2005년 대한 생화학·분자생물학회 하계학술대회를 다녀와서

A Short Course in Cloud Physics

Deep-learning based salient object detection methods achieve great progress. However, the variable scale and unknown category of salient objects are great challenges all the time. These are closely related to the utilization of multi-level and multi-scale features. In this paper, we propose the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates. To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit. Besides, the class imbalance issue caused by the scale variation weakens the effect of the binary cross entropy loss and results in the spatial inconsistency of the predictions. Therefore, we exploit the consistency-enhanced loss to highlight the fore-/back-ground difference and preserve the intra-class consistency. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches. The source code will be publicly available at https://github.com/lartpang/MINet.

/pdf/multi-scale-interactive-network-for-salient-object-detection-1a0pmyc6n7.pdf

Multi-Scale Interactive Network for Salient Object Detection

TensorFlow 2.0 in ActionTensorFlow 1.x Deep Learning CookbookMachine Learning with TensorFlow 1.xMachine Learning with TensorFlow, Second EditionTensorFlow 2 Pocket PrimerProgramming with TensorFlowTensorFlow Machine Learning ProjectsHands-On Neural Networks with TensorFlow 2.0TensorFlow for Deep LearningTensor Flow Pocket PrimerNatural Language Processing with TensorFlowTensorFlow: Powerful Predictive Analytics with TensorFlowHands-On Convolutional Neural Networks with TensorFlowTensorFlow 2.0 Computer Vision CookbookIntelligent Mobile Projects with TensorFlowLearning TensorFlow.jsDeep Learning with TensorFlow 2 and KerasLearning TensorFlowTensorFlow 2 Pocket ReferenceMachine Learning Using TensorFlow CookbookTensorFlow 2.0 Quick Start GuideTensorFlow Machine Learning CookbookLearn TensorFlow 2.0Learn TensorFlow in 24 HoursHands-On Computer Vision with TensorFlow 2Mastering Computer Vision with TensorFlow 2.xPro Deep Learning with TensorFlowHands-On Machine Learning with TensorFlow.jsTensorFlow for Deep LearningTinyMLLearning TensorFlow.jsDeep Learning with TensorFlow 2 and Keras Second EditionDeep Learning with TensorFlowMastering TensorFlow 1.xAdopting TensorFlow for Real-World AITensorFlow For DummiesArtificial Intelligence with PythonHands-On Machine Learning with Scikit-Learn, Keras, and TensorFlowLearn TensorFlow EnterpriseThe TensorFlow Workshop

구글 TensorFlow 소개

Multivariate time series forecasting via attention-based encoder–decoder framework

LSTM-based traffic flow prediction with missing data

Traffic flow prediction using LSTM with feature enhancement

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to video sequences. Prevalent shortcomings include the failure to handle motion blur, video defocus, or pose occlusions, arising from the inability in capturing the temporal dependency among video frames. On the other hand, directly employing conventional recurrent neural networks incurs empirical difficulties in modeling spatial contexts, especially for dealing with pose occlusions. In this paper, we propose a novel multi-frame human pose estimation framework, leveraging abundant temporal cues between video frames to facilitate keypoint detection. Three modular components are designed in our framework. A Pose Temporal Merger encodes keypoint spatiotemporal context to generate effective searching scopes while a Pose Residual Fusion module computes weighted pose residuals in dual directions. These are then processed via our Pose Correction Network for efficient refining of pose estimations. Our method ranks No.1 in the Multi-frame Person Pose Estimation Challenge on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018. We have released our code, hoping to inspire future research.

/pdf/deep-dual-consecutive-network-for-human-pose-estimation-r4978vq0ko.pdf

Deep Dual Consecutive Network for Human Pose Estimation

Joint temporal context exploitation and active learning for video segmentation

Depth-image-based rendering (DIBR) is widely used in 3DTV, free-viewpoint video, and interactive 3D graphics applications. Typically, synthetic images generated by DIBR-based systems incorporate various distortions, particularly geometric distortions induced by object dis-occlusion. Ensuring the quality of synthetic images is critical to maintaining adequate system service. However, traditional 2D image quality metrics are ineffective for evaluating synthetic images as they are not sensitive to geometric distortion. In this paper, we propose a novel no-reference image quality assessment method for synthetic images based on convolutional neural networks, introducing local image saliency as prediction weights. Due to the lack of existing training data, we construct a new DIBR synthetic image dataset as part of our contribution. Experiments were conducted on both the public benchmark IRCCyN/IVC DIBR image dataset and our own dataset. Results demonstrate that our proposed metric outperforms traditional 2D image quality metrics and state-of-the-art DIBR-related metrics.

/pdf/no-reference-synthetic-image-quality-assessment-with-46g9v70yep.pdf

Bailin Yang

Papers

LSTM-based traffic flow prediction with missing data

Traffic flow prediction using LSTM with feature enhancement

Deep Dual Consecutive Network for Human Pose Estimation

Joint temporal context exploitation and active learning for video segmentation

No-reference synthetic image quality assessment with convolutional neural network and local image saliency