![](https://img-blog.csdnimg.cn/20201014180756927.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
论文分享
论文分享
NeverMoreH
^_^
展开
-
2020-07-16 CVPR2020 V&L论文讨论(5) 笔记
目录[1] SQuINTing at VQA Models: Introspecting VQA Models with Sub-Questions[2] Iterative Answer Prediction with Pointer-Augmented Multimodal Transformers for Text VQA[3] Syntax-Aware Action Targeting for Video Captioning[4] Modality Shifting Attention Netwo原创 2020-07-17 10:25:34 · 605 阅读 · 0 评论 -
2020-07-15 CVPR2020 表示学习论文讨论(4) 笔记
目录[1] Multi-Scale Fusion Subspace Clustering Using Similarity Constraint[2] Non-Local Neural Networks with Grouped Bilinear Attentional Transforms[3] Neural Networks Are More Productive Teachers Than Human Raters[4] Search to Distill Pearls are Everywhere原创 2020-07-15 16:54:05 · 964 阅读 · 2 评论 -
2020-07-14 CVPR2020 i3DV论文讨论(4) 笔记
目录[1] MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction[2] Upgrading Optical Flow to 3D Scene Flow through Optical Expansion[3] Context Prior for Scene Segmentation[4] CascadePSP: Toward Class-Agnostic a原创 2020-07-14 17:03:36 · 605 阅读 · 0 评论 -
2020-07-09 CVPR2020 V&L论文讨论(4) 笔记
目录[1] Embodied Language Grounding with 3D Visual Feature Representations[2] Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences[3] PhraseCut: Language-based Image Segmentation in the Wild总结[1] Embodied Language Grounding with 3D原创 2020-07-13 09:00:12 · 306 阅读 · 0 评论 -
2020-07-08 CVPR2020 表示学习论文讨论(3) 笔记
目录[1] X-Linear Attention Networks for Image Captioning[2] Select to Better Learn Fast and Accurate Deep Learning using Data Selection from Nonlinear Manifolds[3] AdderNet: Do We Really Need Multiplications in Deep Learning?[4] Optimizing Rank-based Metrics原创 2020-07-08 17:01:56 · 860 阅读 · 0 评论 -
2020-07-07 CVPR2020 i3DV论文讨论(3) 笔记
目录[1] PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization[2] Height and Uprightness Invariance for 3D Prediction from a Single View[3] RoutedFusion: Learning Real-time Depth Map Fusion[4] Information-Driven Direct原创 2020-07-07 18:07:27 · 798 阅读 · 0 评论 -
2020-07-03 CVPR2020 i3DV论文讨论(2) 笔记
目录[1] Context Prior for Scene Segmentation[2] Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness[3] Bi3D: Stereo Depth Estimation via Binary Classification[4] SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth原创 2020-07-03 17:14:48 · 659 阅读 · 1 评论 -
2020-07-02 CVPR2020 V&L论文讨论(3) 笔记
目录[1] Bi-directional Relationship Inferring Network for Referring Image Segmentation[2] A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension[3] Vision-Dialog Navigation by Exploring Cross-modal Memory[4] VQA with N原创 2020-07-02 16:25:04 · 944 阅读 · 0 评论 -
2020-06-18 CVPR2020 V&L论文讨论(1) 笔记
目录CC JJY S[1] Normalized and Geometry-Aware Self-Attention Network for Image Captioning[2] Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension[3] Multi-task Collaborative Network for Joint Referring Expression Comprehension原创 2020-07-02 14:54:22 · 1251 阅读 · 0 评论 -
2020-07-01 CVPR2020 表示学习论文讨论(2) 笔记
目录[1] CVPR2020_A Unified Optimization Framework for Low-Rank Inducing Penaltie[2] CVPR2020_Automatic Neural Network Compression by Sparsity-Quantization Joint[3] CVPR2020_Cogradient Descent for Bilinear Optimization[4] CVPR2020_Adaptive Subspaces for Few-S原创 2020-07-01 17:45:02 · 724 阅读 · 1 评论