAP visualizes high-dimensional categorical data with interpretable geometric structure.
problem Lack of visualization tools for high-dimensional categorical data.
method cGAP uses Homogeneity Analysis (HOMALS) to embed data in a 3D space and maps it to colors for visualization.
result cGAP reveals coherent clusters, outliers, and local-to-global structure in categorical data.
Adaptive cross-modal few-shot learning improves performance in image classification.
problem Few-shot classification with limited data.
method Adaptive combination of visual and semantic features.
result Model outperforms uni-modality and modality-alignment methods.
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important…
G-SimCLR improves unsupervised learning by clustering images into pseudo labels.
problem Improving unsupervised learning for image recognition.
method Proposes a method to cluster images into pseudo labels to batch images of the same category.
result Comparable performance enhancements on CIFAR10 and ImageNet datasets.
Proposes a new neural network approach to credit assignment.
problem Credit assignment problem in deep neural networks.
method Contrastive similarity matching objective function.
result Deep networks learn to match similarity between layers.
ExGate improves neural network accuracy with feature-based attention.
problem Efficiency and accuracy in artificial neural networks for feature-based attention.
method Externally controlled neuron gating in artificial neural networks.
result 5% increase in classification accuracy on CIFAR-10 dataset.
Extracts object-centric frames from unlabeled images.
problem Extracting abstract models of 3D objects from visual measurements.
method Viewpoint factorization and dense equivariant labelling neural network.
result Extracts dense object-centric coordinate frames invariant to deformations.
Proposes a method for weakly-supervised object localization to improve few-shot learning.
problem Challenges of few-shot learning, especially with fine-grained categories.
method Introduces a Self-Attention Based Complementary Module (SAC Module) for weakly-supervised object localization.
result Significantly outperforms state-of-the-art methods on benchmark datasets, especially for fine-grained few-shot tasks.
Deep learning system classifies phonological categories from EEG data.
problem Speech-related BCI for people with speaking disabilities.
method Hierarchical deep learning approach using CNN, LSTM, and autoencoder.
result Average accuracy of 77.9% across five binary classification tasks.
A new method for tracking objects using diverse templates.
problem Improving visual tracking performance and robustness.
method Proposes a framework that uses additional object templates and a new diversity measure in siamese feature space.
result Achieves strong empirical results on tracking benchmarks, improving performance and robustness.
The Familiarity Hypothesis explains deep open set methods' success in detecting novel objects.
problem Detecting novel objects in open set recognition problems.
method Logits-based detection of absence of familiar features.
result Familiarity-based detection fails in scenarios with both novel and familiar objects.
New DL approach reveals feature construction in dense samples.
problem Understanding deep learning's effectiveness across diverse applications.
method High-density sample task with 5 unique tokens, 500 exemplars per token.
result Emergence of category structure and feature detectors observed.
Thousands of first-millennium BCE ivory carvings have been excavated from Neo-Assyrian sites in Mesopotamia (primarily Nimrud, Khorsabad, and Arslan Tash) hundreds of miles from their Levantine production contexts. At present, their specific manufacture dates and workshop localities are unknown. Relying on subjective, …
Survey on embedding techniques in source code.
problem Applying word embedding techniques to source code.
method Collection and categorization of articles from related work and scholarly searches.
result Word embedding has been successfully applied to various granularities of source code.
Virtual reality brings non-Euclidean geometry to life.
problem Understanding non-Euclidean geometry is challenging.
method Interactive visualizations in virtual reality.
result Users can experience non-Euclidean geometry firsthand.
Paper tackles cross-granularity few-shot learning with meta-embedder.
problem Few-shot learning with coarse labels and fine-grained testing.
method Meta-embedder that optimizes visual and semantic discrimination across coarse and fine classes.
result Meta-embedder achieves effective cross-granularity few-shot classification.