- Instructor: WANG Lin (linwang@ust.hk)
- TAs: SU Ying (ysuay@connect.ust.hk) and ZHU Qingyan (qzhuai@connect.ust.hk)
- Class time: Tuesday & Thursday 16.30 -17.50
- Office Hours: BY appointment only.
This is a task-oriented yet interaction-based course, which aims to scrutinize the recent trends and challenges of deep learning in visual intelligence tasks (learning methods, high- and low-level vision problems). This course will follow the way of flipped-classroom manner where the lecturer teaches the basics; meanwhile, the students will also be focused on active discussions, presentations (lecturing), and hands-on research projects under the guidance of the lecturer in the whole semester. Through this course, students will be equipped with the capability to critically challenge the existing methodologies/techniques and hopefully make breakthroughs in some new research directions.
- Paper summary (10%)
- Paper presentation and discussion (30%)
- Group project and paper submission (50%)
- Attendance and Participation (10%)
| Dates | Topics | Active Learning |
|---|---|---|
| 2/8 | Course introduction | |
| 2/10 | Course introduction | Overview of computer vision |
| 2/15 | Deep learning basics | TAs’ lectures for CNN basics, algorithm basics and Pytorch tuorial |
| 2/17 | Deep learning basics | TAs’ lectures for CNN basics, algorithm basics and Pytorch tuorial |
| 2/22 | DNN models in computer vision (GAN, RNN, RNN) | |
| 2/24 | DNN models in computer vision (GAN, RNN, RNN) | (1) Persenation (2) Review due 2/27 (3) Project meetings |
| 3/1 | Learning methods in computer vision (Transfer learning, domain adaptation, self/semi-supervised learning) | |
| 3/3 | Learning methods in computer vision ((Transfer learning, domain adaptation, self/semi-supervised learning)) | (1) Persenation (2) Review due 3/6 |
| 3/8 | Deep learning for image restoration and enhancement (I) deblurring, deraining, dehazing | |
| 3/10 | Deep learning for image restoration and enhancement (I) deblurring, deraining, dehazing | (1) Persenation (2) Review due 3/13 (3) Project proposal kick-off (one page) |
| 3/15 | Deep learning for image restoration and enhancement (II) Super-resolution, HDR imaging | |
| 3/17 | Deep learning for image restoration and enhancement (II) Super-resolution, HDR imaging | (1) Persenation (2) Review due 3/20 |
| 3/22 | Deep learning for scene understanding (I) Object detection & tracking | |
| 3/24 | Deep learning for scene understanding (I) Object detection & tracking | Project mid-term presentation |
| 3/29 | Deep learning for scene understanding (II) Semantic segmentation | |
| 3/31 | Deep learning for scene understanding (II) Semantic segmentation | (1) Persenation (2) Review due 4/3 |
| 4/5 | Computer vision with novel cameras (I) Event camera-based vision | |
| 4/7 | Computer vision with novel cameras (I) Event camera-based vision | (1) Persenation (2) Review due 4/10 |
| 4/12 | Computer vision with novel cameras (II) Thermal/360 camera-based vision | |
| 4/14 | Computer vision with novel cameras (II) Thermal/360 camera-based vision | (1) Persenation (2) Review due 4/17 (3) Project meetings |
| 4/19 | Depth and Motion Estimation in Vision | |
| 4/21 | Depth and Motion Estimation in Vision | (1) Persenation (2) Review due 4/24 |
| 4/26 | Adversarial robustness in computer vision (Adversrial attack and defense) | |
| 4/28 | Adversarial robustness in computer vision (Adversrial attack and defense) | (1) Persenation (2) Review due 4/31 (3) Project meetings |
| 5/3 | Potential and Challenges in computer vision (data, computation, learning, sensor) (self-driving and robotics) | |
| 5/5 | Potential and Challenges in computer vision (data, computation, learning, sensor) (self-driving and robotics) | (1) TA/Student lectures (2) final project Q/A |
| 5/10 | Project presentation and final paper submission | |
| 5/12 | Project presentation and final paper submission | Submission due 5/26 |
[Kingma and Welling 14] Auto-Encoding Variational Bayes, ICLR 2014.
[Kingma et al. 15] Variational Dropout and the Local Reparameterization Trick, NIPS 2015.
[Blundell et al. 15] Weight Uncertainty in Neural Networks, ICML 2015.
[Gal and Ghahramani 16] Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning, ICML 2016.
[Goodfellow et al. 14] Generative Adversarial Nets, NIPS 2014.
[Radford et al. 15] Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, ICLR 2016.
[Chen et al. 16] InfoGAN: Interpreting Representation Learning by Information Maximizing Generative Adversarial Nets, NIPS 2016.
[Arjovsky et al. 17] Wasserstein Generative Adversarial Networks, ICML 2017.
[Zhu et al. 17] Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, ICCV 2017.
[Liu et al. 17] UNIT: Unsupervised Image-to-Image Translation Networks, NeurIPS 2017.
[Choi et al. 18]StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation, CVPR 2018.
[Isola et al. 17] Image-to-Image Translation with Conditional Adversarial Networks, CVPR, 2017.
[Huang et al. 17] Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization, ICCV, 2017.
[Huang et al. 18] Multimodal Unsupervised Image-to-Image Translation, ECCV, 2018.
[Brock et al. 19] Large Scale GAN Training for High-Fidelity Natural Image Synthesis, ICLR 2019.
[Karras et al. 19] A Style-Based Generator Architecture for Generative Adversarial Networks, CVPR 2019.
[Karras et al. 20] Analyzing and Improving the Image Quality of StyleGAN, CVPR 2020.
[Park et al. 20] Contrastive Learning for Unpaired Image-to-Image Translation, ECCV 2020.
[Karras et al. 20] Training Generative Adversarial Networks with Limited Data, NeurIPS 2020.
[Xie et al. 20] Self-Supervised CycleGAN for Object-Preserving Image-to-Image Domain Adaptation, ECCV 2020.
[Mustafa et al. 20] Transformation Consistency Regularization– A Semi-Supervised Paradigm for
Image-to-Image Translation, ECCV 2020.
[Li et al. 20] Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation, ECCV, 2020.
[Xu et al. 21] Linear Semantics in Generative Adversarial Networks, CVPR, 2021.
[Cao et al. 21] ReMix: Towards Image-to-Image Translation with Limited Data, CVPR 2021.
[Liu et al. 21] DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network, CVPR 2021.
[Pizzati et al. 21] CoMoGAN: continuous model-guided image-to-image translation, CVPR 2021.
[Jin et al. 21] Teachers Do More Than Teach: Compressing Image-to-Image Models, CVPR 2021.
[Baek et al. 21] Rethinking the Truly Unsupervised Image-to-Image Translation, ICCV, 2021.
[Wang et al. 21] TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets, ICCV, 2021.
[Yang et al. 21] Global and Local Alignment Networks for Unpaired Image-to-Image Translation, Arxiv 2021.
[Jiang et al. 21] Focal Frequency Loss for Image Reconstruction and Synthesis, ICCV, 2021.
[Wang et al. 21] Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks, TPAMI, 2021.
[Hiton et al. 15] Distilling the Knowledge in a Neural Network, NIPS Workshop, 2015.
[Romero et al. 15] FitNets: Hints for Thin Deep Nets, ICLR, 2015.
[Gupta et al. 16] Cross Modal Distillation for Supervision Transfer, CVPR, 2016.
[Zagoruyko et al. 16] Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer, ICLR, 2017.
[Furlanello et al. 18] Born Again Neural Networks, ICML, 2018.
[Zhang et al. 18] Deep Mutual Learning, CVPR,2018.
[Tarvainen et al. 18]Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results, NIPS, 2018.
[Zhang et al. 19] Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation, ICCV, 2019.
[Heo et al. 19] A Comprehensive Overhaul of Feature Distillation, ICCV, 2019.
[Tung et al.19] Similarity-Preserving Knowledge Distillation, ICCV, 2019.
[Chen et al. 19] DAFL:Data-Free Learning of Student Networks, ICCV, 2019.
[Ahn et al. 19] Variational Information Distillation for Knowledge Transfer, CVPR, 2019.
[Tian et al. 20] Contrastive Representation Distillation, ICLR, 2020.
[Fang et al. 20] Data-Free Adversarial Distillation, CVPR, 2020.
[Yang et al. 20] MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution, ECCV, 2020.
[Yao et al. 20] Knowledge Transfer via Dense Cross-layer Mutual-distillation. ECCV 2020
[Guo et al. 20] Reducing the Teacher-Student Gap via Spherical Knowledge Disitllation, Arxiv, 2020.
[Ji et al. 21] Refine Myself by Teaching Myself: Feature Refinement via Self-Knowledge Distillation, CVPR, 2021.
[Liu et al. 21] Source-Free Domain Adaptation for Semantic Segmentation, CVPR, 2021.
[Chen et al. 21] Learning Student Networks in the Wild, CVPR, 2021.
[Xue et a. 21] Multimodal Knowledge Expansion，ICCV, 2021.
[ZHu et al. 21] Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher, ICCV, 2021.
[Kim et al. 21] Self-Knowledge Distillation with Progressive Refinement of Targets, ICCV, 2021.
[Son et al. 21] Densely Guided Knowledge Distillation using Multiple Teacher Assistants, ICCV, 2021.
[Long et al. 15] Learning Transferable Features with Deep Adaptation Networks, ICML, 2015.
[Tzeng et al. 17] Adversarial Discriminative Domain Adaptation, CVPR, 2017.
[Huang et al. 18] Domain Transfer Through Deep Activation Matching, ECCV, 2018.
[Bermu’dez-Chaco’n et al. 20] Domain Adaptive Multibranch Networks, ICLR, 2020.
[Carlucci et al. 17] AutoDIAL: Automatic DomaIn Alignment Layers, ICCV, 2017.
[Chang et al. 19] Domain-Specific Batch Normalization for Unsupervised Domain Adaptation, CVPR, 2019.
[Cui et al. 20] Towards Discriminability and Diversity:Batch Nuclear-norm Maximization under Label Insufficient Situations, CVPR 2020.
[Roy et al. 19] Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss, CVPR, 2019.
[Csurka et al. 17] Discrepancy-based networks for unsupervised domain adaptation: a comparative study, CVPRW, 2017.
[Murez et al. 18] Image to Image Translation for Domain Adaptation, CVPR, 2018.
[Liu et al. 17] Coupled Generative Adversarial Networks, NIPS, 2017.
[Hoffman et al. 18] CyCADA: Cycle-Consistent Adversarial Domain Adaptation, ICLR, 2018.
[Lee et al. 18] Diverse Image-to-Image Translation via Disentangled Representations, ECCV, 2018.
[Chen et al. 12] Marginalized Denoising Autoencoders for Domain Adaptation, ICML, 2012.
[Zhuang et al. 15] Supervised Representation Learning: Transfer Learning with Deep Autoencoders, IJCAI, 2015.
[ Ghifary et al. 16] Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation, ECCV, 2016.
[Bousmalis et al. 16] Domain Separation Networks, NIPS, 2016.
[French et al. 19] Self-ensembling for Visual Domain Adaptation, ICLR, 2019.
[Shu et al. 18] A DIRT-T Approach to Unsupervised Domain Adaptation, ICLR, 2018.
[ Deng et al. 19] Cluster Alignment with a Teacher for Unsupervised Domain Adaptation, ICCV, 2019.
[Chen et al. 19] Progressive Feature Alignment for Unsupervised Domain Adaptation, CVPR 2019.
[Zhang et al. 18] Progressive Feature Alignment for Unsupervised Domain Adaptation, CVPR 2018.
[Kang et al. 19] Contrastive Adaptation Network for Unsupervised Domain Adaptation, CVPR 2019.
[Guizilini et al. 21] Geometric Unsupervised Domain Adaptation for Semantic Segmentation, ICCV, 2021.
[Wang et al. 20] Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation, ECCV, 2020.
[Peng et al. 20] Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation, ECCV, 2020.
[Liu et al. 21] Source-Free Domain Adaptation for Semantic Segmentation, CVPR, 2021.
[Na et al. 21] FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation, CVPR, 2021.
[Sharma et al. 21] Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation, CVPR, 2021.
[Ahmed et al. 21]
Unsupervised Multi-source Domain Adaptation Without Access to Source Data, CVPR, 2021.
[He et al. 21] Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation, CVPR, 2021.
[Wu et al. 21] DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation, CVPR, 2021.
[Lengyel et al. 21] Zero-Shot Day-Night Domain Adaptation with a Physics Prior, ICCV, 2021.
[Li et al. 21] Semantic Concentration for Domain Adaptation, ICCV, 2021.
[Awais et al. 21] Adversarial Robustness for Unsupervised Domain Adaptation, ICCV, 2021.
[Sajjadi et al. 16] Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning, NIPS, 2016.
[Laine et al. 17] Temporal Ensembling for Semi-Supervised Learning，ICLR, 2017.
[Tarvainen et al. 17] Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results, NIPS, 2017.
[Miyato et al. 18] Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning, TPAMI, 2018.
[Verma et al. 19] Interpolation Consistency Training for Semi-Supervised Learning, NIPS, 2019.
[Lee et al. 13] Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks, ICML, 2013.
[Iscen et al. 19] Label Propagation for Deep Semi-supervised Learning, CVPR, 2019.
[Xie et al. 20] Self-training with Noisy Student improves ImageNet classification, CVPR, 2020.
[Berthelot et al. 19] MixMatch: A Holistic Approach to Semi-Supervised Learning, NIPS, 2019.
[Berthelot et al. 20] ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring, ICLR, 2020.
[Junnan Li et al. 20] DivideMix: Learning with Noisy Labels as Semi-supervised Learning, ICLR, 2020.
[Sohn et al. 20] FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence, NIPS, 2020.
[Quali et al. 20] An Overview of Deep Semi-Supervised Learning, 2020.
[Ke et al. 19] Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning, ICCV, 2019.
[Luo et al. 20] Semi-supervised Semantic Segmentation via Strong-weak Dual-branch Network, ECCV, 2020.
[Gao et al. 20] Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost, ECCV, 2020.
[Liu et al. 20] Generative View-Correlation Adaptation for Semi-Supervised Multi-View Learning, ECCV, 2020.
[Kuo et al. 20] FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning, ECCV, 2020.
[Mustafa et al. 20] Transformation Consistency Regularization – A Semi-Supervised Paradigm for Image-to-Image Translation, ECCV, 2020.
[Chen et al. 21] Semi-Supervised Semantic Segmentation With Cross Pseudo Supervision,CVPR, 2021.
[Lai et al. 21] Adaptive Consistency Regularization for Semi-Supervised Transfer Learning, CVPR,2021.
[Hu et al. 21] SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification,CVPR,2021.
[Zhou et al. 21] Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation, ICCV, 2021.
[Xiong et al. 21] Multiview Pseudo-Labeling for Semi-supervised Learning from Video, ICCV, 2021.
[Xu et al. 14] Deep Convolutional Neural Network for Image Deconvolution, NIPS, 2014.
[Zhang et al. 22] Deep Image Deblurring: A Survey, Arxiv, 2022.
[Dong et al. 21] Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring, NIPS, 2021.
[Nimisha et al., 17] Blur-Invariant Deep Learning for Blind-Deblurring, ICCV, 2017.
[Nah et al. 17] Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring, CVPR, 2017.
[Kupyn et al. 19] DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better, ICCV, 2019.
[Zhang et al. 20] Deblurring by Realistic Blurring, CVPR, 2020.
[Zhou et al. 19] Spatio-Temporal Filter Adaptive Network for Video Deblurring, ICCV, 2019.
[Nah et al. 19] Recurrent Neural Networks with Intra-Frame Iterations for Video Deblurring, CVPR, 2019.
[Purohit et al. 20] Region-Adaptive Dense Network for Efficient Motion Deblurring, AAAI,2020. (SoTA of single image deblur on GoPro dataset)
[Shen et al. 19] Human-Aware Motion Deblurring, ICCV, 2019.
[Rim et al. 20] Real-World Blur Dataset for Learning and Benchmarking Deblurring Algorithms, ECCV, 2020.
[Lin et al. 20] Learning Event-Driven Video Deblurring and Interpolation, ECCV, 2020.
[Zhong et al. 20] Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring, ECCV, 2020.
[Abuolaim et al. 20] Defocus Deblurring Using Dual-Pixel Data, ECCV, 2020.
[Cun et al. 20] Defocus Blur Detection via Depth Distillation, ECCV, 2020.
[Chen et al. 21] Learning a Non-blind Deblurring Network for Night Blurry Images, CVPR, 2021.
[Rozumnyi et al. 21] DeFMO: Deblurring and Shape Recovery of Fast Moving Objects, CVPR, 2021.
[Xu et al. 21] Motion Deblurring with Real Events, ICCV, 2021.
[Cho et al. 21] Rethinking Coarse-to-Fine Approach in Single Image Deblurring, ICCV, 2021.
[Shang et al. 21] Bringing Events into Video Deblurring with Non-consecutively Blurry Frames, ICCV, 2021.
[Deng et al. 21] Multi-Scale Separable Network for Ultra-High-Definition Video Deblurring, ICCV, 2021.
[Hu et al 21] Pyramid Architecture Search for Real-Time Image Deblurring, ICCV, 2021.
[Li et al. 19] Single Image Deraining: A Comprehensive Benchmark Analysis, CVPR, 2019.
[Li et al. 21] A Comprehensive Benchmark Analysis of Single Image Deraining:
Current Challenges and Future Perspectives, IJCV, 2021.
[Yang et al. 17] Deep Joint Rain Detection and Removal from a Single Image, CVPR, 2017.
[Zhang et al. 18] Density-aware Single Image De-raining using a Multi-stream Dense Network, CVPR, 2018.
[Hu et al. 19] Depth-attentional features for single-image rain removal, CVPR, 2019.
[Qian et al. 18] Attentive Generative Adversarial Network for Raindrop Removal from A Single Image, CVPR, 2018.
[Zhang et al. 19] Image de-raining using a conditional generative adversarial network, IEEE transactions on circuits and systems for video technology, 2019.
[Wei et al. 19] Semi-supervised Transfer Learning for Image Rain Removal, CVPR, 2019.
[Yang et al. 17] Deep Joint Rain Detection and Removal from a Single Image, CVPR, 2017.
[Hu et al. 17] Depth-Attentional Features for Single-Image Rain Removal, CVPR, 2019.
[Yasarla et al. 20] Syn2Real Transfer Learning for Image Deraining using Gaussian Processes, CVPR, 2020.
[Liu et al. 21] Unpaired Learning for Deep Image Deraining with Rain Direction Regularizer, ICCV, 2021.
[Zhou et al. 21] Image De-raining via Continual Learning, CVPR, 2021.
[Wang et al. 21] Multi-Decoding Deraining Network and Quasi-Sparsity Based Training, CVPR, 2021.
[Chen et al. 21] Robust Representation Learning with Feedback for Single Image Deraining, CVPR, 2021.
[Yue et al. 21] Semi-Supervised Video Deraining with Dynamical Rain Generator, CVPR, 2021.
[Yi et al. 21] Structure-Preserving Deraining with Residue Channel Prior Guidance, ICCV,2021.
[Huang et a. 21] Memory Oriented Transfer Learning for Semi-Supervised Image Deraining, CVPR, 2021.
[Chen et al. 21] Pre-Trained Image Processing Transformer, CVPR, 2021.
[Jiang et al. 21] Multi-Scale Progressive Fusion Network for Single Image Deraining, CVPR, 2020.
[Fu et al. 20] Lightweight Pyramid Networks for Image Deraining, IEEE Transactions on Neural Networks and Learning Systems, 2020.
[Gui et al. 21] A Comprehensive Survey on Image Dehazing Based on Deep Learning, IJCAI, 2021.
[Cai et al. 16] DehazeNet: An End-to-End System for Single Image Haze Removal, IEEE, TIP, 2016.
[Ren et al. 20] Single Image Dehazing via Multi-scale Convolutional Neural Networks
with Holistic Edges, IJCV, 2020. (Extension of the conference version at 2016)
[Li et al. 17] AOD-Net: All-in-One Dehazing Network, ICCV, 2017.
[Qin et al. 20] FFA-Net: Feature Fusion Attention Network for Single Image Dehazing, AAAI,2020.
[Zhang et al. 18] Densely Connected Pyramid Dehazing Network, CVPR, 2018.
[Ren et al. 18] Gated Fusion Network for Single Image Dehazing
, CVPR, 2018.
[Qu et al. 19] Enhanced Pix2pix Dehazing Network, CVPR, 2019.
[Hong et al. 20] Distilling Image Dehazing With Heterogeneous Task Imitation, CVPR, 2020.
[Shao et al. 20] Domain Adaptation for Image Dehazing, CVPR, 2020.
[Engin et al. 18]Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing, ECCVW, 2018.
[Li et al. 20] Zero-Shot Image Dehazing, IEEE TIP, 2020.
[Wu et al. 21] Contrastive Learning for Compact Single Image Dehazing, CVPR, 2021.
[Shyam et al. 21] Towards Domain Invariant Single Image Dehazing, AAAI, 2021.
[Zheng et al. 21] Ultra-High-Defifinition Image Dehazing via Multi-Guided Bilateral Learning, CVPR, 2021.
[Chen et al. 21] PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors, CVPR, 2021.
[Zhao et al. 21] BidNet: Binocular Image Dehazing without Explicit Disparity Estimation, CVPR, 2021.
[Kar et al. 21] Transmission Map and Atmospheric Light Guided Iterative Updater Network for Single Image Dehazing, CVPR, 2021.
[Li et al. 20] Semi-Supervised Image Dehazing, IEEE TIP, 2020.
[Yi et al. 21] Two-Step Image Dehazing with Intra-domain and Inter-domain Adaptation, Arxiv, 2021.
[Dong et al. 16] mage Super-Resolution Using Deep Convolutional Networks, ECCV,2016.(First deep learning-based method)
[Lim et al. 17] Enhanced Deep Residual Networks for Single Image Super-Resolution, CVPRW, 2017.
[Wang et al. 19] Deep Learning for Image Super-resolution: A Survey, IEEE TPAMI, 2021.
[Kim et al. 17] Accurate Image Super-Resolution Using Very Deep Convolutional Networks, CVPR, 2017.
[Tai et al. 17] MemNet: A Persistent Memory Network for Image Restoration, CVPR, 2017.
[Li et al. 18] Multi-scale Residual Network for Image Super-Resolution, ECCV, 2018.
[Zhang et al. 18] Image Super-Resolution Using Very Deep Residual Channel Attention Networks, ECCV, 2018.
[Zhang et al. 19] Residual Non-local Attention Networks for Image Restoration, ICLR, 2019.
[Dai et al. 19] Second-order Attention Network for Single Image Super-Resolution, CVPR, 2019.
[Han et al. 18] Image Super-Resolution via Dual-State Recurrent Networks, CVPR, 2018.
[Li et al. 18] Multi-scale Residual Network for Image Super-Resolution, ECCV, 2018.
[Ren et al. 18] Image Super Resolution Based on Fusing Multiple Convolution Neural Networks, CVPRW, 2017.
[Ahn et al. 18] Fast, accurate, and lightweight
super-resolution with cascading residual network, ECCV, 2018.
[Zhang et al. 19] DCSR: Dilated Convolutions for Single Image Super-Resolution, IEEE TIP, 2019.
[Zhantg et al. 18] Residual Dense Network for Image Super-Resolution, CVPR, 2018.
[Hu et al. 19] Meta-SR: A Magnification-Arbitrary Network for Super-Resolution, CVPR, 2021.
[Chen et al. 21] Learning Continuous Image Representation with Local Implicit Image Function, CVPR, 2021.
[Lee et al. 20] Learning with Privileged Information for Efficient Image Super-Resolution, ECCV, 2020.
[Hu et al. 21] Towards Compact Single Image Super-Resolution via Contrastive Self-distillation, IJCAI, 2021.
[Cai et al. 19] Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model, ICCV, 2019.
[Wei et al. 20] Component Divide-and-Conquer for Real-World Image Super-Resolution, ECCV, 2021.
[Wang et al. 21] Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective, ICCV, 2021.
[Maeda et a. 20] Unpaired Image Super-Resolution using Pseudo-Supervision, CVPR, 2020.
[Shocher et al. 18] “Zero-Shot” Super-Resolution using Deep Internal Learning, CVPR, 2018.
[Wei et al. 21] Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective, ICCV, 2021.
[Zhang et al. 21] Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training, CVPR, 2021.
[Sefi et al. 20] Blind Super-Resolution Kernel Estimation using an Internal-GAN, NIPS, 2020.
[Cheng et a. 20] Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning, ECCV, 2020.
[Sun et al. 21] Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution, CVPR, 2021.
[Wang et al. 21] Unsupervised Degradation Representation Learning for Blind Super-Resolution, CVPR, 2021.
[Son et al. 21] SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation, CVPR, 2021.
[Jo et al. 21] Tackling the Ill-Posedness of Super-Resolution through Adaptive Target Generation, CVPR, 2021.
[Mei et al. 21] Image Super-Resolution with Non-Local Sparse Attention, CVPR, 2021.
[Wang et al. 21] Learning a Single Network for Scale-Arbitrary Super-Resolution, ICCV, 2021.
[Wang et al. 21] Dual-Camera Super-Resolution with Aligned Attention Modules, CVPR, 2021.
[Chan et al. 21] BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond, ICCV, 2021.
[Yi et al. 21] Omniscient Video Super-Resolution, ICCV, 2021.
[Tian et al. 20] TDAN: Temporally Deformable Alignment Network for Video Super-Resolution, CVPR, 2020.
[Wang et al. 19] EDVR: Video Restoration With Enhanced Deformable Convolutional Networks, CVPRW, 2019.
[Wang et al. 21] Deep Learning for HDR Imaging:State-of-the-Art and Future Trends, IEEE TPAMI, 2021.
[Kalantrai et al. 17] Deep High Dynamic Range Imaging of Dynamic Scenes, Siggraph, 2017.
[Prabhakar et al. 19] A Fast, Scalable, and Reliable Deghosting Method for Extreme Exposure Fusion, ICCP, 2019.
[Wu et al. 18] Deep High Dynamic Range Imaging with Large Foreground Motions, ECCV, 2018.
[Yan et al. 21] Towards accurate HDR imaging with learning generator constraints, Neurocomputing, 2020.
[Yan et al. 19] Attention-guided Network for Ghost-free High Dynamic Range Imaging, CVPR, 2019.
[Rosh et al. 19] Deep Multi-Stage Learning for HDR With Large Object Motions, ICCP, 2019.
[Xu et al. 20] MEF-GAN: Multi-Exposure Image Fusion via Generative Adversarial Networks, TIP, 2020.
[Eilertsen et al. 17] HDR image reconstruction from a single exposure using deep CNNs, Siggraph, 2017.
[Santas et al. 20] Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss, Siggraph, 2020.
[Endo et al. 17] Deep Reverse Tone Mapping, Siggraph, 2017.
[Liu et al. 20] Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline, CVPR, 2020.
[Metzler] Deep Optics for Single-shot High-dynamic-range Imaging, CVPR, 2020.
[Kim et al. 18] A Multi-purpose Convolutional Neural Network for Simultaneous Super-Resolution and High Dynamic Range Image Reconstruction, ACCV, 2018.
[Kim et al. 19] Deep sr-itm: Joint learning of superresolution and inverse tone-mapping for 4k uhd hdr applications, ICCV,2019.
[Kim et al. 20] JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video, AAAI, 2020.
[Kim et al. 20] End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images, AAAI, 2020.
[Chen et al. 21] HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset, ICCV, 2021.
[Jiang et al. 21] HDR Video Reconstruction with Tri-Exposure Quad-Bayer Sensors, Arxiv, 2021.
[Wu et al. 20] Recent advances in deep learning for object detection, Neurocomputing, 2020.
[Girshick et al. 15] Fast R-CNN, ICCV, 2015.
[Ghodrati et al. 15] DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers, ICCV, 2015.
[Ren et al. 15] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, NIPS, 2016.
[Kong et al. 16] HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection, CVPR, 2016.
[He et al. 14] Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, ECCV, 2014.
[Cai et al. 18] Cascade R-CNN: Delving into High Quality Object Detection, CVPR, 2018.
[Redmon et al. 16] You Only Look Once: Unified, Real-Time Object Detection, CVPR, 2016.
[Liu et al. 16] SSD: Single Shot MultiBox Detector, ECCV, 2016.
[Lin et al. 18] Focal Loss for Dense Object Detection (RetinaNet), CVPR, 2018.
[Redmon et al. 16] YOLO9000: Better, Faster, Stronger, Arxiv, 2017.
[Law et al. 19] CornerNet: Detecting Objects as Paired Keypoints,IJCV, 2019.
[He et al. 15] Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition, IEEE TPAMI, 2015.
[Long et al. 16] R-FCN: Object Detection via Region-based Fully Convolutional Networks, NIPS, 2016.
[Lin et al. 17] Feature Pyramid Networks for Object Detection, CVPR, 2017.
[He et al. 18] Mask R-CNN, ICCV, 2018.
[Chen et al. 19] Towards Accurate One-Stage Object Detection with AP-Loss, CVPR, 2019.
[Redmon et al. 18] YOLOv3: An Incremental Improvement, Arxiv, 2018.
[Chen et al. 19] Learning Efficient Object Detection Models with Knowledge Distillation, NIPS, 2019.
[Kang et al. 21] Instance-Conditional Knowledge Distillation for Object Detection, NIPS, 2021.
[Fang et al. 21] You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection, NIPS, 2021.
[Ge et al. 21] YOLOX: Exceeding YOLO Series in 2021, Arxiv, 2021.
[Pramanik et al. 22] Granulated RCNN and Multi-Class Deep SORT for Multi-Object Detection and Tracking, IEEE TETCI, 2022.
[Wang et al. 21] You Only Learn One Representation: Unified Network for Multiple Tasks, Arxiv, 2021.
[Wang et al. 19] Towards Universal Object Detection by Domain Attention, CVPR, 2019.
[Huang et al. 19] Mask Scoring R-CNN, CVPR, 2019.
[Guo et al. 21] Distilling Object Detectors via Decoupled Features, CVPR, 2021.
[Chen et al. 18] Domain Adaptive Faster R-CNN for Object Detection in the Wild, CVPR, 2018.
[Wang et al. 21] Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection, CVPR,2021.
[Zhou et al. 21] Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework, CVPR, 2021.
[Yang et al. 21] Interactive Self-Training with Mean Teachers for Semi-supervised Object Detection, CVPR, 2021.
[Luo et al. 16] Understanding the Effective Receptive Field in Deep Convolutional Neural Networks, 2016.
[Tang et al. 18] PyramidBox: A Context-assisted Single Shot Face Detector, ECCV, 2018.
[Liu et al. 19] High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection, CVPR, 2019.
[Li et al. 20] Dsfd: Dual shot face detector， CVPR, 2019.
[Wang et al. 20] Hierarchical Pyramid Diverse Attention Networks for Face Recognition, CVPR, 2020.
[Huang et al. 21] When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework, CVPR, 2021.
[Tong et al. 21] FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems, CVPR, 2021.
[Qiu et al. 21] SynFace: Face Recognition with Synthetic Data, ICCV, 2021.
[Song et al. 21] Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network, ICCV, 2021.
[Fabbri et al. 21] MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?, ICCV, 2021.
[Wang et al. 18] Repulsion Loss: Detecting Pedestrians in a Crowd, CVPR, 2018.
[Zhang et al. 18] Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd, ECCV, 2018.
[Liu et al. 19] Adaptive NMS: Refining Pedestrian Detection in a Crowd, CVPR, 2019.
[Zhou et al. 20] Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems, ECCV, 2020.
[Wu et al. 20] Temporal-Context Enhanced Detection of Heavily Occluded Pedestrians, CVPR, 2020.
[Wu et al. 20] Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection, CVPR, 2020.
[Huang et al. 20] NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing, CVPR, 2020.
[Wang et al. 20] Learning Human-Object Interaction Detection using Interaction Points, CVPR, 2020.
[Sundararaman et al. 21] Tracking Pedestrian Heads in Dense Crowd, CVPR, 2020.
[Yan et al. 20] Anchor-Free Person Search, CVPR,2020.
[Gu et al. 18] Learning Region Features for Object Detection, ECCV, 2018.
[Long et al. 15] Fully Convolutional Networks for Semantic Segmentation, CVPR, 2015.
[Noh et al. 15] Learning Deconvolution Network for Semantic Segmentation, ICCV, 2015.
[Badrinarayanan et al. 16] SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation, ICCV, 2016.
[Sun et al. 19] High-Resolution Representations for Labeling Pixels and Regions, CVPR, 2019.
[Zhao et al. 17] Pyramid Scene Parsing Network, CVPR, 2017.
[Chen et al. 18] Rethinking Atrous Convolution for Semantic Image Segmentation (Deeplabv3), CVPR, 2018.
[Visin et al. 16] ReSeg: A Recurrent Neural Network-based Model for Semantic Segmentation, CVPR, 2016.
[Visin et al. 15] ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks, NIPS, 2015.
[Chen et al. 16], Attention to Scale: Scale-aware Semantic Image Segmentation, CVPR, 2016.
[Ghiasi et al. 16] Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation, ECCV, 2016.
[Li et al. 18] Pyramid Attention Network for Semantic Segmentation, BMVC, 2018.
[Fu et al. 19] Dual Attention Network for Scene Segmentation, CVPR, 2019.
[Chen et al. 16] Attention to Scale: Scale-aware Semantic Image Segmentation, ICCV, 2016.
[Wang et al. 20] Deep High-Resolution Representation Learning for Visual Recognition, CVPR, 2020.
[He et al. 17] Mask R-CNN, ICCV, 2017.
[Yuan et al. 18] OCNet: Object Context Network for Scene Parsing, CVPR, 2019.
[Wang et al. 20] Dual Super-Resolution Learning for Semantic Segmentation, CVPR, 2020.
[Liu et al. 19] Structured Knowledge Distillation for Semantic Segmentation, CVPR, 2019.
[Wang et al. 20] Intra-class Feature Variation Distillation for Semantic Segmentation, ECCV, 2020.
[Xu et al. 18] Deep Affinity Net: Instance Segmentation via Affinity,ECCV, 2018.
[Quali et al. 20] Semi-Supervised Semantic Segmentation with Cross-Consistency Training, CVPR, 2020.
[Zhao et al. 19] Multi-source Domain Adaptation for Semantic Segmentation, NIPS, 2019.
[Chen et al. 19] CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency, CVPR, 2019.
[Choi et al. 19] Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation, ICCV, 2019.
[Xu et al. 19] Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation, AAAI, 2019.
[Csurka et al. 21] Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey, Arxiv, 2021.
[Araslanov et al. 21] Self-supervised Augmentation Consistency for Adapting Semantic Segmentation, CVPR, 2021.
[Chan et al. 20] A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains, IJCV, 2020.
[He et al. 21] Deep Learning based 3D Segmentation: A Survey, Arxiv, 2021.
[Minaee et al. 20] Image Segmentation Using Deep Learning: A Survey, Arxiv, 2020.
[Huang et al. 19] CCNet: Criss-Cross Attention for Semantic Segmentation, ICCV, 2019.
[Zhu et al. 19] Asymmetric Non-local Neural Networks for Semantic Segmentation, ICCV, 2019.
[Du et al. 19] SSF-DAN: Separated Semantic Feature based Domain Adaptation Network for Semantic Segmentation, ICCV, 2019.
[Ibrahim et al. 20] Semi-Supervised Semantic Image Segmentation with Self-correcting Networks, CVPR,2020.
[He et al. 21] Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation, CVPR, 2021.
[Liu et al. 21] Source-Free Domain Adaptation for Semantic Segmentation, CVPR, 2021.
[Liu et al. 21] Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning, ICCV, 2021.
[Chen et al. 18] ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes, CVPR, 2018.
[Wang et al. 21] Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation, AAAI, 2021.
[Kundu et al. 21] Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation, ICCV, 2021.
[Wang et al. 20]
Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation, CVPR, 2020.
[Sun et al. 21] ECS-Net: Improving Weakly Supervised Semantic Segmentation by Using Connections Between Class Activation Maps, ICCV, 2021.
[Chang et al. 20] Weakly-Supervised Semantic Segmentation via Sub-category Exploration, CVPR, 2020.
[Zhang et al. 20] Learning to See in the Dark with Events, ECCV, 2020.
[Rebacq et al. 19] High Speed and High Dynamic Range Video with an Event Camera, IEEE TPAMI (CVPR), 2019.
[Wang et al. 20] Event Enhanced High-Quality Image Recovery, ECCV, 2020.
[Wang et al. 19] Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks, CVPR, 2019.
[Wang et al. 20] EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning, CVPR, 2020.
[Kim et al. 22] Event-guided Deblurring of Unknown Exposure Time Videos, Arxiv, 2022.
[Mostafavi et al. 21] Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds, ICCV, 2021.
[Wang et al. 21] Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation, ICCV, 2021.
[Han et al. 21] EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-resolution, ICCV, 2021.
[Gehrig et al. 21] Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction, ICRA, 2021.
[Alonso et al. 19] EV-SegNet: Semantic Segmentation for Event-based Cameras, CVPR, 2019.
[Xu et al. 21] Motion Deblurring with Real Events, ICCV, 2021.
[Lin et al. 20] Learning Event-Driven Video Deblurring and Interpolation, ECCV, 2020.
[Federico et al. 21] Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy, CVPR, 2021.
[Jing et al. 21] Turning Frequency to Resolution: Video Super-resolution via Event Cameras, CVPR, 2021.
[Zou et al. 21] Learning to Reconstruct High Speed and High Dynamic Range Videos from Events, CVPR, 2021.
[Chen et al. 21] Indoor Lighting Estimation using an Event Camera, CVPR, 2021.
[Zhang et al. 21] Event-based Synthetic Aperture Imaging with a Hybrid Network, CVPR, 2021.
[Tulyakov et al. 21] Time Lens: Event-based Video Frame Interpolation, CVPR, 2021.
[Shang et al. 21] Bringing Events into Video Deblurring with Non-consecutively Blurry Frames, ICCV, 2021.
[Xu et al. 21] Motion Deblurring with Real Events, ICCV, 2021.
[Yu et al. 21] Training Weakly Supervised Video Frame Interpolation with Events, ICCV, 2021.
[Li et al. 21] Event Stream Super-Resolution via Spatiotemporal Constraint Learning, ICCV, 2021.
[Weng et al. 21] Event-based Video Reconstruction Using Transformer, ICCV, 2021.
[Zou et al. 21] EventHPE: Event-based 3D Human Pose and Shape Estimation, ICCV, 2021.
[Zhang et al. 21] Object Tracking by Jointly Exploiting Frame and Event Domain, ICCV, 2021.
[Kuang et al. 19] Thermal Infrared Colorization via Conditional Generative Adversarial Network， ICCP, 2019.
[Nniaz et al.20] ThermalGAN: Multimodal Color-to-Thermal Image Translation for Person Re-Identification in Multispectral Dataset, ECCV,2018.
[Li et al. 19] Segmenting Objects in Day and Night: Edge-Conditioned CNN for Thermal Image Semantic Segmentation, IEEE TNNLS, 2019.
[Wang et al. 20] Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification, AAAI,2020.
[Deng et al. 21] FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation, ICRA, 2021.
[Sun et al. 20] FuseSeg: Semantic Segmentation of Urban Scenes Based on RGB and Thermal Data Fusion, IEEE TASE, 2020.
[Zhang et al. 21] ABMDRNet: Adaptive-weighted Bi-directional Modality Difference Reduction Network for RGB-T Semantic Segmentation, CVPR, 2021.
[Wang et al. 20] BiFuse: Monocular 360◦ Depth Estimation via Bi-Projection Fusion, CVPR, 2020.
[Deng et al. 21] LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution, CVPR, 2021.
[Lee et al. 19] SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360◦ Images, CVPR, 2019.
[Cohen et al. 18] SPHERICAL CNNS, ICLR, 2018.
[Chen et al. 18] Cube Padding for Weakly-Supervised Saliency Prediction in 360◦ Videos, CVPR, 2018.
[Jeon et al. 18] Deep Upright Adjustment of 360 Panoramas Using Multiple Roll Estimations, ACCV, 2018
[Davidson et al. 20] 360o Camera Alignment via Segmentation, ECCV, 2020.
[Su et al. 18] Learning Spherical Convolution for Fast Features from 360° Imagery, NIPS, 2018.
[Tateno et al. 18] Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images, ECCV, 2018.
[Ghose et al. 19] Pedestrian Detection in Thermal Images using Saliency Maps, CVPR, 2019.
[Kieu et al. 20] Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery, ECCV, 2020.
[Li et al. 20] Full-Time Monocular Road Detection Using Zero-Distribution Prior of Angle of Polarization, ECCV, 2020.
[Choi et al. 20] Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification, CVPR, 2020.
[Wu et al. 21] Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification, CVPR, 2021.
[Chen et al. 21] Neural Feature Search for RGB-Infrared Person Re-Identification, CVPR, 2021.
[Ye et al. 21] Channel Augmented Joint Learning for Visible-Infrared Recognition, ICCV, 2021.
[Fu et al. 21] CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification, ICCV, 2021.
[Wei et al.21] Syncretic Modality Collaborative Learning for Visible Infrared Person Re-Identification, ICCV, 2021.
[Park et al. 21] Visible-Infrared Person Re-identification using Cross-Modal Correspondences, ICCV, 2021.
[Ye et al. 20] Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification, ECCV, 2020.
[Kieu et al. 20] Task-conditioned Domain Adaptation for Pedestrian Detection in Thermal Imagery, ECCV, 2020.
[Wu et al. 20] Infrared-Visible Cross-Modal Person Re-Identification with an X Modality, AAAI, 2020.
[Wang et al. 19] RGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment, ICCV, 2019.
[Feng et al. 20] Learning Modality-Specific Representations for Visible-Infrared Person Re-Identification, IEEE TIP, 2020.
[Ye et al. 20] Cross-Modality Person Re-Identification via Modality-aware Collaborative Ensemble Learning, IEEE TIP, 2020.
[Wang et al. 19] Learning to Reduce Dual-level Discrepancy for Infrared-Visible Person Re-identification, CVPR, 2019.
[Jin et al. 20] Geometric Structure Based and Regularized Depth Estimation From 360◦ Indoor Imagery, CVPR, 2020.
[Deng et al. 21] LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution, CVPR, 2021.
[Sun et al. 21] HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features, CVPR, 2021.
[Yang et al. 21] Capturing Omni-Range Context for Omnidirectional Segmentation, CVPR, 2021.
[Yang et al. 21] Is Context-Aware CNN Ready for the Surroundings? Panoramic Semantic Segmentation in the Wild, IEEE TIP, 2021.
[Li et al. 21] Looking here or there? Gaze Following in 360-Degree Images, ICCV, 2021.
[Djilali et al. 21] Rethinking 360° Image Visual Attention Modelling with Unsupervised Learning, ICCV, 2021.
[Tran et al. 21] SSLayout360: Semi-Supervised Indoor Layout Estimation from 360◦ Panorama, CVPR, 2021.
[Ming et al. 21] Deep learning for monocular depth estimation: A review, Neurocomputing, 2021.
[Eigen et al.], “Depth Map Prediction from a Single Image using a Multi-Scale Deep Network”, NeurIPS, 2014.
[Laina et al. 16] Deeper depth prediction with fully convolutional residual networks, 3D vision,2016.
[Fu et al. 18] Deep Ordinal Regression Network for Monocular Depth Estimation, CVPR, 2018.
[Ren et al. 18] Pyramid Stereo Matching Network, CVPR, 2018.
[Jung et al. 17] Depth prediction from a single image with conditional adversarial networks, ICIP, 2017.
[Dosovitskiy et al. 15] Flownet: Learning optical flow with convolutional networks, ICCV, 2015.
[Ilg et al. 15] FlowNet 2.0: Evolution of Optical Flow Estimation With Deep Networks, CVPR, 2017.
[[Ilg et al. 18] Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation, ECCV, 2018.
[Ranjan et al. 17] Optical Flow Estimation using a Spatial Pyramid Network, CVPR, 2017.
[Xu et al. 18] Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation, CVPR, 2018.
[Godard et al. 17] Unsupervised Monocular Depth Estimation with Left-Right Consistency, CVPR, 2017.
[Kuznietsov et al. 17] Semi-Supervised Deep Learning for Monocular Depth Map Prediction, CVPR, 2017.
[Pilzer et al. 19] Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation, CVPR, 2019.
[Cun et al. 20] Defocus Blur Detection via Depth Distillation, ECCV, 2020.
[Ranftl et al. 21] Vision Transformers for Dense Prediction, CVPR, 2021.
[Meng et al. 19] SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception, CVPR, 2019.
[Liu et al. 21] Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation, ICCV, 2021.
[Huynh et al. 20] Guiding Monocular Depth Estimation Using Depth-Attention Volume, ECCV, 2020.
[Watson et al. 20] Learning Stereo from Single Images, ECCV, 2020.
[YUan et al. 20], Efficient Dynamic Scene Deblurring Using Spatially Variant Deconvolution
Network with Optical Flow Guided Training, CVPR, 2020.
[Yan et al. 20] Optical Flow in Dense Foggy Scenes Using Semi-Supervised Learning, CVPR, 2020.
[Aleotti et al. 21] Learning optical flow from still images, CVPR, 2021.
[Luo et al. 21] UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning, CVPR, 2021.
[Goodfellow et al. 15] Explaining and harnessing adversarial examples, ICLR, 2015.
[Szegedy et al. 14] Intriguing properties of neural networks, ICLR, 2014.
[Su et al. 17] One pixel attack for fooling deep neural networks, Arxiv, 2017.
[Karmon et al. 18] LaVAN: Localized and Visible Adversarial Noise, ICML, 2018.
[Xie et al. 17] Adversarial Examples for Semantic Segmentation and Object Detection, ICCV, 2017.
[Moosavi et al. 17] Universal adversarial perturbations, ICCV, 2017.
[Poursaeed et al. 18] Generative Adversarial Perturbations, CVPR, 2018.
[Chen et al. 18] ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector, ECML PKDD, 2018.
[Chao et al. 19] Generating Adversarial Examples with Adversarial Networks, IJCAI, 2019.
[Wang et al. 21] Psat-gan: Efficient adversarial attacks against holistic scene understanding, IEEE TIP, 2021.
[Carli et al. 17] Towards Evaluating the Robustness of Neural Networks, Axiv, 2017.
[Xiao et al. 18] SPATIALLY TRANSFORMED ADVERSARIAL EXAMPLES, ICLR,2018.
[Zhou et al. 20] DaST: Data-Free Substitute Training for Adversarial Attacks, CVPR, 2020.
[Naseer et al. 20] A Self-supervised Approach for Adversarial Robustness, CVPR, 2020.
[Zi et al. 21]
Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better, CVPR, 2021.
[Mahmood et al. 21] On the Robustness of Vision Transformers to Adversarial Examples, ICCV, 2021.
[Wang et al. 21] Feature Importance-aware Transferable Adversarial Attacks, ICCV, 2021.
[Mao et al. 20] Multitask Learning Strengthens Adversarial Robustness, ECCV, 2020
[Arnab et al. 18] On the Robustness of Semantic Segmentation Models to Adversarial Attacks, CVPR, 2018.
[He et al. 19] Biomedical Image Segmentation against Adversarial Attacks, AAAI, 2019.
[Joshi et al. 19] Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers, CVPR, 2019.
[Shamsabadi et al. 20] ColorFool: Semantic Adversarial Colorization, CVPR, 2020.