Self-Supervised Video Representation Learning with Meta-Contrastive Network
Comments Accepted to ICCV 2021
期刊&会议
ICCV
International Conference on Computer Vision · 会议 · Computer Vision
Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment
Journal ref ICCV 2021 Camera Ready Version
FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration
Comments Accepted to ICCV 2021 Workshops on Assistive Computer Vision and Robotics. An updated version of arXiv:2008.08324. Code, models and demo videos are available at:https://github.com/facebookresearch/frankmocap
Greedy Gradient Ensemble for Robust Visual Question Answering
Comments Accepted by ICCV 2021. Code: https://github.com/GeraldHan/GGE
Unsupervised Layered Image Decomposition into Object Prototypes
Comments Accepted at ICCV 2021. Project webpage: https://imagine.enpc.fr/~monniert/DTI-Sprites
Exploring Relational Context for Multi-Task Dense Prediction
Comments International Conference on Computer Vision (ICCV) 2021
Robust Object Detection via Instance-Level Temporal Cycle Confusion
Comments ICCV 2021
Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases
Comments ICCV 2021
Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts
Journal ref ICCV 2021
CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification
Comments Accepted by ICCV 2021
KoDF: A Large-scale Korean DeepFake Detection Dataset
Comments Accepted to ICCV 2021
Hybrid Neural Fusion for Full-frame Video Stabilization
Comments ICCV 2021. Project page: https://alex04072000.github.io/FuSta/ Code: https://github.com/alex04072000/FuSta
Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
Comments accepted by ICCV 2021
Focal Frequency Loss for Image Reconstruction and Synthesis
Comments ICCV 2021. GitHub: https://github.com/EndlessSora/focal-frequency-loss Project page: https://www.mmlab-ntu.com/project/ffl/index.html
HeadGAN: One-shot Neural Head Synthesis and Editing
Comments Accepted in IEEE International Conference on Computer Vision 2021 (ICCV 2021)
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
Comments ICCV 2021. Source code at https://github.com/naraysa/D2-Net
Adaptive confidence thresholding for monocular depth estimation
Comments ICCV 2021
Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform
Comments ICCV 2021
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Comments ICCV 2021 camera-ready version
Detecting and Segmenting Adversarial Graphics Patterns from Images
Comments ICCV 2021 Workshop on Adversarial Robustness in the Real World
Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image
Comments To appear at ICCV 2021(IEEE/CVF International Conference on Computer Vision)
LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning
Comments 17 pages, 9 figures, 5 tables. Accepted at The IEEE/CVF International Conference on Computer Vision (ICCV) 2021
Finding Representative Interpretations on Convolutional Neural Networks
Comments Accepted by ICCV 2021 (http://iccv2021.thecvf.com/home) | A python notebook of the proposed method can be found in https://marketplace.huaweicloud.com/markets/aihub/notebook/detail/?id=8e92ea6c-2f4a-4cff-a89f-bf2905bb7ac0
Accelerating Atmospheric Turbulence Simulation via Learned Phase-to-Space Transform
Comments The paper will be published at the ICCV 2021
ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
Comments To appear in ICCV 2021
Active Learning for Deep Object Detection via Probabilistic Modeling
Comments ICCV 2021, includes supplementary material
In-Place Scene Labelling and Understanding with Implicit Scene Representation
Comments Camera ready version. To be published in Proceedings of IEEE International Conference on Computer Vision (ICCV 2021) as Oral Presentation. Project page with more videos: https://shuaifengzhi.com/Semantic-NeRF/
HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset
Comments ICCV 2021: http://guanyingc.github.io/DeepHDRVideo/
3D Human Pose Estimation with Spatial and Temporal Transformers
Comments ICCV 2021
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
Comments 18 pages including appendix and references. 2 figures in the main paper, 1 figure in appendix. Accepted at ICCV 2021
