2021.8.2 Vision papers

07-30-2021	Out-of-Core Surface Reconstruction via Global TGVTGV Minimization by Nikolai Poliarnyi
07-30-2021	Perceiver IO: A General Architecture for Structured Inputs & Outputs by Andrew Jaegle et al
07-27-2021	DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis by Yanchao Yang et al
07-27-2021	Unsupervised Outlier Detection using Memory and Contrastive Learning by Ning Huyan et al
07-27-2021	Computer Vision-Based Guidance Assistance Concept for Plowing Using RGB-D Camera by Erkin Türköz et al
07-28-2021	Recursively Conditional Gaussian for Ordinal Unsupervised Domain Adaptation by Xiaofeng Liu et al
07-28-2021	A Proof-of-Concept Study of Artificial Intelligence Assisted Contour Revision by Ti Bai et al
07-29-2021	Viewpoint-Invariant Exercise Repetition Counting by Yu Cheng Hsu et al
07-28-2021	Bayesian Embeddings for Few-Shot Open World Recognition by John Willes et al
07-27-2021	Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks by Richard J. Chen et al
07-28-2021	An explainable two-dimensional single model deep learning approach for Alzheimers disease diagnosis and brain atrophy localization by Fan Zhang et al
07-29-2021	Fully-Automatic Pipeline for Document Signature Analysis to Detect Money Laundering Activities by Nikhil Woodruff et al
07-28-2021	CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation by Tao Hu et al
07-30-2021	Recognizing Emotions evoked by Movies using Multitask Learning by Hassan Hayat et al
07-28-2021	Video Based Fall Detection Using Human Poses by Ziwei Chen et al
07-27-2021	Adaptive Denoising via GainTuning by Sreyas Mohan et al
07-27-2021	StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement by Yuda Song et al
07-27-2021	Vision-Guided Forecasting -- Visual Context for Multi-Horizon Time Series Forecasting by Eitan Kosman et al
07-27-2021	Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition with Privacy Protection by Pawel Drozdowski et al
07-28-2021	Assessment of Deep Learning-based Heart Rate Estimation using Remote Photoplethysmography under Different Illuminations by Ze Yang et al
07-30-2021	Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining by Xunlin Zhan et al
07-28-2021	Efficient Human Pose Estimation by Maximizing Fusion and High-Level Spatial Attention by Zhiyuan Ren et al
07-27-2021	Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle by Jie Li et al
07-28-2021	DeepTeeth: A Teeth-photo Based Human Authentication System for Mobile and Hand-held Devices by Geetika Arora et al
07-30-2021	Topological Similarity Index and Loss Function for Blood Vessel Segmentation by R. J. Araújo et al
07-30-2021	Shadow Art Revisited: A Differentiable Rendering Based Approach by Kaustubh Sadekar et al
07-27-2021	Deep Reinforcement Learning for L3 Slice Localization in Sarcopenia Assessment by Othmane Laousy et al
07-29-2021	Swap-Free Fat-Water Separation in Dixon MRI using Conditional Generative Adversarial Networks by Nicolas Basty et al
07-27-2021	Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021 by Haisheng Su et al
07-27-2021	Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection by Shi-Xue Zhang et al
07-27-2021	MixFaceNets: Extremely Efficient Face Recognition Networks by Fadi Boutros et al
07-28-2021	A Similarity Measure of Histopathology Images by Deep Embeddings by Mehdi Afshari et al
07-29-2021	Guided Disentanglement in Generative Networks by Fabio Pizzati et al
07-27-2021	Excavating AI Re-excavated: Debunking a Fallacious Account of the JAFFE Dataset by Michael J. Lyons
07-28-2021	Normalization Matters in Weakly Supervised Object Localization by Jeesoo Kim et al
07-29-2021	Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation by Wenkang Shan et al
07-29-2021	PiBase: An IoT-based Security System using Raspberry Pi and Google Firebase by Venkat Margapuri et al
07-29-2021	Feature Importance-aware Transferable Adversarial Attacks by Zhibo Wang et al
07-30-2021	Automatic Vocabulary and Graph Verification for Accurate Loop Closure Detection by Haosong Yue et al
07-29-2021	Few-Shot and Continual Learning with Attentive Independent Mechanisms by Eugene Lee et al
07-27-2021	Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization by Fa-Ting Hong et al
07-27-2021	Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting by Changan Wang et al
07-27-2021	Exceeding the Limits of Visual-Linguistic Multi-Task Learning by Cameron R. Wolfe et al
07-27-2021	Optimizing Operating Points for High Performance Lesion Detection and Segmentation Using Lesion Size Reweighting by Brennan Nichyporuk et al
07-28-2021	Generalizing Fairness: Discovery and Mitigation of Unknown Sensitive Attributes by William Paul et al
07-28-2021	Surrogate Model-Based Explainability Methods for Point Cloud NNs by Hanxiao Tan et al
07-28-2021	CarveNet: Carving Point-Block for Complex 3D Shape Completion by Qing Guo et al
07-29-2021	Learning with Noisy Labels for Robust Point Cloud Segmentation by Shuquan Ye et al
07-27-2021	Image color correction, enhancement, and editing by Mahmoud Afifi
07-28-2021	A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification by Uddipan Mukherjee et al
07-28-2021	Learning the shape of female breasts: an open-access 3D statistical shape model of the female breast built from 110 breast scans by Maximilian Weiherer et al
07-28-2021	Adversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate by Xiaofeng Liu et al
07-30-2021	Enhancing Social Relation Inference with Concise Interaction Graph and Discriminative Scene Representation by Xiaotian Yu et al
07-30-2021	Fourier Series Expansion Based Filter Parametrization for Equivariant Convolutions by Qi Xie et al
07-27-2021	Identify Apple Leaf Diseases Using Deep Learning Algorithm by Daping Zhang et al
07-27-2021	Image Scene Graph Generation (SGG) Benchmark by Xiaotian Han et al
07-27-2021	ENHANCE (ENriching Health data by ANnotations of Crowd and Experts): A case study for skin lesion classification by Ralf Raumanns et al
07-27-2021	COPS: Controlled Pruning Before Training Starts by Paul Wimmer et al
07-27-2021	Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation by Song Tang et al
07-28-2021	Task-Specific Normalization for Continual Learning of Blind Image Quality Models by Weixia Zhang et al
07-28-2021	Neural Rays for Occlusion-aware Image-based Rendering by Yuan Liu et al
07-29-2021	From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection by Jiajun Deng et al
07-28-2021	UIBert: Learning Generic Multimodal Representations for UI Understanding by Chongyang Bai et al
07-27-2021	Is Object Detection Necessary for Human-Object Interaction Recognition? by Ying Jin et al
07-29-2021	Automatic Multi-Stain Registration of Whole Slide Images in Histopathology by Abubakr Shafique et al
07-30-2021	DPT: Deformable Patch-based Transformer for Visual Recognition by Zhiyang Chen et al
07-27-2021	Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network by Zhikang Zou et al
07-27-2021	RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly by Abhinav Narayan Harish et al
07-30-2021	The Minimum Edit Arborescence Problem and Its Use in Compressing Graph Collections [Extended Version] by Lucas Gnecco et al
07-29-2021	Machine Learning Advances aiding Recognition and Classification of Indian Monuments and Landmarks by Aditya Jyoti Paul et al
07-29-2021	What Does TERRA-REFs High Resolution, Multi Sensor Plant Sensing Public Domain Data Offer the Computer Vision Community? by David LeBauer et al
07-30-2021	Seeing poverty from space, how much can it be tuned? by Tomas Sako et al
07-30-2021	When Deep Learners Change Their Mind: Learning Dynamics for Active Learning by Javad Zolfaghari Bengar et al
07-27-2021	Multi-Scale Local-Temporal Similarity Fusion for Continuous Sign Language Recognition by Pan Xie et al
07-27-2021	Angels Girl for Blind Painters: an Efficient Painting Navigation System Validated by Multimodal Evaluation Approach by Hang Liu et al
07-31-2021	DCT2net: an interpretable shallow CNN for image denoising by Sébastien Herbreteau et al
07-27-2021	Improving ClusterGAN Using Self-AugmentedInformation Maximization of Disentangling LatentSpaces by Tanmoy Dam et al
07-27-2021	DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization by Zhaoyu Su et al
07-27-2021	VIPose: Real-time Visual-Inertial 6D Object Pose Tracking by Rundong Ge et al
07-28-2021	AI assisted method for efficiently generating breast ultrasound screening reports by Shuang Ge et al
07-27-2021	Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning by Reece Walsh et al
07-28-2021	Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detection by Xinyang Feng et al
07-27-2021	A Tale Of Two Long Tails by Daniel D'souza et al
07-28-2021	TEDS-Net: Enforcing Diffeomorphisms in Spatial Transformers to Guarantee Topology Preservation in Segmentations by Madeleine K. Wyburd et al
07-30-2021	Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN by Xiaohan Ding et al
07-30-2021	T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation by Ruihuang Li et al

07-30-2021	Single image deep defocus estimation and its applications by Fernando J. Galetto et al
07-28-2021	Egyptian Sign Language Recognition Using CNN and LSTM by Ahmed Elhagry et al
07-29-2021	Temporal Feature Warping for Video Shadow Detection by Shilin Hu et al
07-29-2021	ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation by Yanchao Yang et al
07-27-2021	Learning Local Recurrent Models for Human Mesh Recovery by Runze Li et al
07-27-2021	Dynamic and Static Object Detection Considering Fusion Regions and Point-wise Features by Andrés Gómez et al
07-29-2021	Structure and Performance of Fully Connected Neural Networks: Emerging Complex Network Properties by Leonardo F. S. Scabini et al
07-29-2021	The Need and Status of Sea Turtle Conservation and Survey of Associated Computer Vision Advances by Aditya Jyoti Paul
07-27-2021	Predicting Take-over Time for Autonomous Driving with Real-World Data: Robust Data Augmentation, Models, and Evaluation by Akshay Rangesh et al
07-28-2021	Inferring bias and uncertainty in camera calibration by Annika Hagemann et al
07-29-2021	Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows by Tom Wehrbein et al
07-30-2021	Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation by Duo Peng et al
07-27-2021	Multi-modal estimation of the properties of containers and their content: survey and evaluation by Alessio Xompero et al
07-28-2021	Shape Controllable Virtual Try-on for Underwear Models by Xin Gao et al
07-28-2021	Retinal Microvasculature as Biomarker for Diabetes and Cardiovascular Diseases by Anusua Trivedi et al
07-27-2021	Global Aggregation then Local Distribution for Scene Parsing by Xiangtai Li et al
07-28-2021	High-speed object detection with a single-photon time-of-flight image sensor by Germán Mora-Martín et al
07-28-2021	Hierarchical Self-supervised Augmented Knowledge Distillation by Chuanguang Yang et al
07-28-2021	Cascaded Residual Density Network for Crowd Counting by Kun Zhao et al
07-27-2021	Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification by Zefeng Ding et al
07-29-2021	Self-Supervised Learning for Fine-Grained Image Classification by Farha Al Breiki et al
07-28-2021	Social Processes: Self-Supervised Forecasting of Nonverbal Cues in Social Conversations by Chirag Raman et al
07-28-2021	Evaluating the Use of Reconstruction Error for Novelty Localization by Patrick Feeney et al
07-29-2021	Exploring Low-light Object Detection Techniques by Winston Chen et al
07-29-2021	Real-time Streaming Perception System for Autonomous Driving by Yongxiang Gu et al
07-29-2021	DarkLighter: Light Up the Darkness for UAV Tracking by Junjie Ye et al
07-30-2021	Medical Instrument Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning by Hongxu Yang et al
07-30-2021	Pix2Point: Learning Outdoor 3D Using Sparse Point Clouds and Optimal Transport by Rémy Leroy et al
07-29-2021	Mapping Vulnerable Populations with AI by Benjamin Kellenberger et al
07-30-2021	Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images by Adrià Casamitjana et al
07-29-2021	Bridging Gap between Image Pixels and Semantics via Supervision: A Survey by Jiali Duan et al
07-28-2021	SimROD: A Simple Adaptation Method for Robust Object Detection by Rindra Ramamonjison et al
07-27-2021	Content-aware Directed Propagation Network with Pixel Adaptive Kernel Attention by Min-Cheol Sagong et al
07-28-2021	Predicting the Future from First Person (Egocentric) Vision: A Survey by Ivan Rodin et al
07-28-2021	Squeeze-Excitation Convolutional Recurrent Neural Networks for Audio-Visual Scene Classification by Javier Naranjo-Alcazar et al
07-28-2021	C^3Net: End-to-End deep learning for efficient real-time visual active camera control by Christos Kyrkou
07-28-2021	Abnormal Behavior Detection Based on Target Analysis by Luchuan Song et al
07-27-2021	Technical Report: Quality Assessment Tool for Machine Learning with Clinical CT by Riqiang Gao et al
07-29-2021	PPT Fusion: Pyramid Patch Transformerfor a Case Study in Image Fusion by Yu Fu et al
07-29-2021	Towards robust vision by multi-task learning on monkey visual cortex by Shahd Safarani et al
07-28-2021	Graph Constrained Data Representation Learning for Human Motion Segmentation by Mariella Dimiccoli et al
07-29-2021	Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition by Jingwei Yan et al
07-30-2021	OpenForensics: Large-Scale Challenging Dataset For Multi-Face Forgery Detection And Segmentation In-The-Wild by Trung-Nghia Le et al
07-30-2021	ManiSkill: Learning-from-Demonstrations Benchmark for Generalizable Manipulation Skills by Tongzhou Mu et al
07-30-2021	Instant Visual Odometry Initialization for Mobile AR by Alejo Concha et al
07-30-2021	Relightable Neural Video Portrait by Youjia Wang et al
07-28-2021	WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification by Qiufu Li et al
07-27-2021	Improved-Mask R-CNN: Towards an Accurate Generic MSK MRI instance segmentation platform (Data from the Osteoarthritis Initiative) by Banafshe Felfeliyan et al
07-27-2021	Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Clouds by Wei Zhou et al
07-29-2021	CI-Net: Contextual Information for Joint Semantic Segmentation and Depth Estimation by Tianxiao Gao et al
07-28-2021	Accurate Grid Keypoint Learning for Efficient Video Prediction by Xiaojie Gao et al
07-29-2021	Geometry Uncertainty Projection Network for Monocular 3D Object Detection by Yan Lu et al
07-28-2021	A Computer Vision-Based Approach for Driver Distraction Recognition using Deep Learning and Genetic Algorithm Based Ensemble by Ashlesha Kumar et al
07-29-2021	VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation by Zeyu Hu et al
07-29-2021	Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection by Yinmin Zhang et al
07-28-2021	Similarity and symmetry measures based on fuzzy descriptors of image objects` composition by Marcin Iwanowski et al
07-27-2021	Co-Transport for Class-Incremental Learning by Da-Wei Zhou et al
07-27-2021	Enriching Local and Global Contexts for Temporal Action Localization by Zixin Zhu et al
07-27-2021	A Physiologically-Adapted Gold Standard for Arousal during Stress by Alice Baird et al
07-30-2021	Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation by Bowen Zhang et al
07-28-2021	Unsupervised Segmentation for Terracotta Warrior with Seed-Region-Growing CNN(SRG-Net) by Yao Hu et al
07-29-2021	Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness by Runzhou Ge et al
07-29-2021	Video Generation from Text Employing Latent Path Construction for Temporal Modeling by Amir Mazaheri et al
07-29-2021	Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes by Wenhang Ge et al
07-28-2021	Fast and Scalable Image Search For Histology by Chengkuan Chen et al
07-28-2021	Spatial Uncertainty-Aware Semi-Supervised Crowd Counting by Yanda Meng et al
07-29-2021	Recurrent U-net for automatic pelvic floor muscle segmentation on 3D ultrasound by Frieda van den Noort et al
07-27-2021	Continual Learning with Neuron Activation Importance by Sohee Kim et al
07-29-2021	Enhancing Adversarial Robustness via Test-time Transformation Ensembling by Juan C. Pérez et al
07-29-2021	Probabilistic and Geometric Depth: Detecting Objects in Perspective by Tai Wang et al
07-27-2021	Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection by Jinlei Hou et al
07-27-2021	A Thorough Review on Recent Deep Learning Methodologies for Image Captioning by Ahmed Elhagry et al
07-27-2021	Experimenting with Self-Supervision using Rotation Prediction for Image Captioning by Ahmed Elhagry et al
07-27-2021	A New Split for Evaluating True Zero-Shot Action Recognition by Shreyank N Gowda et al
07-29-2021	The interpretation of endobronchial ultrasound image using 3D convolutional neural network for differentiating malignant and benign mediastinal lesions by Ching et al
07-28-2021	United We Learn Better: Harvesting Learning Improvements From Class Hierarchies Across Tasks by Sindi Shkodrani et al
07-28-2021	Underwater inspection and intervention dataset by Tomasz Luczynski et al
07-28-2021	Discovering 3D Parts from Image Collections by Chun-Han Yao et al
07-29-2021	FREE: Feature Refinement for Generalized Zero-Shot Learning by Shiming Chen et al
07-29-2021	RigNet: Repetitive Image Guided Network for Depth Completion by Zhiqiang Yan et al
07-29-2021	Why You Should Try the Real Data for the Scene Text Recognition by Vladimir Loginov
07-30-2021	Iterative, Deep, and Unsupervised Synthetic Aperture Sonar Image Segmentation by Yung-Chen Sun et al
07-27-2021	Improving Video Instance Segmentation via Temporal Pyramid Routing by Xiangtai Li et al
07-30-2021	On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals by Haizhou Shi et al
07-29-2021	Generalizing Gaze Estimation with Outlier-guided Collaborative Adaptation by Yunfei Liu et al
07-27-2021	PlaneTR: Structure-Guided Transformers for 3D Plane Recovery by Bin Tan et al
07-27-2021	PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution by Pan Xie et al
07-29-2021	Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GAN by Fariborz Taherkhani et al
07-29-2021	Self-Paced Contrastive Learning for Semi-supervisedMedical Image Segmentation with Meta-labels by Jizong Peng et al
07-27-2021	Discriminative-Generative Representation Learning for One-Class Anomaly Detection by Xuan Xia et al
07-28-2021	Sign and Search: Sign Search Functionality for Sign Language Lexica by Manolis Fragkiadakis et al
07-29-2021	From Continuity to Editability: Inverting GANs with Consecutive Images by Yangyang Xu et al
07-29-2021	Open-World Entity Segmentation by Lu Qi et al
07-29-2021	Rethinking and Improving Relative Position Encoding for Vision Transformer by Kan Wu et al
07-28-2021	TransAction: ICL-SJTU Submission to EPIC-Kitchens Action Anticipation Challenge 2021 by Xiao Gu et al
07-27-2021	Energy-Based Open-World Uncertainty Modeling for Confidence Calibration by Yezhen Wang et al
07-30-2021	SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection by Hengli Wang et al
07-30-2021	High-Resolution Depth Maps Based on TOF-Stereo Fusion by Vineet Gandhi et al
07-30-2021	Can non-specialists provide high quality gold standard labels in challenging modalities? by Samuel Budd et al
07-29-2021	ReFormer: The Relational Transformer for Image Captioning by Xuewen Yang et al
07-27-2021	A persistent homology-based topological loss for CNN-based multi-class segmentation of CMR by Nick Byrne et al
07-27-2021	Insights from Generative Modeling for Neural Video Compression by Ruihan Yang et al
07-27-2021	Unsupervised Monocular Depth Estimation in Highly Complex Environments by Chaoqiang Zhao et al
07-27-2021	Real-Time Activity Recognition and Intention Recognition Using a Vision-based Embedded System by Sahar Darafsh et al
07-28-2021	Lighter Stacked Hourglass Human Pose Estimation by Ahmed Elhagry et al
07-28-2021	Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth by Chenhang He et al
07-28-2021	Improving Multi-View Stereo via Super-Resolution by Eugenio Lomurno et al
07-28-2021	Learning-Based Depth and Pose Estimation for Monocular Endoscope with Loss Generalization by Aji Resindra Widya et al
07-27-2021	Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers by Wen Wang et al
07-27-2021	Greedy Gradient Ensemble for Robust Visual Question Answering by Xinzhe Han et al
07-27-2021	CKConv: Learning Feature Voxelization for Point Cloud Analysis by Sungmin Woo et al
07-27-2021	Subjective evaluation of traditional and learning-based image coding methods by Zhigao Fang et al
07-27-2021	Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework by Qingyu Song et al
07-29-2021	Using Visual Anomaly Detection for Task Execution Monitoring by Santosh Thoduka et al
07-29-2021	Personalized Trajectory Prediction via Distribution Discrimination by Guangyi Chen et al
07-29-2021	Human Trajectory Prediction via Counterfactual Analysis by Guangyi Chen et al
07-29-2021	A Unified Efficient Pyramid Transformer for Semantic Segmentation by Fangrui Zhu et al
07-28-2021	Rank-based verification for long-term face tracking in crowded scenes by Germán Barquero et al
07-28-2021	A Novel CropdocNet for Automated Potato Late Blight Disease Detection from the Unmanned Aerial Vehicle-based Hyperspectral Imagery by Yue Shi et al
07-28-2021	Pseudo-LiDAR Based Road Detection by Libo Sun et al
07-29-2021	Semi-Supervised Active Learning with Temporal Output Discrepancy by Siyu Huang et al