In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Puerto Rico June pages Ego Motion Estimation Using Optical Flow Fields Observed from Multiple Cameras

By T. Tsao, Yi, Ping-Tao Hung, Chiou, Shann Fuh, Yong, Sheng Chen. 2005

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth (2021, methodology): “Skip connections were first introduced in ResNets [HZRS16a], ever since, it has been used to facilitate optimization in deep networks [HZRS16b, VWB16b, BFL18].”
Real-World Image Datasets for Federated Learning (2019, background): “, 2014], image caption [Karpathy and Fei-Fei, 2015], object tracking [Kang et al.”
DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks (2019, methodology): “Bounding the perturbation magnitude is a common practice to stabilize GAN training [Isola et al., 2017].”
Evolving Robust Neural Architectures to Defend from Adversarial Attacks (2019, methodology): “Most of the algorithms for NAS are either based on reinforcement learning [Pham et al., 2018; Zoph et al., 2018] or evolutionary computation [Real et al.”
Complementary Learning for Overcoming Catastrophic Forgetting Using Experience Replay (2019, background): “For these reasons, common distribution distance measures such as KL divergence and Jensen–Shannon divergence are not suitable [Kolouri et al., 2018].”
Knowledge Aware Semantic Concept Expansion for Image-Text Matching (2019, methodology): “We use a multi-label images classification model [Wang et al., 2017] to detect whether a concept appears in an image.”
Learning to Solve NP-Complete Problems - A Graph Neural Network for the Decision TSP (2018, background): “…much in the last decade, advancing the state-of-the art of areas such as image recognition (Krizhevsky et al. 2012; Simonyan and Zisserman 2014; Li et al. 2015), natural language processing (Cho et al. 2014b; Cho et al. 2014a; Bahdanau et al. 2014) and reinforcement learning (Mnih et al. 2013;…”
Degeneration in VAE: in the Light of Fisher Information Loss (2018, methodology): “He et al. (2016); Huang et al. (2016) point out the vanishing-gradient problem that prevents the neural network from going deeper, and introduce residual connections to help training of very deep neural networks.”
Self-Supervised Tuning for Few-Shot Segmentation (2020, background): “Recently, semantic segmentation models [Long et al., 2015] have made great progress under full supervision, and some of them have even surpassed the level of human recognition.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, methodology): “Chen and Li [Chen and Li, 2018] further proposed a progressively complementarity-aware fusion network for RGB-D salient object detection, which is more effective than early-fusion methods [Hou et al., 2017] and late-fusion methods [Han et al.”
Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations (2018, methodology): “Techniques have been developed to invert the network by constructing images that activate the network identically [Mahendran and Vedaldi, 2015], or maximally [Erhan et al.”
Self-weighted Multiview Clustering with Multiple Graphs (2017, background): “Recently, [Nie et al., 2014a; Feng et al., 2014; Chen and Dy, 2016; Nie et al., 2016b] have leveraged this property in different ways.”
Using Explanations to Improve Ensembling of Visual Question Answering Systems (2017, methodology): “We also compare against two other state-of-the-art VQA systems not used in our ensemble: iBOWIMG [Zhou et al. , 2015] and DPPNet [Noh et al. , 2016]. iBOWIMG uses softmax over the bag-of-words representation of the question concatenated with GoogleNet [Szegedy et al. , 2015] image features and…”
MineRL: A Large-Scale Dataset of Minecraft Demonstrations (2019, methodology): “, 2018], domain alignment methods [Wang et al., 2018], or carefully designing real-world environments to allow for the required number of trials [Levine et al.”
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling (2018, background): “, 2016] and residual connection [He et al., 2016b] are applied.”
VR-Goggles for Robots: Real-to-Sim Domain Adaptation for Visual Control (2018, background): “3, we show the temporal error maps, the same metric as in [Huang et al., 2017], of two stylized consecutive frames for each method.”
GeniePath: Graph Neural Networks with Adaptive Receptive Paths (2018, methodology): “Convolutional Neural Networks (CNN) have been proven successful in a diverse range of applications involving images (He et al. 2016a) and sequences (Gehring et al. 2016).”
Image Data Augmentation for Deep Learning: A Survey (2022, methodology): “In this experiment, we compare the classification accuracy with and without augmentation on several widely used image classification techniques, including Wide-ResNet [Zagoruyko and Komodakis, 2016], DenseNet [Huang et al., 2017], and Shake ResNet [Gastaldi, 2017].”
Human Gaze Assisted Artificial Intelligence: A Review (2020, background): “, 2019b] and videos [Yu et al., 2017], as well as visual question answering [Qiao et al.”