ICCV2019 oral papers
-
Exploring Randomly Wired Neural Networks for Image Recognition
-
Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation
-
Multinomial Distribution Learning for Effective Neural Architecture Search
-
Searching for MobileNetV3
-
Data-Free Quantization Through Weight Equalization and Bias Correction
-
A Camera That CNNs: Towards Embedded Neural Networks on Pixel Processor Arrays
-
Knowledge Distillation via Route Constrained Optimization
-
Distillation-Based Training for Multi-Exit Architectures
-
Similarity-Preserving Knowledge Distillation
-
Many Task Learning With Task Routing
-
Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels
-
Transferability and Hardness of Supervised Classification Tasks
-
Moment Matching for Multi-Source Domain Adaptation
-
Unsupervised Domain Adaptation via Regularized Conditional Alignment
-
Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
-
UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation
-
Episodic Training for Domain Generalization
-
Domain Adaptation for Structured Output via Discriminative Patch Representations
-
Semi-Supervised Learning by Augmented Distribution Alignment
-
S4L: Self-Supervised Semi-Supervised Learning
-
Privacy Preserving Image Queries for Camera Localization
-
Calibration Wizard: A Guidance System for Camera Calibration Based on Modelling Geometric and Corner Uncertainty
-
Gated2Depth: Real-Time Dense Lidar From Gated Images
-
X-Section: Cross-Section Prediction for Enhanced RGB-D Fusion
-
Learning an Event Sequence Embedding for Dense Event-Based Deep Stereo
-
Point-Based Multi-View Stereo Network
-
Discrete Laplace Operator Estimation for Dynamic 3D Reconstruction
-
Deep Non-Rigid Structure From Motion
-
Equivariant Multi-View Networks
-
Interpolated Convolutional Networks for 3D Point Cloud Understanding
-
Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
-
PointCloud Saliency Maps
-
ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics
-
Unsupervised Deep Learning for Structured Shape Matching
-
Linearly Converging Quasi Branch and Bound Algorithms for Global Rigid Registration
-
Consensus Maximization Tree Search Revisited
-
Quasi-Globally Optimal and Efficient Vanishing Point Estimation in Manhattan World
-
An Efficient Solution to the Homography-Based Relative Pose Problem With a Common Reference Direction
-
A Quaternion-Based Certifiably Optimal Solution to the Wahba Problem With Outliers
-
PLMP - Point-Line Minimal Problems in Complete Multi-View Visibility
-
Sampling-Free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
-
Universal Adversarial Perturbation via Prior Driven Uncertainty Approximation
-
Understanding Deep Networks via Extremal Perturbations and Smooth Masks
-
Unsupervised Pre-Training of Image Features on Non-Curated Data
-
Learning Local Descriptors With a CDF-Based Dynamic Soft Margin
-
Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
-
Linearized Multi-Sampling for Differentiable Image Transformation
-
AdaTransform: Adaptive Data Transformation
-
CARAFE: Content-Aware ReAssembly of FEatures
-
AFD-Net: Aggregated Feature Difference Learning for Cross-Spectral Image Patch Matching
-
Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval
-
Unsupervised Neural Quantization for Compressed-Domain Similarity Search
-
Siamese Networks: The Tale of Two Manifolds
-
Learning Combinatorial Embedding Networks for Deep Graph Matching
-
Fashion Retrieval via Graph Reasoning Networks on a Similarity Pyramid
-
Wavelet Domain Style Transfer for an Effective Perception-Distortion Tradeoff in Single Image Super-Resolution
-
Toward Real-World Single Image Super-Resolution: A New Benchmark and a New Model
-
RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution
-
Progressive Fusion Video Super-Resolution Network via Exploiting Non-Local Spatio-Temporal Correlations
-
Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications
-
Dynamic PET Image Reconstruction Using Nonnegative Matrix Factorization Incorporated With Deep Image Prior
-
DSIC: Deep Stereo Image Compression
-
Variable Rate Deep Image Compression With a Conditional Autoencoder
-
Real Image Denoising With Feature Attention
-
Noise Flow: Noise Modeling With Conditional Normalizing Flows
-
Bottleneck Potentials in Markov Random Fields
-
Seeing Motion in the Dark
-
SENSE: A Shared Encoder Network for Scene-Flow Estimation
-
Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?
-
Controllable Artistic Text Style Transfer via Shape-Matching GAN
-
Understanding Generalized Whitening and Coloring Transform for Universal Style Transfer
-
Learning Implicit Generative Models by Matching Perceptual Features
-
Free-Form Image Inpainting With Gated Convolution
-
FiNet: Compatible and Diverse Fashion Image Inpainting
-
InGAN: Capturing and Retargeting the “DNA” of a Natural Image
-
Seeing What a GAN Cannot Generate
-
COCO-GAN: Generation by Parts via Conditional Coordinating
-
Neural Turtle Graphics for Modeling City Road Layouts
-
Texture Fields: Learning Texture Representations in Function Space
-
PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows
-
Meta-Sim: Learning to Generate Synthetic Datasets
-
Specifying Object Attributes and Relations in Interactive Scene Generation
-
SinGAN: Learning a Generative Model From a Single Natural Image
-
VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
-
A Graph-Based Framework to Bridge Movies and Synopses
-
From Strings to Things: Knowledge-Enabled VQA Model That Can Read and Reason
-
Counterfactual Critic Multi-Agent Training for Scene Graph Generation
-
Robust Change Captioning
-
Attention on Attention for Image Captioning
-
Dynamic Graph Attention for Referring Expression Comprehension
-
Visual Semantic Reasoning for Image-Text Matching
-
Phrase Localization Without Paired Training Examples
-
Learning to Assemble Neural Module Tree Networks for Visual Grounding
-
A Fast and Accurate One-Stage Approach to Visual Grounding
-
Zero-Shot Grounding of Objects From Natural Language Queries
-
Towards Unconstrained End-to-End Text Spotting
-
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
-
Variational Adversarial Active Learning
-
Confidence Regularized Self-Training
-
Anchor Loss: Modulating Loss Scale Based on Prediction Difficulty
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Ryou_Anchor_Loss_Modulating_Loss_Scale_Based_on_Prediction_Difficulty_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=24)]
- Local Aggregation for Unsupervised Learning of Visual Embeddings
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhuang_Local_Aggregation_for_Unsupervised_Learning_of_Visual_Embeddings_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=36)]
- PR Product: A Substitute for Inner Product in Neural Networks
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_PR_Product_A_Substitute_for_Inner_Product_in_Neural_Networks_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=46)]
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Yun_CutMix_Regularization_Strategy_to_Train_Strong_Classifiers_With_Localizable_Features_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=54)]
- Towards Interpretable Object Detection by Unfolding Latent Structures
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Towards_Interpretable_Object_Detection_by_Unfolding_Latent_Structures_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=62)]
- Scaling Object Detection by Transferring Classification Weights
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Kuen_Scaling_Object_Detection_by_Transferring_Classification_Weights_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=68)]
- Scale-Aware Trident Networks for Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Scale-Aware_Trident_Networks_for_Object_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=77)]
- Object-Aware Instance Labeling for Weakly Supervised Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Kosugi_Object-Aware_Instance_Labeling_for_Weakly_Supervised_Object_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=89)]
- Generative Modeling for Small-Data Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Generative_Modeling_for_Small-Data_Object_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=99)]
- Transductive Learning for Zero-Shot Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Rahman_Transductive_Learning_for_Zero-Shot_Object_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=110)]
- Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Kim_Self-Training_and_Adversarial_Background_Regularization_for_Unsupervised_Domain_Adaptive_One-Stage_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=118)]
- Memory-Based Neighbourhood Embedding for Visual Recognition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Memory-Based_Neighbourhood_Embedding_for_Visual_Recognition_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=124)]
- Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Fu_Self-Similarity_Grouping_A_Simple_Unsupervised_Cross_Domain_Adaptation_Approach_for_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=132)]
- Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Deep_Reinforcement_Active_Learning_for_Human-in-the-Loop_Person_Re-Identification_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=140)]
- A Dual-Path Model With Adaptive Attention for Vehicle Re-Identification
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Khorramshahi_A_Dual-Path_Model_With_Adaptive_Attention_for_Vehicle_Re-Identification_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=149)]
- Bayesian Loss for Crowd Count Estimation With Point Supervision
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Ma_Bayesian_Loss_for_Crowd_Count_Estimation_With_Point_Supervision_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=157)]
- Learning Spatial Awareness to Improve Crowd Counting
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Cheng_Learning_Spatial_Awareness_to_Improve_Crowd_Counting_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/xzygVl7ZncQ?tocitem=167)]
- GradNet: Gradient-Guided Network for Visual Object Tracking
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_GradNet_Gradient-Guided_Network_for_Visual_Object_Tracking_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=2)]
- FAMNet: Joint Learning of Feature, Affinity and Multi-Dimensional Assignment for Online Multiple Object Tracking
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Chu_FAMNet_Joint_Learning_of_Feature_Affinity_and_Multi-Dimensional_Assignment_for_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=9)]
- Learning Discriminative Model Prediction for Tracking
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Bhat_Learning_Discriminative_Model_Prediction_for_Tracking_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=18)]
- DynamoNet: Dynamic Action and Motion Network
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Diba_DynamoNet_Dynamic_Action_and_Motion_Network_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=30)]
- SlowFast Networks for Video Recognition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Feichtenhofer_SlowFast_Networks_for_Video_Recognition_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=37)]
- Generative Multi-View Human Action Recognition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Generative_Multi-View_Human_Action_Recognition_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=46)]
- Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Multi-Agent_Reinforcement_Learning_Based_Frame_Sampling_for_Effective_Untrimmed_Video_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=54)]
- SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Korbar_SCSampler_Sampling_Salient_Clips_From_Video_for_Efficient_Action_Recognition_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=60)]
- Weakly Supervised Energy-Based Learning for Action Segmentation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Weakly_Supervised_Energy-Based_Learning_for_Action_Segmentation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=70)]
- What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Furnari_What_Would_You_Expect_Anticipating_Egocentric_Actions_With_Rolling-Unrolling_LSTMs_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=80)]
- PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Rasouli_PIE_A_Large-Scale_Dataset_and_Models_for_Pedestrian_Intention_Estimation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=91)]
- STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Huang_STGAT_Modeling_Spatial-Temporal_Interactions_for_Human_Trajectory_Prediction_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=106)]
- Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Mac_Learning_Motion_in_Feature_Space_Locally-Consistent_Deformable_Convolution_Networks_for_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=113)]
- Dual Attention Matching for Audio-Visual Event Localization
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Dual_Attention_Matching_for_Audio-Visual_Event_Localization_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=120)]
- Uncertainty-Aware Audiovisual Activity Recognition Using Deep Bayesian Variational Inference
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Subedar_Uncertainty-Aware_Audiovisual_Activity_Recognition_Using_Deep_Bayesian_Variational_Inference_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=130)]
- Non-Local Recurrent Neural Memory for Supervised Sequence Modeling
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Fu_Non-Local_Recurrent_Neural_Memory_for_Supervised_Sequence_Modeling_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=139)]
- Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Temporal_Attentive_Alignment_for_Large-Scale_Video_Domain_Adaptation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=146)]
- Action Assessment by Joint Relation Graphs
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Pan_Action_Assessment_by_Joint_Relation_Graphs_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=159)]
- Unsupervised Procedure Learning via Joint Dynamic Summarization
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Elhamifar_Unsupervised_Procedure_Learning_via_Joint_Dynamic_Summarization_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=167)]
- ViSiL: Fine-Grained Spatio-Temporal Video Similarity Learning
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Kordopatis-Zilos_ViSiL_Fine-Grained_Spatio-Temporal_Video_Similarity_Learning_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/8oUPyhwzIDo?tocitem=177)]
- Learning Single Camera Depth Estimation Using Dual-Pixels
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Garg_Learning_Single_Camera_Depth_Estimation_Using_Dual-Pixels_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=2)]
- Domain-Adaptive Single-View 3D Reconstruction
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Pinheiro_Domain-Adaptive_Single-View_3D_Reconstruction_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=13)]
- Transformable Bottleneck Networks
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Olszewski_Transformable_Bottleneck_Networks_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=22)]
- RIO: 3D Object Instance Re-Localization in Changing Indoor Environments
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wald_RIO_3D_Object_Instance_Re-Localization_in_Changing_Indoor_Environments_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=32)]
- Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Park_Pix2Pose_Pixel-Wise_Coordinate_Regression_of_Objects_for_6D_Pose_Estimation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=39)]
- CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_CDPN_Coordinates-Based_Disentangled_Pose_Network_for_Real-Time_RGB-Based_6-DoF_Object_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=49)]
- C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motion
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Novotny_C3DPO_Canonical_3D_Pose_Networks_for_Non-Rigid_Structure_From_Motion_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=65)]
- Learning to Reconstruct 3D Manhattan Wireframes From a Single Image
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhou_Learning_to_Reconstruct_3D_Manhattan_Wireframes_From_a_Single_Image_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=76)]
- Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_Soft_Rasterizer_A_Differentiable_Renderer_for_Image-Based_3D_Reasoning_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=91)]
- Learnable Triangulation of Human Pose
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Iskakov_Learnable_Triangulation_of_Human_Pose_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=100)]
- xR-EgoPose: Egocentric 3D Human Pose From an HMD Camera
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Tome_xR-EgoPose_Egocentric_3D_Human_Pose_From_an_HMD_Camera_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=110)]
- DeepHuman: 3D Human Reconstruction From a Single Image
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zheng_DeepHuman_3D_Human_Reconstruction_From_a_Single_Image_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=117)]
- A Neural Network for Detailed Human Depth Estimation From a Single Image
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Tang_A_Neural_Network_for_Detailed_Human_Depth_Estimation_From_a_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=125)]
- DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Xu_DenseRaC_Joint_3D_Pose_and_Shape_Estimation_by_Dense_Render-and-Compare_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=134)]
- Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Not_All_Parts_Are_Created_Equal_3D_Pose_Estimation_by_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/zem03fZWLrQ?tocitem=140)]
- Extreme View Synthesis
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Choi_Extreme_View_Synthesis_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=2)]
- View Independent Generative Adversarial Network for Novel View Synthesis
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Xu_View_Independent_Generative_Adversarial_Network_for_Novel_View_Synthesis_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=16)]
- Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Cascaded_Context_Pyramid_for_Full-Resolution_3D_Semantic_Scene_Completion_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=29)]
- View-Consistent 4D Light Field Superpixel Segmentation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Khan_View-Consistent_4D_Light_Field_Superpixel_Segmentation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=36)]
- GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhou_GLoSH_Global-Local_Spherical_Harmonics_for_Intrinsic_Image_Decomposition_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=44)]
- Surface Normals and Shape From Water
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Murai_Surface_Normals_and_Shape_From_Water_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=53)]
- Restoration of Non-Rigidly Distorted Underwater Images Using a Combination of Compressive Sensing and Local Polynomial Image Representations
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/James_Restoration_of_Non-Rigidly_Distorted_Underwater_Images_Using_a_Combination_of_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=60)]
- Learning Perspective Undistortion of Portraits
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhao_Learning_Perspective_Undistortion_of_Portraits_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=70)]
- Towards Photorealistic Reconstruction of Highly Multiplexed Lensless Images
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Khan_Towards_Photorealistic_Reconstruction_of_Highly_Multiplexed_Lensless_Images_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=83)]
- Unconstrained Motion Deblurring for Dual-Lens Cameras
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Mohan_Unconstrained_Motion_Deblurring_for_Dual-Lens_Cameras_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=96)]
- Stochastic Exposure Coding for Handling Multi-ToF-Camera Interference
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Lee_Stochastic_Exposure_Coding_for_Handling_Multi-ToF-Camera_Interference_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=107)]
- Convolutional Approximations to the General Non-Line-of-Sight Imaging Operator
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Ahn_Convolutional_Approximations_to_the_General_Non-Line-of-Sight_Imaging_Operator_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=120)]
- Agile Depth Sensing Using Triangulation Light Curtains
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Bartels_Agile_Depth_Sensing_Using_Triangulation_Light_Curtains_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=127)]
- Asynchronous Single-Photon 3D Imaging
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Gupta_Asynchronous_Single-Photon_3D_Imaging_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/IWkSJQ6xxdc?tocitem=140)]
- YOLACT: Real-Time Instance Segmentation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Bolya_YOLACT_Real-Time_Instance_Segmentation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=2)]
- Expectation-Maximization Attention Networks for Semantic Segmentation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Expectation-Maximization_Attention_Networks_for_Semantic_Segmentation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=10)]
- Multi-Class Part Parsing With Joint Boundary-Semantic Awareness
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zhao_Multi-Class_Part_Parsing_With_Joint_Boundary-Semantic_Awareness_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=15)]
- Explaining Neural Networks Semantically and Quantitatively
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Explaining_Neural_Networks_Semantically_and_Quantitatively_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=24)]
- PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_PANet_Few-Shot_Image_Semantic_Segmentation_With_Prototype_Alignment_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=28)]
- ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Kuo_ShapeMask_Learning_to_Segment_Novel_Objects_by_Refining_Shape_Priors_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=36)]
- Sequence Level Semantics Aggregation for Video Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Sequence_Level_Semantics_Aggregation_for_Video_Object_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=52)]
- Video Object Segmentation Using Space-Time Memory Networks
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Oh_Video_Object_Segmentation_Using_Space-Time_Memory_Networks_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=57)]
- Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Zero-Shot_Video_Object_Segmentation_via_Attentive_Graph_Neural_Networks_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=62)]
- MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_MeteorNet_Deep_Learning_on_Dynamic_3D_Point_Cloud_Sequences_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=69)]
- 3D Instance Segmentation via Multi-Task Metric Learning
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Lahoud_3D_Instance_Segmentation_via_Multi-Task_Metric_Learning_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=80)]
- DeepGCNs: Can GCNs Go As Deep As CNNs?
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Li_DeepGCNs_Can_GCNs_Go_As_Deep_As_CNNs_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=88)]
- Deep Hough Voting for 3D Object Detection in Point Clouds
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Qi_Deep_Hough_Voting_for_3D_Object_Detection_in_Point_Clouds_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=96)]
- M3D-RPN: Monocular 3D Region Proposal Network for Object Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Brazil_M3D-RPN_Monocular_3D_Region_Proposal_Network_for_Object_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=105)]
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Behley_SemanticKITTI_A_Dataset_for_Semantic_Scene_Understanding_of_LiDAR_Sequences_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=113)]
- WoodScape: A Multi-Task, Multi-Camera Fisheye Dataset for Autonomous Driving
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Yogamani_WoodScape_A_Multi-Task_Multi-Camera_Fisheye_Dataset_for_Autonomous_Driving_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=122)]
- Scalable Place Recognition Under Appearance Change for Autonomous Driving
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Doan_Scalable_Place_Recognition_Under_Appearance_Change_for_Autonomous_Driving_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=128)]
- Exploring the Limitations of Behavior Cloning for Autonomous Driving
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Codevilla_Exploring_the_Limitations_of_Behavior_Cloning_for_Autonomous_Driving_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=134)]
- Habitat: A Platform for Embodied AI Research
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Savva_Habitat_A_Platform_for_Embodied_AI_Research_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/2ntDYowHbZs?tocitem=143)]
- Towards Interpretable Face Recognition
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Yin_Towards_Interpretable_Face_Recognition_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=2)]
- Co-Mining: Deep Face Recognition With Noisy Labels
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Co-Mining_Deep_Face_Recognition_With_Noisy_Labels_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=12)]
- Few-Shot Adaptive Gaze Estimation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Park_Few-Shot_Adaptive_Gaze_Estimation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=17)]
- Live Face De-Identification in Video
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Gafni_Live_Face_De-Identification_in_Video_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=23)]
- Face Video Deblurring Using 3D Facial Priors
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Ren_Face_Video_Deblurring_Using_3D_Facial_Priors_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=31)]
- Semi-Supervised Monocular 3D Face Reconstruction With End-to-End Shape-Preserved Domain Transfer
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Piao_Semi-Supervised_Monocular_3D_Face_Reconstruction_With_End-to-End_Shape-Preserved_Domain_Transfer_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=39)]
- 3D Face Modeling From Diverse Raw Scan Data
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Liu_3D_Face_Modeling_From_Diverse_Raw_Scan_Data_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=49)]
- A Decoupled 3D Facial Shape Model by Adversarial Training
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Abrevaya_A_Decoupled_3D_Facial_Shape_Model_by_Adversarial_Training_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=58)]
- Photo-Realistic Facial Details Synthesis From Single Image
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_Photo-Realistic_Facial_Details_Synthesis_From_Single_Image_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=68)]
- S2GAN: Share Aging Factors Across Ages and Share Aging Trends Among Individuals
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/He_S2GAN_Share_Aging_Factors_Across_Ages_and_Share_Aging_Trends_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=78)]
- PuppetGAN: Cross-Domain Image Manipulation by Demonstration
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Usman_PuppetGAN_Cross-Domain_Image_Manipulation_by_Demonstration_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=84)]
- Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Zakharov_Few-Shot_Adversarial_Learning_of_Realistic_Neural_Talking_Head_Models_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=92)]
- Pose-Aware Multi-Level Feature Network for Human Object Interaction Detection
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Wan_Pose-Aware_Multi-Level_Feature_Network_for_Human_Object_Interaction_Detection_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=101)]
- TRB: A Novel Triplet Representation for Understanding 2D Human Body
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Duan_TRB_A_Novel_Triplet_Representation_for_Understanding_2D_Human_Body_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=109)]
- Learning Trajectory Dependencies for Human Motion Prediction
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Mao_Learning_Trajectory_Dependencies_for_Human_Motion_Prediction_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=120)]
- Cross-Domain Adaptation for Animal Pose Estimation
[[Paper](http://openaccess.thecvf.com/content_ICCV_2019/html/Cao_Cross-Domain_Adaptation_for_Animal_Pose_Estimation_ICCV_2019_paper.html)] [[Video](https://conftube.com/video/ByfFufRhuRc?tocitem=129)]