[31] Multimodal Motion Prediction with Stacked Transformers
标题 |堆叠式变压器的多模态运动预测
链接 | https://arxiv.org/abs/2103.11624
[32] Progressive and Aligned Pose Attention Transfer for Person Image Generation
标题 | 用于人图像生成的渐进式和对齐式姿势注意转移
链接 | https://arxiv.org/abs/2103.11622
[33] Anchor-Free Person Search
标题 | 无锚人搜索
链接 | https://arxiv.org/abs/2103.11617
[34] A Survey of Hand Crafted and Deep Learning Methods for Image Aesthetic Assessment
标题 | 手工和深度学习方法用于图像美学评估的概述
链接 | https://arxiv.org/abs/2103.11616
[35] PriorityCut: Occlusion-guided Regularization for Warp-based Image Animation
标题 | PriorityCut：基于扭曲的图像动画的遮挡引导正则化
链接 | https://arxiv.org/abs/2103.11600
[36] Human De-occlusion: Invisible Perception and Recovery for Humans
标题 | 消除人为遮挡：对人类的无知觉和恢复
链接 | https://arxiv.org/abs/2103.11597
[37] Deep Neural Networks Learn Meta-Structures to Segment Fluorescence Microscopy Images
标题 | 深度神经网络学习元结构以分割荧光显微镜图像
链接 | https://arxiv.org/abs/2103.11594
[38] Delving into Variance Transmission and Normalization: Shift of Average Gradient Makes the Network Collapse
标题 | 深入研究方差传递和归一化：平均梯度的偏移会使网络崩溃
链接 | https://arxiv.org/abs/2103.11590
[39] Brain Image Synthesis with Unsupervised Multivariate Canonical CSCℓ4Net
标题 | 无监督多元规范CSCℓ4Net的脑图像合成
链接 | https://arxiv.org/abs/2103.11587
[40] Neural Lumigraph Rendering
标题 | 神经发光仪渲染
链接 | https://arxiv.org/abs/2103.11571
[41] Cluster Contrast for Unsupervised Person Re-Identification
标题 | 无监督人员重新识别的聚类对比
链接 | https://arxiv.org/abs/2103.11568
[42] Context-aware Biaffine Localizing Network for Temporal Sentence Grounding
标题 | 上下文感知的Biaffine本地化网络，用于临时句接地
链接 | https://arxiv.org/abs/2103.11555
[43] ISTA-Net++: Flexible Deep Unfolding Network for Compressive Sensing
标题 | ISTA-Net ++：灵活的深度展开网络，用于压缩传感
链接 | https://arxiv.org/abs/2103.11554
[44] Unsupervised and self-adaptative techniques for cross-domain person re-identification
标题 | 用于跨域人员重新识别的无监督和自适应技术
链接 | https://arxiv.org/abs/2103.11520
[45] MoViNets: Mobile Video Networks for Efficient Video Recognition
标题 | MoViNets：用于有效视频识别的移动视频网络
链接 | https://arxiv.org/abs/2103.11511
[46] Paying Attention to Activation Maps in Camera Pose Regression
标题 |注意相机姿势回归中的激活图
链接 | https://arxiv.org/abs/2103.11477
[47] #PraCegoVer: A Large Dataset for Image Captioning in Portuguese
标题 | #PraCegoVer：葡萄牙语图像字幕的大型数据集
链接 | https://arxiv.org/abs/2103.11474
[48] Conditional Generative Adversarial Networks for Speed Control in Trajectory Simulation
标题 | 弹道仿真中速度控制的条件生成对抗网络
链接 | https://arxiv.org/abs/2103.11471
[49] Learning Multi-Scene Absolute Pose Regression with Transformers
标题 | 用变压器学习多场景绝对姿势回归
链接 | https://arxiv.org/abs/2103.11468
[50] UAV Images Dataset for Moving Object Detection from Moving Cameras
标题 |无人机图像数据集，用于从移动摄像机检测移动物体
链接 | https://arxiv.org/abs/2103.11460
[51] Traffic Camera Calibration via Vehicle Vanishing Point Detection
标题 |通过车辆消失点检测对交通摄像机进行校准
链接 | https://arxiv.org/abs/2103.11438
[52] Responsible AI: Gender bias assessment in emotion recognition
标题 |负责任的AI：情绪识别中的性别偏见评估
链接 | https://arxiv.org/abs/2103.11436
[53] Deep Distribution-preserving Incomplete Clustering with Optimal Transport
标题 | 具有最优传输的深度分布保留不完整聚类
链接 | https://arxiv.org/abs/2103.11424
[54] Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework
标题 | 即时教学：端到端半监督对象检测框架
链接 | https://arxiv.org/abs/2103.11402
[55] Learning Calibrated-Guidance for Object Detection in Aerial Images
标题 | 学习用于空中图像中目标检测的校准指导
链接 | https://arxiv.org/abs/2103.11399
[56] ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning
标题 | ScanMix：通过语义聚类和半监督学习从严重的标签噪声中学习
链接 | https://arxiv.org/abs/2103.11395
[57] Multi-view analysis of unregistered medical images using cross-view transformers
标题 |使用跨视点转换器对未注册的医学图像进行多视点分析
链接 | https://arxiv.org/abs/2103.11390
[58] Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
标题 | 少量图像分类的基于层次表示的查询专用原型网络
链接 | https://arxiv.org/abs/2103.11384
[59] Multi-level Metric Learning for Few-shot Image Recognition
标题 | 多级度量学习的少量镜头识别
链接 | https://arxiv.org/abs/2103.11383
[60] MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation
标题 | MaAST：借助语义变形器进行地图注意以实现有效的视觉导航
链接 | https://arxiv.org/abs/2103.11374