EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition

22 Aug 2019ekazakos/temporal-binding-network

We focus on multi-modal fusion for egocentric action recognition, and propose a novel architecture for multi-modal temporal-binding, i. e. the combination of modalities within a range of temporal offsets.

7
22 Aug 2019

Progressive Face Super-Resolution via Attention to Facial Landmark

22 Aug 2019DeokyunKim/Progressive-Face-Super-Resolution

Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images.

FACE ALIGNMENT SUPER RESOLUTION

12
22 Aug 2019

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

22 Aug 2019StephanieWyt/RDGCN

Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods.

ENTITY ALIGNMENT ENTITY EMBEDDINGS KNOWLEDGE GRAPHS

3
22 Aug 2019

Text Summarization with Pretrained Encoders

22 Aug 2019nlpyang/PreSumm

For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained while the latter is not).

 SOTA for Extractive Document Summarization on CNN / Daily Mail (using extra training data)

ABSTRACTIVE TEXT SUMMARIZATION DOCUMENT SUMMARIZATION EXTRACTIVE DOCUMENT SUMMARIZATION

39
22 Aug 2019

Noise Flow: Noise Modeling with Conditional Normalizing Flows

22 Aug 2019BorealisAI/noise_flow

Modeling and synthesizing image noise is an important aspect in many computer vision applications.

9
22 Aug 2019

Limited Data Rolling Bearing Fault Diagnosis with Few-shot Learning

IEEE Access 2019 SNBQT/Limited-Data-Rolling-Bearing-Fault-Diagnosis-with-Few-shot-Learning

In this study, we propose a deep neural network based few-shot learning approach for rolling bearing fault diagnosis with limited data.

FEW-SHOT LEARNING

4
22 Aug 2019

Trajectory Space Factorization for Deep Video-Based 3D Human Pose Estimation

22 Aug 2019jiahaoLjh/trajectory-pose-3d

Although existing CNN-based temporal frameworks attempt to address the sensitivity and drift problems by concurrently processing all input frames in the sequence, the existing state-of-the-art CNN-based framework is limited to 3d pose estimation of a single frame from a sequential input.

3D HUMAN POSE ESTIMATION 3D POSE ESTIMATION

3
22 Aug 2019

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

21 Aug 2019GothicAi/InstaBoost

With the guidance of such map, we boost the performance of R101-Mask R-CNN on instance segmentation from 35. 7 mAP to 37. 9 mAP without modifying the backbone or network structure.

DATA AUGMENTATION INSTANCE SEGMENTATION SEMANTIC SEGMENTATION

72
21 Aug 2019

Testing Robustness Against Unforeseen Adversaries

21 Aug 2019ddkang/advex-uar

We construct novel JPEG, Fog, Gabor, and Snow adversarial attacks to simulate unforeseen adversaries and perform a careful study of adversarial robustness against these and existing distortion types.

ADVERSARIAL DEFENSE

20
21 Aug 2019

Deep High-Resolution Representation Learning for Visual Recognition

20 Aug 2019shijianjian/HRNet_Keras

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.

 SOTA for Semantic Segmentation on Cityscapes (using extra training data)

OBJECT DETECTION POSE ESTIMATION REPRESENTATION LEARNING SEMANTIC SEGMENTATION

3
20 Aug 2019