_ | not | _ |
2D or | not | 2D: Bridging the Gap Between Tracking and Structure from Motion |
2D or | not | 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition |
4d Counter-example Showing that DWCNess Does | not | Imply CWCness in nD, A |
4k or | not | ? - Automatic Image Resolution Assessment |
Above the Nyquist Rate, Modulo Folding Does | not | Hurt |
Accuracy assessment on camera calibration method | not | considering lens distortion |
Activate or | not | : Learning Customized Activation |
ALAN: Self-Attention Is | not | All You Need for Image Super-Resolution |
Aligned to the Object, | not | to the Image: A Unified Pose-Aligned Representation for Fine-Grained Recognition |
All Burglaries Are | not | the Same: Predicting Near-Repeat Burglaries in Cities Using Modus Operandi |
All Iris Code Bits are | not | Created Equal |
All Iris Filters are | not | Created Equal |
All Labels Are | not | Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training |
Approximating the problem, | not | the solution: An alternative view of point set matching |
Arterial spin labeling at ultra-high field: All that glitters is | not | gold |
Attention is | not | Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion |
Auto QA: The Question Is | not | Only What, but Also Where |
Automated assessment: it's assessment Jim but | not | as we know it |
Balanced Datasets Are | not | Enough: Estimating and Mitigating Gender Bias in Deep Image Representations |
Because | not | all displays are lists |
Being Comes from | not | -Being: Open-Vocabulary Text-to-Motion Generation with Wordless Training |
Believe It or | not | , We Know What You Are Looking At! |
Benchmarking Stereo Data ( | not | the Matching Algorithms) |
Better May | not | Be Fairer: A Study on Subgroup Discrepancy in Image Classification |
Beyond semi-supervised tracking: Tracking should be as simple as detection, but | not | simpler than recognition |
BUGSYS: A Programming System for Picture Processing -- | not | for Debugging |
But That's | not | Why: Inference Adjustment by Interactive Prototype Revision |
Capsule Network is | not | More Robust than Convolutional Network |
Cardinal axes are | not | independent in color discrimination |
Classifying materials from images: to cluster or | not | to cluster? |
CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or | not | |
Coding or | not | : Optimal Mobile Data Offloading in Opportunistic Vehicular Networks |
Color constancy in a scene with bright colors that do | not | have a fully natural surface appearance |
Color filters: When optimal is | not | optimal |
combining classifier: to train or | not | to train?, The |
Combining Sentinel-1 and Landsat 8 Does | not | Improve Classification Accuracy of Tropical Selective Logging |
Connected Pictures Are | not | Recognizable by Deterministic Two Dimensional On-Line Tessellation Acceptors |
Construction of a System for Defining Areas Which Are | not | Obtained Data from Stereo Images |
Content-Based Image Retrieval for | not | -Well-Framed Images Using Multiresolutional Eigen-Features |
Continuing Reinvention of Content-Based Retrieval: Multimedia Is | not | Dead, The |
Crossing or | not | ? Context-Based Recognition of Pedestrian Crossing Intention in the Urban Environment |
CrowdEst: a method for estimating (and | not | simulating) crowd evacuation parameters in generic environments |
Danish Fungi 2020: | not | Just Another Image Recognition Dataset |
DAPC: Answering Why- | not | Questions on Top-k Direction-Aware ASK Queries in Polar Coordinates |
Debiasing Skin Lesion Datasets and Models? | not | So Fast |
Deep Features or | not | : Temperature and Time Prediction in Outdoor Scenes |
Deep Image Retrieval is | not | Robust to Label Noise |
Deep Match Tracker: Classifying when Dissimilar, Similarity Matching when | not | |
Deep neural networks for automatic speaker recognition do | not | learn supra-segmental temporal features |
Denoising image sequences does | not | require motion estimation |
DETR Does | not | Need Multi-Scale or Locality Design |
Digital Geometry May | not | Be Discrete |
Discrete Point-Wise Attack is | not | Enough: Generalized Manifold Adversarial Attack for Face Recognition |
Distributed video coding: A promising solution for distributed wireless video sensors or | not | ? |
DiverseNet: When One Right Answer is | not | Enough |
Do | not | Disturb Me: Person Re-identification Under the Interference of Other Pedestrians |
Do | not | Forget to Attend to Uncertainty while Mitigating Catastrophic Forgetting |
Do | not | Mask What You Do Not Need to Mask: A Parser-free Virtual Try-on |
Do | not | Mask What You Do Not Need to Mask: A Parser-free Virtual Try-on |
Do | not | Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation |
Early Exit or | not | : Resource-efficient Blind Quality Enhancement for Compressed Images |
Even big data is | not | enough: need for a novel reference modelling for forensic document authentication |
Expanding dictionary for robust face recognition: Pixel is | not | necessary while sparsity is |
Face Recognition: Too Bias, or | not | Too Bias? |
Farnsworth Flashlight is | not | equivalent to the Farnsworth Lantern, The |
fast image dehazing method that does | not | introduce color artifacts, A |
Favoring One Among Equals - | not | a Good Idea: Many-to-one Matching for Robust Transformer based Pedestrian Detection |
Finding the best | not | the most: regularized loss minimization subgraph selection for graph classification |
Focus on Content | not | Noise: Improving Image Generation for Nuclei Segmentation by Suppressing Steganography in CycleGAN |
Functional Size Invariant is | not | Provided by the Cortical Magnification Factor |
Generalization Over Contrast and Mirror Reversal, But | not | Figure-ground Reversal, in an Edge-based Model of IT Neurons |
Genetically identical irises have texture similarity that is | not | detected by iris biometrics |
Good Data Augmentation Policy is | not | All You Need: A Multi-Task Learning Perspective, A |
Higher-order MRFs based image super resolution: why | not | MAP? |
Hot or | not | : Exploring Correlations between Appearance and Temperature |
How | not | to Benchmark Image Processors |
Human Assisted Computer Vision and Artificial Intelligence -- Why | not | ? |
Human or Machine? It Is | not | What You Write, But How You Write It |
Hyper-parameter optimization in classification: To-do or | not | -to-do |
Idiot's Bayes: | not | so Stupid After All? |
If We Did | not | Have ImageNet: Comparison of Fisher Encodings and Convolutional Neural Networks on Limited Training Data |
If We Use 4- or 8-Connectedness for Both the Objects and the Background, the Euler Characteristic Is | not | Locally Computable |
Image databases are | not | databases with images |
Improvement of contrast sensitivity with practice is | not | compatible with a sensory threshold account |
Improving short-term traffic forecasts: To combine models or | not | to combine? |
Is | not | the Truth the Truth?: Analyzing the Impact of User Validations for Bus In/Out Detection in Smartphone-Based Surveys |
It Is | not | the Journey But the Destination: Endpoint Conditioned Trajectory Prediction |
It is Okay to | not | Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection |
It's | not | About the Journey; It's About the Destination: Following Soft Paths Under Question-Guidance for Visual Reasoning |
It's | not | All About Size: On the Role of Data Properties in Pedestrian Detection |
It's | not | Just Black and White: Classifying Defendant Mugshots Based on the Multidimensionality of Race and Ethnicity |
It's | not | Polite to Point: Describing People with Uncertain Attributes |
Iterative Gradient-Based Shift Estimation: To Multiscale or | not | to Multiscale? |
Labels are | not | Perfect: Inferring Spatial Uncertainty in Object Detection |
Large Class Separation is | not | What You Need for Relational Reasoning-Based OOD Detection |
Leaf Surface Reflectance Does | not | Affect Biophysical Traits Modelling from VIS-NIR Spectra in Plants with Sparsely Distributed Trichomes |
Learning | not | to Learn: Training Deep Neural Networks With Biased Data |
Learning Target Candidate Association to Keep Track of What | not | to Track |
Learning What | not | to Segment: A New Perspective on Few-Shot Segmentation |
Local features are | not | lonely: Laplacian sparse coding for image classification |
Localisation via Deep Imagination: Learn the Features | not | the Map |
Look who is | not | talking: Assessing engagement levels in panel conversations |
Machines Should | not | See as People Do, but Must Know How People See |
Mammogram Analysis Using Two-Dimensional Autoregressive Models: Sufficient or | not | ? |
Masked Autoencoding Does | not | Help Natural Language Supervision at Scale |
Matching Is | not | Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation |
maximum likelihood estimator is | not | optimal on 3-D motion estimation from noisy optical flow, The |
Medical Ultrasound Imaging: To GPU or | not | to GPU? |
Memory Aware Synapses: Learning What ( | not | ) to Forget |
MLP-Based Texture Segmentation Technique Which Does | not | Require a Feature Set, An |
Multi-attribute Queries: To Merge or | not | to Merge? |
N2D: ( | not | Too) Deep Clustering via Clustering the Local Manifold of an Autoencoded Embedding |
NetTailor: Tuning the Architecture, | not | Just the Weights |
New Journal Entries -- | not | Classified Yet |
Non-cardinal color mechanism strength differs across color planes but | not | across subjects |
| not | 3D Re-ID: Simple Single Stream 2D Convolution for Robust Video Re-identification |
| not | Afraid of the Dark: NIR-VIS Face Recognition via Cross-Spectral Hallucination and Low-Rank Embedding |
| not | All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection |
| not | all domains are equally complex: Adaptive Multi-Domain Learning |
| not | All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement |
| not | All Frames Are Equal: Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses |
| not | All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation |
| not | All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection |
| not | All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space |
| not | All Negatives Are Equal: Learning to Track With Multiple Background Clusters |
| not | All Operations Contribute Equally: Hierarchical Operation-adaptive Predictor for Neural Architecture Search |
| not | All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts |
| not | All Patches Are Equal: Hierarchical Dataset Condensation for Single Image Super-Resolution |
| not | all pixels are created equal |
| not | All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade |
| not | All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds |
| not | All Relations are Equal: Mining Informative Labels for Scene Graph Generation |
| not | All Samples Are Born Equal: Towards Effective Clean-Label Backdoor Attacks |
| not | All Samples are Trustworthy: Towards Deep Robust SVP Prediction |
| not | All Steps are Created Equal: Selective Diffusion Distillation for Image Manipulation |
| not | All Swear Words Are Used Equal: Attention over Word n-grams for Abusive Language Identification |
| not | All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer |
| not | End-to-end: Explore Multi-stage Architecture for Online Surgical Phase Recognition |
| not | Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection |
| not | Everybody's Special: Using Neighbors in Referring Expressions with Uncertain Attributes |
| not | Just a Matter of Semantics: The Relationship Between Visual and Semantic Similarity |
| not | just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction |
| not | Just Selection, but Exploration: Online Class-Incremental Continual Learning via Dual View Consistency |
| not | Just Streaks: Towards Ground Truth for Single Image Deraining |
| not | only Look, But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision |
| not | only size matters: Regularized partial matching of nonrigid shapes |
| not | Seeing the Crime for the Cameras? |
| not | So Digital Future of Digital Signal Processing, The |
| not | So Naive Bayes: Aggregating One-Dependence Estimators |
| not | Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and Segmentation |
| not | with My Name! Inferring Artists' Names of Input Strings Employed by Diffusion Models |
| not | es on shape orientation where the standard method does not work |
Objects do | not | disappear: Video object detection by single-frame object location anticipation |
On the Convergence of Tsetlin Machines for the IDENTITY- and | not | Operators |
On the Number of Rules and Conditions in Mining Data with Attribute-Concept Values and 'Do | not | Care' Conditions |
On the Recovery of Motion and Structure when Cameras are | not | Calibrated |
One Size Does | not | Fit All: Data-Adaptive Adversarial Training |
One size does | not | fit all: multimodal search on mobile and desktop devices with the I-SEARCH search engine |
optimal triangulation method is | not | really optimal, The |
Out-of-Distribution Identification: Let Detector Tell Which I Am | not | Sure |
Perfect Estimation of a Background Image Does | not | Lead to a Perfect Background Subtraction: Analysis of the Upper Bound on the Performance, A |
Predicting Is | not | Understanding: Recognizing and Addressing Underspecification in Machine Learning |
Predicting Tropical Tree Species Richness from Normalized Difference Vegetation Index Time Series: The Devil Is Perhaps | not | in the Detail |
Privacy-Preserving Representations are | not | Enough: Recovering Scene Content from Camera Poses |
Produced Quality is | not | Perceived Quality: A Qualitative Approach to Overall Audiovisual Quality |
Railroad is | not | a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation |
Repeatability Is | not | Enough: Learning Affine Regions via Discriminability |
Resetting the baseline: CT-based COVID-19 diagnosis with Deep Transfer Learning is | not | as accurate as widely thought |
Rethinking Data Distillation: Do | not | Overlook Calibration |
Rove-tree-11: The | not | -so-wild Rover a Hierarchically Structured Image Dataset for Deep Metric Learning Research |
same is | not | the same: Postcorrection of alphabet confusion errors in mixed-alphabet OCR recognition, The |
Search to Distill: Pearls Are Everywhere but | not | the Eyes |
Securing Images Online: A Protection Mechanism That Does | not | Involve Watermarking |
Seeing is | not | believing |
Seeing is | not | Enough |
Seeing What is | not | There: Learning Context to Determine Where Objects are Missing |
Segment Anything Model Can | not | Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping |
Self-Guiding Multimodal LSTM: When We Do | not | Have a Perfect Training Dataset for Image Captioning |
Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search: Tight or | not | |
Separate Calibration Method of Laser Pointing and Ranging for the GF-7 Satellite Laser That Does | not | Require Field Detectors, A |
Shape Prior is | not | All You Need: Discovering Balance Between Texture and Shape Bias in CNN |
Shape-biased CNNs are | not | Always Superior in Out-of-Distribution Robustness |
SiameseFuse: A computationally efficient and a | not | -so-deep network to fuse visible and infrared images |
Simple Connectivity Is | not | Locally Computable for Connected 3D Images |
Sky Is | not | the Limit: Use of a Spray Drone for the Precise Application of Herbicide and Control of an Invasive Plant in Managed Wetlands, The |
Smile When You Read This, Whether You Like It or | not | : Conceptual Challenges to Affect Detection |
Solid or | not | solid: vision for radar target validation |
Sonified Distance in Sensory Substitution Does | not | Always Improve Localization: Comparison With a 2-D and 3-D Handheld Device |
Sparse Algorithms Are | not | Stable: A No-Free-Lunch Theorem |
Spatial Disposition of Axes in a Generalized Cylinder Representation of Objects that Do | not | Encompass the Viewer |
Supporting video library exploratory search: When storyboards are | not | enough |
System for displaying an object that is | not | visible to a camera |
Template Estimation in Computational Anatomy: Frechet Means Top and Quotient Spaces Are | not | Consistent |
They are | not | Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning |
They are | not | Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers |
This Face Does | not | Exist... But It Might Be Yours! Identity Leakage in Generative Models |
Tilting at windmills: Data augmentation for deep pose estimation does | not | help with occlusions |
To Adapt or | not | to Adapt? Real-Time Adaptation for Semantic Segmentation |
To Aggregate or | not | to aggregate: Selective Match Kernels for Image Search |
To Be or | not | to Be in Flow at Work: Physiological Classification of Flow Using Machine Learning |
To Beat or | not | to Beat: Beat Gestures in Direction Giving |
To Blend or | not | to Blend? A Framework for Nationwide Landsat-MODIS Data Selection for Crop Yield Prediction |
To boost or | not | to boost? On the limits of boosted trees for object detection |
To Bundle Adjust or | not | : A Comparison of Relative Geolocation Correction Strategies for Satellite Multi-View Stereo |
To cluster, or | not | to cluster: An analysis of clusterability methods |
To complete or | not | to complete: Gap completion in real images |
To e or | not | to e in poisson image reconstruction |
To face or | not | to face: Towards reducing false positive of face detection |
To Fill or | not | to Fill: Sensitivity Analysis of the Influence of Resolution and Hole Filling on Point Cloud Surface Modeling and Individual Rockfall Event Detection |
To FRAME or | not | to FRAME in probabilistic texture modelling? |
To Frontalize or | not | to Frontalize: Do We Really Need Elaborate Pre-processing to Improve Face Recognition? |
To Keystone or | not | to Keystone, that is the Correction |
To Listen or | not | : Distributed Detection with Asynchronous Transmissions |
To NeRF or | not | to NeRF: A View Synthesis Challenge for Human Heads |
To skip or | not | to skip? A dataset of spontaneous affective response of online advertising (SARA) for audience behavior analysis |
To switch travel mode or | not | ? Impact of Smartphone delivered high-quality multimodal information |
To text or | not | to text- drivers' interpretation of traffic situations as the basis for their decision to (not) engage in text messaging |
To text or | not | to text- drivers' interpretation of traffic situations as the basis for their decision to (not) engage in text messaging |
To Veer or | not | to Veer: Learning from Experts How to Stay Within the Crosswalk |
To Watch or | not | to Watch: Video Summarization with Explicit Duplicate Elimination |
Too Far to See? | not | Really!: Pedestrian Detection With Scale-Aware Localization Policy |
Tourism De-Metropolisation but | not | De-Concentration: COVID-19 and World Destinations |
Traffic Collisions, Accidents, Analysis, Congestion, | not | Image Analysis |
Traffic Control, Traffic Analysis, | not | Image Analysis |
Traffic Flow Models and Analysis, | not | Image Based |
Traffic Signal Control, Traffic Analysis, | not | Image Analysis |
Tree Death | not | Resulting in Gap Creation: An Investigation of Canopy Dynamics of Northern Temperate Deciduous Forests |
TrustEYE.M4: Protecting the sensor: | not | the camera |
Understanding when spatial transformer networks do | not | support invariance, and what to do about it |
Urban Archaeology: How to Communicate a Story of a Site, 3D Virtual Reconstruction but | not | Only |
Use of Sub-Ensembles and Multi-Template Observers to Evaluate Detection Task Performance for Data That are | not | Multivariate Normal |
Vectorization in Graphics Recognition: To Thin or | not | to Thin |
Vegetation Indices Do | not | Capture Forest Cover Variation in Upland Siberian Larch Forests |
Vehicle trajectory prediction works, but | not | everywhere |
Virtual Reality is Better Than Desktop for Training a Spatial Knowledge Task, but | not | for Everyone |
Vision pyramids that do | not | grow too high |
VLAD Is | not | Necessary for CNN |
Watermarking Is | not | Cryptography |
We are | not | contortionists: Coupled adaptive learning for head and body orientation estimation in surveillance video |
What Does Your Computational Imaging Algorithm | not | Know?: A Plug-and-Play Model Quantifying Model Uncertainty |
What If We Do | not | have Multiple Videos of the Same Action? Video Action Localization Using Web Images |
What is and What is | not | a Salient Object? Learning Salient Object Detector by Ensembling Linear Exemplar Regressors |
What Machines See Is | not | What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images |
What Rainfall Does | not | Tell Us: Enhancing Financial Instruments with Satellite-Derived Soil Moisture and Evaporative Stress |
What the Eye Did | not | See: A Fusion Approach to Image Coding |
What you saw is | not | what you get: Domain adaptation using asymmetric kernel transforms |
What You Say Is | not | What You Do: Studying Visio-Linguistic Models for TV Series Summarization |
What's News, What's | not | ? Associating News Videos with Words |
When It Is | not | Only About Color: The Importance of Hyperspectral Imaging Applied to the Investigation of Paintings |
When Prompt-based Incremental Learning Does | not | Meet Strong Pretraining |
When Small Is | not | Beautiful: The Unexpected Impacts of Trees and Parcel Size on Metered Water-Use in a Semi-Arid City |
When standard RANSAC is | not | enough: Cross-media visual matching with hypothesis relevancy |
Whether normalized or | not | ? Towards more robust iris recognition using dynamic programming |
Why Accuracy is | not | Enough: The Need for Consistency in Object Detection |
Why Aspect Graphs Are | not | (Yet) Practical for Computer Vision |
Why direct LDA is | not | equivalent to LDA |
Why | not | a Single Image? Combining Visualizations to Facilitate Fieldwork and On-Screen Mapping |
Why | not | use the Levenberg-Marquardt method for fundamental matrix estimation? |
Why Stereo Vision is | not | Always About 3D Reconstruction |
You Can Run but | not | Hide: Improving Gait Recognition with Intrinsic Occlusion Type Awareness |
You Do | not | Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement |
You're | not | You When You're Angry: Robust Emotion Features Emerge by Recognizing Speakers |
Your Flamingo is My Bird: Fine-Grained, or | not | |
263 for not