| _ | should | _ |
|---|
| 3D Reconstruction: Why | should | the accuracy always be presented in the pixel unit? |
| Affect Dilemma for Artificial Agents: | should | We Develop Affective Artificial Agents?, The |
| Are metrics measuring what they | should | ? An evaluation of Image Captioning task metrics |
| Autonomous vehicles lite self-driving technologies | should | start small, go slow |
| Beyond semi-supervised tracking: Tracking | should | be as simple as detection, but not simpler than recognition |
| Can the Biases in Facial Recognition Be Fixed; Also, | should | They? |
| Can we trust computer with body-cam vidio? Police departments are being led to believe AI will help, but they | should | be wary |
| Contrasts Between Human and Machine Vision: | should | Technology Recapitulate Phylogeny? |
| Face Recognition by Humans: Nineteen Results All Computer Vision Researchers | should | Know About |
| Fair Comparison | should | Be Based on the Same Protocol: Comments on Trainable Convolution Filters and Their Application to Face Recognition, A |
| Found a Good Match: | should | I Keep Searching?: Accuracy and Performance in Iris Matching Using 1-to-First Search |
| Fusing China GF-5 Hyperspectral Data with GF-1, GF-2 and Sentinel-2A Multispectral Data: Which Methods | should | Be Used? |
| Fusion by the IHS Transform: | should | We Use Cylindrical or Spherical Coordinates |
| Fusion of China ZY-1 02D Hyperspectral Data and Multispectral Data: Which Methods | should | Be Used? |
| Generalization in Metric Learning: | should | the Embedding Layer Be Embedding Layer? |
| Generator Knows What Discriminator | should | Learn in Unconditional GANs |
| Good Our Field Can Hope to Do, the Harm It | should | Avoid, The |
| How Big Is a Gabor Patch, and Why | should | We Care |
| How Far Two UAVs | should | be Subject to Communication Uncertainties |
| How large | should | ensembles of classifiers be? |
| How Long | should | the MISR Record Be when Evaluating Aerosol Optical Depth Climatology in Climate Models? |
| How Realistic | should | Synthetic Images Be for Training Crowd Counting Models? |
| How | should | we Handle 4D Light Fields with CNNS? |
| How | should | We Represent Faces for Automatic Recognition? |
| Immersive Video Coding: | should | Geometry Information Be Transmitted as Depth Maps? |
| Local Climate Zone (LCZ) Map Accuracy Assessments | should | Account for Land Cover Physical Characteristics that Affect the Local Thermal Environment |
| Machines | should | Not See as People Do, but Must Know How People See |
| On The Importance Of Being Asymmetric In Stereopsis: Or Why We | should | Use Skewed Parallel Cameras |
| Orthogonal function representation for online signature verification: which features | should | be looked at? |
| Pull the Plug? Predicting If Computers or Humans | should | Segment Images |
| Real-time Segmentation Networks | should | be Latency Aware |
| Recording Information On Architectural Heritage | should | Meet The Requirements for Conservation Digital Recording Practices at the Summer Palace |
| ReGen: A good Generative zero-shot video classifier | should | be Rewarded |
| Roses are Red, Violets are Blue… But | should | VQA expect Them To? |
| should | a movie have two different soundtracks for its stereoscopic and non-stereoscopic versions? A study on the front/rear balance |
| should | All Proposals Be Treated Equally in Object Detection? |
| should | I take a walk? Estimating Energy Expenditure from Video Data |
| should | the Desired Heading in Path Following of Autonomous Vehicles be the Tangent Direction of the Desired Path? |
| should | we discard sparse or incomplete videos? |
| should | We Encode Rain Streaks in Video as Deterministic or Stochastic? |
| should | We Pre-register Experiments in Computer Vision? |
| should | We Search for a Global Minimizer of Least Squares Regularized with an L_0 Penalty to Get the Exact Solution of an under Determined Linear System? |
| Spatially-Regularized Features for Vehicle Re-Identification: An Explanation of Where Deep Models | should | Focus |
| Statistical shape modelling: How many modes | should | be retained? |
| Three Guidelines You | should | Know for Universally Slimmable Self-Supervised Learning |
| Three Things Everyone | should | Know About Vision Transformers |
| Three things everyone | should | know to improve object retrieval |
| trolley, the bull bar, and why engineers | should | care about the ethics of autonomous cars, The |
| Weighted Accuracy Measure for Land Cover Mapping: Comment on Johnson et al. Local Climate Zone (LCZ) Map Accuracy Assessments | should | Account for Land Cover Physical Characteristics that Affect the Local Thermal Environment. Remote Sens. 2019, 11, 2420, A |
| What Object | should | I Use? - Task Driven Object Detection |
| What | should | be Computed In Low Level Vision Systems |
| What | should | Be Equivariant In Self-Supervised Learning |
| What | should | the user do? Inference structures and line drawing interpretation |
| What | should | We Be Comparing for Writer Identification? |
| When | should | We Consider Lens Distortion in Camera Calibration |
| Where | should | cameras look at soccer games: Improving smoothness using the overlapped hidden Markov model |
| Where | should | Saliency Models Look Next? |
| Where | should | Traffic Sensors Be Placed on Highways? |
| Why A Statistics-Based Face Recognition System | should | Base Its Recognition on the Pure Face Portion: A Probabilistic Decision-Based Proof |
| Why recognition in a statistics-based face recognition system | should | be based on the pure face portion: a probabilistic decision-based proof |
| Why You | should | Forget Luminance Conversion and Do Something Better |
| You | should | Look at All Objects |
62 for should
| _ | shoulder | _ |
|---|
| 2D to Pseudo-3D Conversion of Head and | shoulder | Images Using Feature Based Parametric Disparity Maps |
| Automatic extraction of moving objects for head- | shoulder | video sequence |
| Automatic Segmentation of | shoulder | Joint in MRI Using Patch-Based and Fully Convolutional Networks |
| Block-Based Search Space Reduction Technique for Face Detection Using | shoulder | and Head Curves |
| Compact and Portable Exoskeleton for | shoulder | and Elbow Assistance for Workers and Prospective Use in Space, A |
| Comparison of a Touch-Gesture- and a Keystroke-Based Password Method: Toward | shoulder | -Surfing Resistant Mobile User Authentication, A |
| Covert Attentional | shoulder | Surfing: Human Adversaries Are More Powerful Than Expected |
| Estimating the number of people in crowded scenes by MID based foreground segmentation and head- | shoulder | detection |
| Fast Human Head and | shoulder | Detection Using Convolutional Networks and RGBD Data |
| Head- | shoulder | based gender recognition |
| Head- | shoulder | human contour estimation in still images |
| Human head- | shoulder | segmentation |
| Impact of NPV on the Spectral Parameters in the Yellow-Edge, Red-Edge and NIR | shoulder | Wavelength Regions in Grasslands, The |
| Integrating region and edge information for the automatic segmentation of interventional magnetic resonance images of the | shoulder | complex |
| Learning Appearance Features for Pain Detection Using the UNBC-McMaster | shoulder | Pain Expression Archive Database |
| Locating Facial Region of a Head-and- | shoulder | s Color Image |
| Locating head and face boundaries for head- | shoulder | images |
| model-based approach for human head-and- | shoulder | segmentation, A |
| new edge feature for head- | shoulder | detection, A |
| new segmentation method for MRI images of the | shoulder | joint, A |
| Optimised Region-Growing Algorithm for Extraction of the Loess | shoulder | -Line from DEMs, An |
| Painful data: The UNBC-McMaster | shoulder | pain expression archive database |
| Painful monitoring: Automatic pain monitoring using the UNBC-McMaster | shoulder | pain expression archive database |
| Point Cloud Oriented | shoulder | Line Extraction In Loess Hilly Area |
| Polly: Telepresence from a Guide's | shoulder | |
| Profiles Based on Ridge and Valley Lines to Extract | shoulder | Lines on the Loess Plateau, The |
| Review on Design and Control Aspects of Robotic | shoulder | Rehabilitation Orthoses |
| Robust Head- | shoulder | Detection by PCA-Based Multilevel HOG-LBP Detector for People Counting |
| Robust Head- | shoulder | Detection Using a Two-Stage Cascade Framework |
| Robust real-time attention-based head- | shoulder | detection for video surveillance |
| Saliency model-based face segmentation and tracking in head-and- | shoulder | video sequences |
| Segmentation Scheme for Head- | shoulder | in MPEG Compressed Domain, A |
| shoulder | gesture interface for operating electric wheelchair |
| shoulder | -Surfing Resistant Authentication Using Pass Pattern of Pattern Lock |
| Simulation of hard | shoulder | running combined with queue warning during traffic accident with CTM model |
| Text-Driven Automatic Frame Generation Using MPEG-4 Synthetic/Natural Hybrid Coding for 2-D Head-and- | shoulder | Scene |
| Three-dimensional reconstruction of the bony structures involved in the articular complex of the human | shoulder | using shape-based interpolation and contour-based extrapolation |
| Topographic Spatial Variation Analysis of Loess | shoulder | Lines in the Loess Plateau of China Based on MF-DFA |
| Towards computer-assisted surgery in | shoulder | joint replacement |
| Video object segmentation for head- | shoulder | sequences in the cellular neural networks architecture |
| VIS-NIR, Red-Edge and NIR- | shoulder | Based Normalized Vegetation Indices Response to Co-Varying Leaf and Canopy Structural Traits in Heterogeneous Grasslands |
41 for shoulder